{"object":"list","data":[{"id":"openai/gpt-5.6-sol-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Sol Pro (batch)","description":"GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":631.81,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-4o-transcribe","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: GPT-4o Transcribe","description":"GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.","context_window":128000,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"nex-agi/nex-n2.5-mini:free","object":"model","created":1789025613,"owned_by":"nex-agi","display_name":"Nex AGI: Nex-N2.5-Mini (free)","description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file changes, run commands, launch applications, interact with browser and desktop interfaces, and test software from the user's perspective. When observed behavior does not match the intended result, Nex-N2.5 can diagnose the issue, revise its implementation, and test again. This makes it especially effective for autonomous software engineering, GUI-based QA, computer-use automation, deep research, and scientific workflows where success must be demonstrated in the environment—not merely inferred from generated code.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"qwen/qwen3.8-2.4t-a95b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 2.4T A95B","description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"~z-ai/glm-flash-latest","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM Flash Latest","description":"This model always redirects to the latest model in the GLM Flash family.","context_window":1310720,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":31.6,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-6 Astra Pro (batch)","description":"GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-5.3-flash:batch","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3 Flash (batch)","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":31.6,"currency":"RUB","is_free":false}},{"id":"~deepseek/deepseek-v4-flash-latest","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek V4 Flash Latest","description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_window":1310720,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":20.22,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-audio-3.0-tts-plus","object":"model","created":1789025656,"owned_by":"qwen","display_name":"Qwen: Qwen-Audio-3.0-TTS Plus","description":"Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"supported_voices":["longanlingxin","longanlufeng"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":2527.22,"unit":"m characters"}],"is_free":false}},{"id":"tencent/hy4-preview","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy4 preview","description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":105.39,"output_rub_per_million":316.03,"currency":"RUB","is_free":false}},{"id":"sourceful/riverflow-v2-standard-preview","object":"model","created":1783372385,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2 Standard Preview","description":"Riverflow V2 Standard Preview is the standard variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":[],"pricing":{"unit":"unknown","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"sourceful/riverflow-v2-max-preview","object":"model","created":1783372385,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2 Max Preview","description":"Riverflow V2 Max Preview is the most powerful variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":[],"pricing":{"unit":"unknown","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.8:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.8 (batch)","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-fable-5.1:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Fable 5.1 (batch)","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy3","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy3","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.\nTencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":16.68,"output_rub_per_million":66.72,"currency":"RUB","is_free":false}},{"id":"~z-ai/glm-latest","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM Latest","description":"This model always redirects to the latest GLM model from Z.ai.","context_window":1310720,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":137.11,"output_rub_per_million":430.9,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 5 (batch)","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":631.81,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"meta/muse-spark-1.3","object":"model","created":1789025613,"owned_by":"meta","display_name":"Meta: Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed, with an emphasis on concise execution.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":537.04,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.32,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-5.3-flash","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3 Flash","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","context_window":1310720,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":31.6,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.8-flash","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.8 Flash","description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":473.86,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.8-2.4t-a95b:batch","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 2.4T A95B (batch)","description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","context_window":1010000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"inclusionai/ling-3.0-flash","object":"model","created":1789025613,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.0 Flash","description":"Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token.\nThe model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":2.66,"output_rub_per_million":7.97,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-6 Astra (batch)","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy-mt2-7b","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy-MT2-7B","description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"pricing":{"unit":"token","input_rub_per_million":9.36,"output_rub_per_million":37.28,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-flash-preview:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3 Flash Preview (batch)","description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":189.55,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3.8-flash:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.8 Flash (batch)","description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":47.39,"output_rub_per_million":236.93,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3.6-flash","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.6 Flash","description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":473.86,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/voxtral-mini-tts-2603","object":"model","created":1789025656,"owned_by":"mistralai","display_name":"Mistral: Voxtral Mini TTS","description":"Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.","context_window":4096,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"supported_voices":["en_paul_sad","en_paul_neutral","en_paul_happy","en_paul_frustrated","en_paul_excited","en_paul_confident","en_paul_cheerful","en_paul_angry","gb_oliver_neutral","gb_oliver_sad","gb_oliver_excited","gb_oliver_curious","gb_oliver_confident","gb_oliver_cheerful","gb_oliver_angry","gb_jane_sarcasm","gb_jane_confused","gb_jane_shameful","gb_jane_sad","gb_jane_neutral","gb_jane_jealousy","gb_jane_frustrated","gb_jane_curious","gb_jane_confident","fr_marie_sad","fr_marie_neutral","fr_marie_happy","fr_marie_excited","fr_marie_curious","fr_marie_angry"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":2021.78,"unit":"m characters"}],"is_free":false}},{"id":"inclusionai/ling-3.0-flash-fin:free","object":"model","created":1789025613,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.0 Flash Fin (free)","description":"Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment workflows that require complex multi-step tasks and long-horizon planning and execution, while retaining general capabilities in reasoning, coding, and mathematics.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"z-ai/glm-5.3","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.\nReasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.","context_window":1310720,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":176.91,"output_rub_per_million":555.99,"currency":"RUB","is_free":false}},{"id":"tencent/hy-mt2-1.8b","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy-MT2-1.8B","description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"pricing":{"unit":"token","input_rub_per_million":5.56,"output_rub_per_million":22.37,"currency":"RUB","is_free":false}},{"id":"perceptron/perceptron-mk1","object":"model","created":1789025613,"owned_by":"perceptron","display_name":"Perceptron: Perceptron Mk1","description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation.\nReasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the annotation_format parameter (pass \"point\", \"box\", or \"polygon\" for spatial localization on images, or \"clip\" (start/end timestamps) for temporal segments in video). Without annotation_format, the model returns natural-language text only.","context_window":32768,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":189.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-27b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 27B","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":53.08,"output_rub_per_million":379.09,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-lightning","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Lightning","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":10.11,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"tencent/hy-mt2-30b-a3b","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy-MT2-30B-A3B","description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation. It uses 3B active parameters out of 30B total.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"pricing":{"unit":"token","input_rub_per_million":9.36,"output_rub_per_million":37.28,"currency":"RUB","is_free":false}},{"id":"upstage/solar-pro4","object":"model","created":1789025613,"owned_by":"upstage","display_name":"Upstage: Solar Pro 4","description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.","context_window":524288,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":3.8,"output_rub_per_million":15.17,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-27b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-27B","description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":24.65,"output_rub_per_million":197.13,"currency":"RUB","is_free":false}},{"id":"meta/muse-spark-1.2","object":"model","created":1789025613,"owned_by":"meta","display_name":"Meta: Muse Spark 1.2","description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window.\nThe model is built to support multi-agent workflows, whether as either a main agent that plans and delegates or as a subagent executing in parallel. It works across multiple coding harnesses and supports structured output, parallel function calling, and configurable reasoning effort. In Meta’s testing, it performs well on multi-file refactors, extended debugging sessions, whole-repository generation, and tasks that stretch well past a single prompt.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":537.04,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.32,"unit":"1k calls"}],"is_free":false}},{"id":"inclusionai/ling-3.0-flash-fin","object":"model","created":1789025613,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.0 Flash Fin","description":"Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment workflows that require complex multi-step tasks and long-horizon planning and execution, while retaining general capabilities in reasoning, coding, and mathematics.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":22.75,"currency":"RUB","is_free":false}},{"id":"meta/muse-glimmer-30b:batch","object":"model","created":1789025613,"owned_by":"meta","display_name":"Meta: Muse Glimmer 30B (batch)","description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":22.12,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.7-flash","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":3.8,"output_rub_per_million":16.43,"currency":"RUB","is_free":false}},{"id":"meta/muse-spark-1.1","object":"model","created":1789025613,"owned_by":"meta","display_name":"Meta: Muse Spark 1.1","description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.\nThe model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates or as a subagent, and generalizes zero-shot to new tools, MCP servers, and custom skills. It supports structured output, parallel function calling, built-in search with citations, and configurable reasoning effort. Meta reports strong performance on real-world coding across large codebases, computer-use workflows, and visual-to-code generation.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":537.04,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.32,"unit":"1k calls"}],"is_free":false}},{"id":"deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash Vision Exp","description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":27.8,"output_rub_per_million":83.4,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2-1-turbo","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed 2.1 Turbo","description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and video content, with capabilities for planning, debugging, and self-correction.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash-vision-exp:batch","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash Vision Exp (batch)","description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":13.9,"output_rub_per_million":41.7,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2.0-code","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed-2.0-Code","description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude Code, Kilo, and OpenCode.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":379.09,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.3:batch","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3 (batch)","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.\nReasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":88.46,"output_rub_per_million":278,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling-small:batch","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling Small (batch)","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","context_window":524288,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling-small:free","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling Small (free)","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"anthropic/claude-opus-5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-fable-5.1","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Fable 5.1","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":6318.05,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.7-plus","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.7 Plus","description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":40.44,"output_rub_per_million":161.75,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash-0731:batch","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash 0731 (batch)","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":13.9,"output_rub_per_million":41.7,"currency":"RUB","is_free":false}},{"id":"meta/muse-glimmer-30b","object":"model","created":1789025613,"owned_by":"meta","display_name":"Meta: Muse Glimmer 30B","description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":139,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-31b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 4 31B","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":11.38,"output_rub_per_million":42.97,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Claude Opus 5 (batch)","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"rekaai/reka-edge","object":"model","created":1789025613,"owned_by":"rekaai","display_name":"Reka Edge","description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, video analysis, object detection, and agentic tool-use.","context_window":16384,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":12.64,"currency":"RUB","is_free":false}},{"id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","object":"model","created":1789025613,"owned_by":"sentence-transformers","display_name":"Sentence Transformers: multi-qa-mpnet-base-dot-v1","description":"The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-27b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.6 27B","description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs — and supports a 262,144-token context window.\nThe model is designed for agentic coding and reasoning tasks, with particular strength in repository-level code comprehension, front-end development workflows, and multi-step problem solving. It includes a built-in thinking mode for extended reasoning and preserves thinking context across conversation history. Qwen3.6 27B supports 201 languages and dialects and is released under the Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling-small","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling Small","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":56.87,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.1:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.1 (batch)","description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":78.98,"output_rub_per_million":631.81,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"meituan/longcat-2.0","object":"model","created":1789025613,"owned_by":"meituan","display_name":"Meituan: LongCat 2.0","description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows.","context_window":1048756,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Ultra (free)","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.6-luna-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Luna Pro (batch)","description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":75.82,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"poolside/laguna-s-2.1","object":"model","created":1789025613,"owned_by":"poolside","display_name":"Poolside: Laguna S 2.1","description":"Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the OpenMDW-1.1 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\nPlease report security vulnerabilities or safety concerns to [email&#160;protected].\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":11.38,"output_rub_per_million":22.75,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.2","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.2","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\nReasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":122.07,"output_rub_per_million":383.64,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":511.77,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-terra","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"thinkingmachines/inkling:batch","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling (batch)","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","context_window":524288,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":511.77,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-sol-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Sol Pro","description":"GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Ultra","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":78.98,"output_rub_per_million":394.88,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-235b-a22b-2507","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 235B A22B Instruct 2507","description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" (<think> blocks).\nCompared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":27.8,"output_rub_per_million":111.2,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.5","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.5","description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","context_window":500000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"thinkingmachines/inkling:free","object":"model","created":1789025613,"owned_by":"thinkingmachines","display_name":"Thinking Machines: Inkling (free)","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.3-codex","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.3-Codex","description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.\nBeyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":221.14,"output_rub_per_million":1769.06,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":6318.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"moonshotai/kimi-k3:batch","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K3 (batch)","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-pro-image","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","context_window":131072,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.5","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3790.83,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-sonnet-5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-4.20","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.20","description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.\nReasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs","context_window":2000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":315.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"openai/o4-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o4 Mini","description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":139,"output_rub_per_million":555.99,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"sakana/fugu-ultra","object":"model","created":1789025613,"owned_by":"sakana","display_name":"Sakana: Fugu Ultra","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.\nFugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3790.83,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"stepfun/step-3.7-flash","object":"model","created":1789025613,"owned_by":"stepfun","display_name":"StepFun: Step 3.7 Flash","description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":145.32,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-fable-5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":6318.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"~google/gemini-pro-latest","object":"model","created":1789025613,"owned_by":"google","display_name":"Google Gemini Pro Latest","description":"This model always redirects to the latest model in the Google Gemini Pro family.","context_window":1048576,"modalities":["text"],"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-4.8","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-5-turbo","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5 Turbo","description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.","context_window":202752,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":151.64,"output_rub_per_million":505.45,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large-2407","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral Large 2407","description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.","context_window":131072,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-luna:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Luna (batch)","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":75.82,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"minimax/minimax-m3","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M3","description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"~moonshotai/kimi-latest","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI Kimi Latest","description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":303.27,"output_rub_per_million":1516.33,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-3.0","object":"model","created":1789025613,"owned_by":"aion-labs","display_name":"AionLabs: Aion-3.0","description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"inception/mercury-2","object":"model","created":1789025613,"owned_by":"inception","display_name":"Inception: Mercury 2","description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).\nInstead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost.\nMercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the blog post.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Mini (batch)","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":47.39,"output_rub_per_million":284.32,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-build-0.1","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok Build 0.1","description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers SpaceXAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.","context_window":256000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":252.73,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemma-4-31b-it:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 4 31B (batch)","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":49.29,"output_rub_per_million":122.58,"currency":"RUB","is_free":false}},{"id":"microsoft/mai-voice-2","object":"model","created":1789025656,"owned_by":"microsoft","display_name":"MicrosoftAI: MAI-Voice-2","description":"MAI-Voice-2 is an expressive text-to-speech model from Microsoft. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18 locales,...","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_completion_tokens","max_tokens","temperature","top_p"],"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":2779.94,"unit":"m characters"}],"is_free":false}},{"id":"qwen/qwen3.6-35b-a3b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.6 35B A3B","description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":113.73,"currency":"RUB","is_free":false}},{"id":"ibm-granite/granite-4.2-8b","object":"model","created":1789025613,"owned_by":"ibm-granite","display_name":"IBM: Granite 4.2 8B","description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort, and non-thinking modes.\nThe model supports 12 languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":31.6,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-content-safety","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Content Safety","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.\nIt is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-image-2","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Image 2","description":"GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and visual generation within the same interaction.","context_window":272000,"modalities":["image","text"],"input_modalities":["image","text","file"],"output_modalities":["image","text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","top_logprobs"],"pricing":{"unit":"token","input_rub_per_million":1010.89,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-next-80b-a3b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Next 80B A3B Instruct","description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.\nThe model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":11.38,"output_rub_per_million":139,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4-pro","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Pro","description":"Recraft V4 Pro is an image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios, double the resolution of...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":31.6,"unit":"image"}],"is_free":false}},{"id":"google/gemini-3.7-flash:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.7 Flash (batch)","description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":47.39,"output_rub_per_million":236.93,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-sol:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Sol (batch)","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":631.81,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"cohere/north-mini-code:free","object":"model","created":1789025613,"owned_by":"cohere","display_name":"Cohere: North Mini Code (free)","description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.\nIt offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.","context_window":256000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"mistralai/codestral-2508","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Codestral 2508","description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\nBlog Post","context_window":256000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":113.73,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1 (batch)","description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":505.45,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"aion-labs/aion-3.0-mini","object":"model","created":1789025613,"owned_by":"aion-labs","display_name":"AionLabs: Aion-3.0-Mini","description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":88.46,"output_rub_per_million":176.91,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-pro-preview-customtools","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Pro Preview Custom Tools","description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows.\nIt retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.","context_window":1048576,"modalities":["text"],"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","is_free":false}},{"id":"poolside/laguna-xs-2.1","object":"model","created":1789025613,"owned_by":"poolside","display_name":"Poolside: Laguna XS 2.1","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the OpenMDW-1.1 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\nPlease report security vulnerabilities or safety concerns to [email&#160;protected].\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":15.17,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.5-flash:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.5 Flash (batch)","description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":568.63,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"google/lyria-3-pro-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Lyria 3 Pro Preview","description":"Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Pro can generate full-length songs with verses, choruses, bridges.","context_window":1048576,"modalities":["text","audio"],"input_modalities":["text","image"],"output_modalities":["text","audio"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Song Generation","price_rub":10.11,"unit":"song"}],"is_free":false}},{"id":"anthropic/claude-opus-4.1:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.1 (batch)","description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":947.71,"output_rub_per_million":4738.54,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"poolside/laguna-xs-2.1:free","object":"model","created":1789025613,"owned_by":"poolside","display_name":"Poolside: Laguna XS 2.1 (free)","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.\nLaguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the OpenMDW-1.1 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\nPlease report security vulnerabilities or safety concerns to [email&#160;protected].\nIf you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"moonshotai/kimi-k2.7-code","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2.7 Code","description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":89.72,"output_rub_per_million":442.27,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.7-max","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.7 Max","description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":186.39,"output_rub_per_million":559.15,"currency":"RUB","is_free":false}},{"id":"upstage/solar-pro-3","object":"model","created":1789025613,"owned_by":"upstage","display_name":"Upstage: Solar Pro 3","description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.5-flash","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.5 Flash","description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":189.55,"output_rub_per_million":1137.25,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"deepseek/deepseek-v4-pro","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.\nBuilt on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":120.71,"output_rub_per_million":241.42,"currency":"RUB","is_free":false}},{"id":"~openai/gpt-mini-latest","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI GPT Mini Latest","description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":568.63,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3-5:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Medium 3.5 (batch)","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":473.86,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.5-flash-lite:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.5 Flash Lite (batch)","description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":157.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"~google/gemini-flash-latest","object":"model","created":1789025613,"owned_by":"google","display_name":"Google Gemini Flash Latest","description":"This model always redirects to the latest model in the Google Gemini Flash family.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":473.86,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/mistral-large-2512","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Large 3 2512","description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":189.55,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-pro-0813:batch","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Pro 0813 (batch)","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":83.4,"output_rub_per_million":250.2,"currency":"RUB","is_free":false}},{"id":"tencent/hy3-preview","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hy3 preview","description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":22.75,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4.1-utility-pro","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1 Utility Pro","description":"Recraft V4.1 Utility Pro is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios — double...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":26.54,"unit":"image"}],"is_free":false}},{"id":"moonshotai/kimi-k2.6","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2.6","description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":120.05,"output_rub_per_million":505.45,"currency":"RUB","is_free":false}},{"id":"arcee-ai/trinity-large-thinking","object":"model","created":1789025613,"owned_by":"arcee-ai","display_name":"Arcee AI: Trinity Large Thinking","description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7\nThis model is optimized for agentic workflows and performs best when reasoning is preserved (aka interleaved thinking). Learn how to preserve reasoning in our docs: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":101.09,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-super-120b-a12b","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Super","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":10.75,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-lite-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Flash Lite Preview","description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":189.55,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-4.7","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.7","description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\nFor users upgrading from earlier Opus versions, see our official migration guide here","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.4","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4","description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","context_window":1050000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-9b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-9B","description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":18.96,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2.0-mini","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed-2.0-Mini","description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding, and is optimized for lightweight tasks where cost and speed take priority.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-32b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 32B Instruct","description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text comprehension, enabling fine-grained spatial reasoning, document and scene analysis, and long-horizon video understanding.Robust OCR in 32 languages, and enhanced multimodal fusion through Interleaved-MRoPE and DeepStack architectures. Optimized for agentic interaction and visual tool use, Qwen3-VL-32B delivers state-of-the-art performance for complex real-world multimodal tasks.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":13.15,"output_rub_per_million":52.57,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-4.6","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 4.6","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.5-35b-a3b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-35B-A3B","description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":39.49,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-4.6:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 4.6 (batch)","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":189.55,"output_rub_per_million":947.71,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-4.6v","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.6V","description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.","context_window":131072,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":113.73,"currency":"RUB","is_free":false}},{"id":"stepfun/step-3.5-flash","object":"model","created":1789025613,"owned_by":"stepfun","display_name":"StepFun: Step 3.5 Flash","description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"black-forest-labs/flux.2-klein-4b","object":"model","created":1789025643,"owned_by":"black-forest-labs","display_name":"Black Forest Labs: FLUX.2 Klein 4B","description":"FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality. Pricing is based on the output...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":1.77,"unit":"megapixel"}],"is_free":false}},{"id":"openai/gpt-5.2","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2","description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":221.14,"output_rub_per_million":1769.06,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-8b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 8B Instruct","description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon temporal reasoning, DeepStack for fine-grained visual-text alignment, and text-timestamp alignment for precise event localization.\nThe model supports a native 256K-token context window, extensible to 1M tokens, and handles both static and dynamic media inputs for tasks like document parsing, visual question answering, spatial reasoning, and GUI control. It achieves text understanding comparable to leading LLMs while expanding OCR coverage to 32 languages and enhancing robustness under varied visual conditions.","context_window":262144,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":14.79,"output_rub_per_million":57.5,"currency":"RUB","is_free":false}},{"id":"relace/relace-apply-3","object":"model","created":1789025613,"owned_by":"relace","display_name":"Relace: Relace Apply 3","description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average.\nThe model requires the prompt to be in the following format:\n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\nZero Data Retention is enabled for Relace. Learn more about this model in their documentation","context_window":256000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","seed","stop"],"pricing":{"unit":"token","input_rub_per_million":107.41,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"deepgram/nova-3","object":"model","created":1789025650,"owned_by":"deepgram","display_name":"Deepgram: Nova-3","description":"Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":[],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":0.55,"unit":"minute"},{"sku":"Audio Minutes (Multilingual)","price_rub":0.66,"unit":"minute"}],"is_free":false}},{"id":"google/gemini-3.1-pro-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Pro Preview","description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","context_window":1048576,"modalities":["text"],"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-coder-plus","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Coder Plus","description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":82.14,"output_rub_per_million":410.68,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5v-turbo","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5V Turbo","description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.","context_window":202752,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":151.64,"output_rub_per_million":505.45,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":568.63,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-3b-2512","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Ministral 3 3B 2512","description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":12.64,"currency":"RUB","is_free":false}},{"id":"poolside/laguna-s-2.1:free","object":"model","created":1789025613,"owned_by":"poolside","display_name":"Poolside: Laguna S 2.1 (free)","description":"Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.\nLaguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the OpenMDW-1.1 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.\nPlease report security vulnerabilities or safety concerns to [email&#160;protected].\nIf you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-4o","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o","description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\nFor benchmarking against other models, it was briefly called \"im-also-a-good-gpt2-chatbot\"\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-max","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Max","description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":98.57,"output_rub_per_million":492.81,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-content-safety:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Content Safety (free)","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.\nIt is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.4-nano","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"amazon/nova-2-lite-v1","object":"model","created":1789025613,"owned_by":"amazon","display_name":"Amazon: Nova 2 Lite","description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-14b-2512","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Ministral 3 14B 2512","description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-haiku-4.5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Haiku 4.5","description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","context_window":200000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-image","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Image","description":"GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following, text rendering, and detailed image editing.","context_window":400000,"modalities":["image","text"],"input_modalities":["image","text","file"],"output_modalities":["image","text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-sol","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-4.5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.5","description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","context_window":200000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-4.3:batch","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.3 (batch)","description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.\nIt supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":252.73,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/mistral-medium-3-5","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Medium 3.5","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":189.55,"output_rub_per_million":947.71,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-max-0902","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 Max (0902)","description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.\nThis snapshot is post-trained for coding and agentic work, including multi-step software projects, multi-tool orchestration, and long-horizon task execution. It also targets chart reasoning, document parsing, and multimodal understanding over long documents and extended video. Tool calling, structured outputs, and configurable reasoning effort are supported.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2.0-lite","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed-2.0-Lite","description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across text, vision, and tools. Engineered for high-frequency visual understanding and agentic workflows, it's an ideal choice for deployment at scale with minimal latency.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3.1","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Medium 3.1","description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","context_window":131072,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-flash","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.6 Flash","description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in above 256K tokens. Prompt caching is supported, with both explicit cache read and cache creation pricing.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":23.7,"output_rub_per_million":142.16,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Pro","description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":15163.3,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-4.1-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1 Mini","description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":202.18,"currency":"RUB","is_free":false}},{"id":"thedrummer/skyfall-36b-v2","object":"model","created":1789025613,"owned_by":"thedrummer","display_name":"TheDrummer: Skyfall 36B V2","description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":69.5,"output_rub_per_million":101.09,"currency":"RUB","is_free":false}},{"id":"thedrummer/cydonia-24b-v4.1","object":"model","created":1789025613,"owned_by":"thedrummer","display_name":"TheDrummer: Cydonia 24B V4.1","description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":63.19,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder-flash","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Coder Flash","description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":24.65,"output_rub_per_million":123.21,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.1","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.1","description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":9477.07,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-stt-1.0","object":"model","created":1789025650,"owned_by":"x-ai","display_name":"SpaceXAI: Grok STT 1.0","description":"Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","top_logprobs","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Hours","price_rub":12.64,"unit":"hour"}],"is_free":false}},{"id":"mistralai/mistral-small-24b-instruct-2501","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Small 3","description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.\nThe model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. Read the blog post about the model here.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":10.11,"currency":"RUB","is_free":false}},{"id":"hubris/free","object":"model","created":1789025613,"owned_by":"hubris","display_name":"Free Models Router","description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that support features needed for your request such as image understanding, tool calling, structured outputs and more.","context_window":200000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.1-codex-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.1-Codex-Mini","description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","context_window":400000,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-nano","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Nano","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-nano:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Nano (batch)","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":3.16,"output_rub_per_million":25.28,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"~x-ai/grok-latest","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"xAI: Grok Latest","description":"This model always redirects to the latest Grok model from xAI.","context_window":500000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"baidu/ernie-4.5-vl-424b-a47b","object":"model","created":1789025613,"owned_by":"baidu","display_name":"Baidu: ERNIE 4.5 VL 424B A47B ","description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.","context_window":123000,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":53.08,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash-lite","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Flash Lite","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-asr-0.6b","object":"model","created":1789025650,"owned_by":"qwen","display_name":"Qwen: Qwen3 ASR 0.6B","description":"Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"minimax/speech-2.8-turbo","object":"model","created":1789025656,"owned_by":"minimax","display_name":"MiniMax: Speech 2.8 Turbo","description":"MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_tokens","temperature","top_p"],"supported_voices":["English_expressive_narrator","English_radiant_girl","English_magnetic_voiced_man","English_compelling_lady1","English_Aussie_Bloke","English_captivating_female1","English_Upbeat_Woman","English_Trustworth_Man","English_CalmWoman","English_UpsetGirl","English_Gentle-voiced_man","English_Whispering_girl","English_Diligent_Man","English_Graceful_Lady","English_ReservedYoungMan","English_PlayfulGirl","English_ManWithDeepVoice","English_MaturePartner","English_FriendlyPerson","English_MatureBoss","English_Debator","English_LovelyGirl","English_Steadymentor","English_Deep-VoicedGentleman","English_Wiselady","English_CaptivatingStoryteller","English_DecentYoungMan","English_SentimentalLady","English_ImposingManner","English_SadTeen","English_PassionateWarrior","English_WiseScholar","English_Soft-spokenGirl","English_SereneWoman","English_ConfidentWoman","English_PatientMan","English_Comedian","English_BossyLeader","English_Strong-WilledBoy","English_StressedLady","English_AssertiveQueen","English_AnimeCharacter","English_Jovialman","English_WhimsicalGirl","English_Kind-heartedGirl"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":7581.65,"unit":"m characters"}],"is_free":false}},{"id":"qwen/qwen3.5-flash-02-23","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-Flash","description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.22,"output_rub_per_million":32.86,"currency":"RUB","is_free":false}},{"id":"sourceful/riverflow-v2-fast-preview","object":"model","created":1783372385,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2 Fast Preview","description":"Riverflow V2 Fast Preview is the fastest variant of Sourceful's Riverflow V2 preview lineup. This preview version exceeds the performance of Riverflow 1 Family and is Sourceful's first unified text-to-image...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":[],"pricing":{"unit":"unknown","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-397b-a17b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5 397B A17B","description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":69.5,"output_rub_per_million":442.27,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.3","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.3","description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.\nIt supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":315.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-2.5-pro:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Pro (batch)","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":78.98,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4","description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation.\nRead more at the blog post here","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":9477.07,"currency":"RUB","is_free":false}},{"id":"anthracite-org/magnum-v4-72b","object":"model","created":1789025613,"owned_by":"anthracite-org","display_name":"Magnum v4 72B","description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\nThe model is fine-tuned on top of Qwen2.5 72B.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.6","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.6","description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\nFor users upgrading from earlier Opus versions, see our official migration guide here","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.1-codex-max","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.1-Codex-Max","description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research.\nGPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle.","context_window":400000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1 Mini (batch)","description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":101.09,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/o1","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o1","description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the launch announcement.","context_window":200000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":7581.65,"currency":"RUB","is_free":false}},{"id":"intfloat/e5-large-v2","object":"model","created":1789025613,"owned_by":"intfloat","display_name":"Intfloat: E5-Large-v2","description":"The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"openai/text-embedding-ada-002","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: Text Embedding Ada 002","description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-26b-a4b-it:free","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 4 26B A4B  (free)","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"qwen/qwen3.6-plus","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.6 Plus","description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":41.07,"output_rub_per_million":246.41,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-4.5","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 4.5","description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-sonnet-4","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 4","description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.\nRead more at the blog post here","context_window":1000000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"sourceful/riverflow-v2.5-pro","object":"model","created":1789025643,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2.5 Pro","description":"Riverflow V2.5 Pro is the most powerful variant of Sourceful's Riverflow 2.5 lineup, best for top-tier control and quality-sensitive outputs. The Riverflow 2.5 series is a unified text-to-image and image-to-image...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","output_format","background","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":16.43,"unit":"image"},{"sku":"output_image","price_rub":18.96,"unit":"image"},{"sku":"output_image","price_rub":21.49,"unit":"image"}],"is_free":false}},{"id":"deepseek/deepseek-chat","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3","description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.\nFor model details, please visit the DeepSeek-V3 repo for more information, or see the launch announcement.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.53,"output_rub_per_million":129.99,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-fable-5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Fable 5 (batch)","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-audio-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT Audio Mini","description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.","context_window":128000,"modalities":["text","audio"],"input_modalities":["text","audio"],"output_modalities":["text","audio"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":303.27,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash 0423","description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.\nThe model includes hybrid attention for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":11.2,"output_rub_per_million":22.4,"currency":"RUB","is_free":false}},{"id":"amazon/nova-lite-v1","object":"model","created":1789025613,"owned_by":"amazon","display_name":"Amazon: Nova Lite 1.0","description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.","context_window":300000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":30.33,"currency":"RUB","is_free":false}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","object":"model","created":1789025613,"owned_by":"cognitivecomputations","display_name":"Venice: Uncensored","description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving user control over alignment, system prompts, and behavior. Intended for advanced and unrestricted use cases, Venice Uncensored emphasizes steerability and transparent behavior, removing default safety and alignment layers typically found in mainstream assistant models.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":113.73,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash-0731","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","context_window":1310720,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.22,"output_rub_per_million":22.75,"currency":"RUB","is_free":false}},{"id":"thenlper/gte-base","object":"model","created":1789025613,"owned_by":"thenlper","display_name":"Thenlper: GTE-Base","description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash-image","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. Aspect ratios can be controlled with the image_config API Parameter","context_window":32768,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"amazon/nova-micro-v1","object":"model","created":1789025613,"owned_by":"amazon","display_name":"Amazon: Nova Micro 1.0","description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has simple mathematical reasoning and coding abilities.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":4.43,"output_rub_per_million":17.7,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-plus","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen-Plus","description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.86,"output_rub_per_million":98.57,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-pro-search","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Sonar Pro Search","description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. This model powers the Pro Search mode on the Perplexity platform.\nSonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.","context_window":200000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":2.28,"unit":"1k calls"}],"is_free":false}},{"id":"nousresearch/hermes-3-llama-3.1-405b","object":"model","created":1789025613,"owned_by":"nousresearch","display_name":"Nous: Hermes 3 405B Instruct","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\nHermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.\nHermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4.1","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1","description":"Recraft V4.1 is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":4.43,"unit":"image"}],"is_free":false}},{"id":"openai/gpt-5-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Mini","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"liquid/lfm-2.5-2.6b:free","object":"model","created":1789025613,"owned_by":"liquid","display_name":"LiquidAI: LFM2.5-2.6B (free)","description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks.\nPrompts and outputs may be retained and used to train Liquid models.","context_window":65536,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"google/gemini-3.1-flash-image","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the image_config API Parameter","context_window":131072,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":379.09,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3.5-flash-lite","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.5 Flash Lite","description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":315.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-4.20-multi-agent","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.20 Multi-Agent","description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.\nReasoning effort behavior:\n• low / medium: 4 agents\n• high / xhigh: 16 agents","context_window":2000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":315.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-asr-1.7b","object":"model","created":1789025650,"owned_by":"qwen","display_name":"Qwen: Qwen3 ASR 1.7B","description":"Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"intfloat/multilingual-e5-large","object":"model","created":1789025613,"owned_by":"intfloat","display_name":"Intfloat: Multilingual-E5-Large","description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and large-scale data search.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"microsoft/mai-voice-2-flash","object":"model","created":1789025656,"owned_by":"microsoft","display_name":"MicrosoftAI: MAI-Voice-2-Flash","description":"MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15 languages...","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_completion_tokens","max_tokens","temperature","top_p"],"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":1895.42,"unit":"m characters"}],"is_free":false}},{"id":"google/gemini-3.6-flash:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.6 Flash (batch)","description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":47.39,"output_rub_per_million":236.93,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-4.5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.5 (batch)","description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","context_window":200000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"inception/mercury-2.5","object":"model","created":1789025613,"owned_by":"inception","display_name":"Inception: Mercury 2.5","description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.\nInstead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving 1,107 tokens/sec on standard GPUs. It delivers a 10+ point jump in intelligence over Mercury 2, comparable quality to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5.\nMercury 2.5 supports tunable reasoning levels, parallel tool calls, and schema-aligned JSON output. It's built for production workloads where latency compounds: search agents, voice pipelines, and coding subagents. Read more in the blog post.","context_window":260000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":5.06,"output_rub_per_million":18.96,"currency":"RUB","is_free":false}},{"id":"inclusionai/ling-3.0-flash-sante:free","object":"model","created":1789025613,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.0 Flash Sante (free)","description":"Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for medical knowledge reasoning, clinical safety, evidence-based retrieval, and long-horizon medical tasks, while retaining general capabilities in reasoning, coding, and agentic tasks.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 (batch)","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":78.98,"output_rub_per_million":631.81,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"thenlper/gte-large","object":"model","created":1789025613,"owned_by":"thenlper","display_name":"Thenlper: GTE-Large","description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and clustering tasks. Trained via multi-stage contrastive learning on a large domain-diverse relevance corpus, it offers excellent performance across general-purpose embedding use-cases.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k3","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.1","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.1","description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-imagine-image-2.0","object":"model","created":1789025643,"owned_by":"x-ai","display_name":"xAI: Grok Imagine Image 2.0","description":"Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","quality","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"input_image","price_rub":1.27,"unit":"image"},{"sku":"output_image","price_rub":5.06,"unit":"image"},{"sku":"output_image","price_rub":7.59,"unit":"image"},{"sku":"output_image","price_rub":7.59,"unit":"image"},{"sku":"output_image","price_rub":10.11,"unit":"image"}],"is_free":false}},{"id":"dots-studio/dots-3-note-preview:free","object":"model","created":1789025613,"owned_by":"dots-studio","display_name":"Dots Studio: Dots3-Note Preview (free)","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is suited for reasoning, coding, multimodal understanding, long-context processing, and multi-step agent workflows.","context_window":512000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"google/gemini-3.7-flash","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.7 Flash","description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":94.78,"output_rub_per_million":473.86,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/voxtral-mini-3b-2507","object":"model","created":1789025650,"owned_by":"mistralai","display_name":"Mistral: Voxtral Mini 3B 2507","description":"Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"deepseek/deepseek-v4-pro-0813","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":132.61,"output_rub_per_million":397.81,"currency":"RUB","is_free":false}},{"id":"openai/gpt-transcribe","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: GPT Transcribe","description":"GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":0.57,"unit":"minute"}],"is_free":false}},{"id":"~anthropic/claude-haiku-latest","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic Claude Haiku Latest","description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","context_window":200000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.6","object":"model","created":1789025613,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.6","description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","context_window":500000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"nvidia/nemotron-3.5-lightning:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Lightning (free)","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.6-luna","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":151.64,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-luna-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Luna Pro","description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":151.64,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-2.5-pro-preview-05-06","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Pro Preview 05-06","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"tencent/hunyuan-a13b-instruct","object":"model","created":1789025613,"owned_by":"tencent","display_name":"Tencent: Hunyuan A13B Instruct","description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":17.7,"output_rub_per_million":72.03,"currency":"RUB","is_free":false}},{"id":"cohere/command-a","object":"model","created":1789025613,"owned_by":"cohere","display_name":"Cohere: Command A","description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.","context_window":256000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1-nano:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1 Nano (batch)","description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":25.28,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-2.5-pro","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Pro","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"kwaipilot/kat-coder-pro-v2.5","object":"model","created":1789025613,"owned_by":"kwaipilot","display_name":"Kwaipilot: KAT-Coder-Pro V2.5","description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make modifications, and complete the entire process in the actual repository. At the same time, it seamlessly integrates multiple experts to fully retain the front-end aesthetic generation capability of V2.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":93.51,"output_rub_per_million":374.03,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-lite:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Flash Lite (batch)","description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":15.8,"output_rub_per_million":94.78,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Nano Omni (free)","description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.\nBuilt on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.","context_window":256000,"modalities":["text"],"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-5.6-terra-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Terra Pro","description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen-2.5-72b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen2.5 72B Instruct","description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n•\nSignificantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n•\nSignificant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n•\nLong-context Support up to 128K tokens and can generate up to 8K tokens.\n•\nMultilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\nUsage of this model is subject to Tongyi Qianwen LICENSE AGREEMENT.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":45.49,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 235B A22B Thinking 2507","description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This \"thinking-only\" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.\nThe model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":29.07,"output_rub_per_million":290.63,"currency":"RUB","is_free":false}},{"id":"openai/o3:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3 (batch)","description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":505.45,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-terra-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Terra Pro (batch)","description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.5-plus-20260420","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5 Plus 2026-04-20","description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This is an updated version of Qwen3.5 Plus with tiered pricing above 256K tokens.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":227.45,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-flash","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 Flash","description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":59.39,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-lite-image","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation in roughly 4 seconds — about 2.7× faster than Gemini 3.1 Flash Image — while keeping the character consistency, precise editing, and real-world knowledge of the Nano Banana family.\nA single drop-in API handles text-to-image, image editing, and multi-image composition. As a multimodal model it also returns text alongside images. Outputs are generated at 1K resolution across 14 aspect ratios and carry an invisible SynthID watermark so they can be identified as AI-generated.\nPositioned as the best balance of quality and speed in the Nano Banana 2 line, it lets you generate thousands of images at a fraction of the cost of heavier production models — ideal for prototyping, real-time apps, and visual workflows at scale.","context_window":65536,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":189.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 235B A22B Instruct","description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":26.54,"output_rub_per_million":240.09,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Coder 480B A35B","description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).\nPricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"~anthropic/claude-opus-latest","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus Latest","description":"This model always redirects to the latest model in the Claude Opus family.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3159.03,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.1","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.1","description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":122.07,"output_rub_per_million":383.64,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 30B A3B Instruct","description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-26b-a4b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 4 26B A4B ","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.85,"output_rub_per_million":42.97,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-max-preview","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.6 Max Preview","description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning traces across multi-turn conversations and supports structured output and function calling. Access is available exclusively through the Alibaba Cloud Model Studio and Qwen Studio APIs; no open weights are provided.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":129.78,"output_rub_per_million":778.64,"currency":"RUB","is_free":false}},{"id":"~anthropic/claude-fable-latest","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Fable Latest","description":"This model always redirects to the latest model in the Claude Fable family.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":6318.05,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.5-pro","object":"model","created":1789025613,"owned_by":"xiaomi","display_name":"Xiaomi: MiMo-V2.5-Pro","description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.","context_window":1050000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":54.97,"output_rub_per_million":109.94,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-6 Astra Pro","description":"GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":6318.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemma-4-31b-it:free","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 4 31B (free)","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"bytedance/ui-tars-1.5-7b","object":"model","created":1789025613,"owned_by":"bytedance","display_name":"ByteDance: UI-TARS 7B ","description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces.\nThis model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.","context_window":128000,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-2603","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Small 4","description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-4-scout","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 4 Scout","description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.","context_window":1310720,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4.1-utility","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1 Utility","description":"Recraft V4.1 Utility is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with typical generation...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":4.43,"unit":"image"}],"is_free":false}},{"id":"mistralai/voxtral-small-24b-2507-stt","object":"model","created":1789025650,"owned_by":"mistralai","display_name":"Mistral: Voxtral Small 24B 2507 STT","description":"Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"black-forest-labs/flux.2-flex","object":"model","created":1789025643,"owned_by":"black-forest-labs","display_name":"Black Forest Labs: FLUX.2 Flex","description":"FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture.","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"input_image","price_rub":7.59,"unit":"megapixel"},{"sku":"output_image","price_rub":7.59,"unit":"megapixel"}],"is_free":false}},{"id":"hexgrad/kokoro-82m","object":"model","created":1789025656,"owned_by":"hexgrad","display_name":"hexgrad: Kokoro 82M","description":"Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...","context_window":4096,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"supported_voices":["af_alloy","af_aoede","af_bella","af_heart","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","pf_dora","pm_alex","pm_santa","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":78.35,"unit":"m characters"}],"is_free":false}},{"id":"openai/gpt-4o-2024-05-13","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o (2024-05-13)","description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\nFor benchmarking against other models, it was briefly called \"im-also-a-good-gpt2-chatbot\"\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"liquid/lfm-2.5-embedding-350m:free","object":"model","created":1789025613,"owned_by":"liquid","display_name":"LiquidAI: LFM2.5-Embedding-350M (free)","description":"LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search.\nSuccessful OpenRouter requests and embeddings may be retained and used to train Liquid models.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"openai/gpt-4-turbo-preview","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4 Turbo Preview","description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023.\nNote: heavily rate limited by OpenAI while in preview.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":3790.83,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-image-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative edits significantly more accessible. Aspect ratios can be controlled with the image_config API Parameter","context_window":65536,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":379.09,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"voyageai/voyage-4-lite","object":"model","created":1789025613,"owned_by":"voyageai","display_name":"VoyageAI by MongoDB: voyage-4-lite","description":"voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options. Learn more about voyage-4-lite here: blog.voyageai.com/2026/01/15/voyage-4","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":[],"pricing":{"unit":"token","input_rub_per_million":2.53,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"fish-audio/transcribe-1","object":"model","created":1789025650,"owned_by":"fish-audio","display_name":"Fish Audio: Transcribe 1","description":"Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":[],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.02,"unit":"second"}],"is_free":false}},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Flash Lite","description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":189.55,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-chat-latest","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT Chat Latest","description":"GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.\nFor more info, see: https://developers.openai.com/api/docs/models/chat-latest","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":3790.83,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.4-nano:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Nano (batch)","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":78.98,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"~anthropic/claude-sonnet-latest","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic Claude Sonnet Latest","description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"~openai/gpt-latest","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI GPT Latest","description":"This model always redirects to the latest model in the OpenAI GPT family.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1263.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"bytedance-seed/seedream-5-0-lite","object":"model","created":1789025643,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seedream 5.0 Lite","description":"Seedream 5.0 Lite is an image generation model from ByteDance Seed. It is suited for professional visual creation that benefits from web-connected retrieval, complex-prompt comprehension, visual references, and broad knowledge...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":4.43,"unit":"image"}],"is_free":false}},{"id":"openai/gpt-5.5-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.5 Pro","description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":3790.83,"output_rub_per_million":22744.95,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-coder-next","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Coder Next","description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.\nThe model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":15.17,"output_rub_per_million":101.09,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.5","object":"model","created":1789025613,"owned_by":"xiaomi","display_name":"Xiaomi: MiMo-V2.5","description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.","context_window":1050000,"modalities":["text"],"input_modalities":["text","audio","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":17.7,"output_rub_per_million":35.39,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.7:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.7 (batch)","description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.\nFor users upgrading from earlier Opus versions, see our official migration guide here","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen-image-3-pro","object":"model","created":1789025643,"owned_by":"qwen","display_name":"Qwen: Qwen Image 3 Pro","description":"Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"input_image","price_rub":0.38,"unit":"image"},{"sku":"output_image","price_rub":5.06,"unit":"image"},{"sku":"output_image","price_rub":9.48,"unit":"image"}],"is_free":false}},{"id":"openai/gpt-5.4-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Pro","description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","context_window":1050000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":3790.83,"output_rub_per_million":22744.95,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4","description":"Recraft V4 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. It delivers stronger compositional judgment,...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":5.06,"unit":"image"}],"is_free":false}},{"id":"black-forest-labs/flux.2-pro","object":"model","created":1789025643,"owned_by":"black-forest-labs","display_name":"Black Forest Labs: FLUX.2 Pro","description":"A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs....","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":3.8,"unit":"megapixel"}],"is_free":false}},{"id":"google/gemini-3.1-pro-preview:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3.1 Pro Preview (batch)","description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.\nDesigned for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.","context_window":1048576,"modalities":["text"],"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"google/lyria-3-clip-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Lyria 3 Clip Preview","description":"Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Clip can generate short clips, loops, previews.","context_window":1048576,"modalities":["text","audio"],"input_modalities":["text","image"],"output_modalities":["text","audio"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Song Generation","price_rub":5.06,"unit":"song"}],"is_free":false}},{"id":"openai/gpt-5.2-codex","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2-Codex","description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1-Codex, 5.2-Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter. Read the docs here\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","context_window":400000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":221.14,"output_rub_per_million":1769.06,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4.1-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1 Vector","description":"Recraft V4.1 Vector is the vector (SVG) variant of Recraft V4.1, tuned for high aesthetics. It supports text and image inputs and produces SVG image output across multiple aspect ratios,...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":10.11,"unit":"image"}],"is_free":false}},{"id":"minimax/minimax-m2.5","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M2.5","description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"minimax/speech-2.8-hd","object":"model","created":1789025656,"owned_by":"minimax","display_name":"MiniMax: Speech 2.8 HD","description":"MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_tokens","temperature","top_p"],"supported_voices":["English_expressive_narrator","English_radiant_girl","English_magnetic_voiced_man","English_compelling_lady1","English_Aussie_Bloke","English_captivating_female1","English_Upbeat_Woman","English_Trustworth_Man","English_CalmWoman","English_UpsetGirl","English_Gentle-voiced_man","English_Whispering_girl","English_Diligent_Man","English_Graceful_Lady","English_ReservedYoungMan","English_PlayfulGirl","English_ManWithDeepVoice","English_MaturePartner","English_FriendlyPerson","English_MatureBoss","English_Debator","English_LovelyGirl","English_Steadymentor","English_Deep-VoicedGentleman","English_Wiselady","English_CaptivatingStoryteller","English_DecentYoungMan","English_SentimentalLady","English_ImposingManner","English_SadTeen","English_PassionateWarrior","English_WiseScholar","English_Soft-spokenGirl","English_SereneWoman","English_ConfidentWoman","English_PatientMan","English_Comedian","English_BossyLeader","English_Strong-WilledBoy","English_StressedLady","English_AssertiveQueen","English_AnimeCharacter","English_Jovialman","English_WhimsicalGirl","English_Kind-heartedGirl"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":12636.09,"unit":"m characters"}],"is_free":false}},{"id":"bytedance-seed/seed-1.6","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed 1.6","description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"nex-agi/nex-n2.5-pro:free","object":"model","created":1789025613,"owned_by":"nex-agi","display_name":"Nex AGI: Nex-N2.5-Pro (free)","description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file changes, run commands, launch applications, interact with browser and desktop interfaces, and test software from the user's perspective. When observed behavior does not match the intended result, Nex-N2.5 can diagnose the issue, revise its implementation, and test again. This makes it especially effective for autonomous software engineering, GUI-based QA, computer-use automation, deep research, and scientific workflows where success must be demonstrated in the environment—not merely inferred from generated code.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"kwaipilot/kat-coder-pro-v2","object":"model","created":1789025613,"owned_by":"kwaipilot","display_name":"Kwaipilot: KAT-Coder-Pro V2","description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions, with a focus on large-scale production environments, multi-system coordination, and seamless integration across modern software stacks, while also supporting web aesthetics generation to produce production-grade landing pages and presentation decks.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m2.7","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M2.7","description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-image-3","object":"model","created":1789025643,"owned_by":"qwen","display_name":"Qwen: Qwen Image 3","description":"Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"input_image","price_rub":0.38,"unit":"image"},{"sku":"output_image","price_rub":3.8,"unit":"image"},{"sku":"output_image","price_rub":3.8,"unit":"image"}],"is_free":false}},{"id":"sourceful/riverflow-v2.5-fast","object":"model","created":1789025643,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2.5 Fast","description":"Riverflow V2.5 Fast is the speed-optimized variant of Sourceful's Riverflow 2.5 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.5 series is a unified text-to-image and image-to-image family...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","output_format","background","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":2.41,"unit":"image"},{"sku":"output_image","price_rub":2.66,"unit":"image"}],"is_free":false}},{"id":"nvidia/nemotron-3-super-120b-a12b:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Super (free)","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"qwen/qwen3.5-122b-a10b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-122B-A10B","description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.86,"output_rub_per_million":262.84,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-2.0","object":"model","created":1789025613,"owned_by":"aion-labs","display_name":"AionLabs: Aion-2.0","description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":202.18,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-max-thinking","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Max Thinking","description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":98.57,"output_rub_per_million":492.81,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-plus-02-15","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5 Plus 2026-02-15","description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.86,"output_rub_per_million":197.13,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2.5","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2.5","description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":56.87,"output_rub_per_million":284.32,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5","description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":242.62,"currency":"RUB","is_free":false}},{"id":"openai/whisper-1","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: Whisper 1","description":"Whisper is OpenAI's open-source automatic speech recognition model, available via API as `whisper-1`. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":0.76,"unit":"minute"}],"is_free":false}},{"id":"z-ai/glm-4.7-flash","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.7 Flash","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.","context_window":202752,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.65,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-imagine-image-quality","object":"model","created":1789025643,"owned_by":"x-ai","display_name":"SpaceXAI: Grok Imagine Image Quality","description":"Grok Imagine Image Quality is SpaceXAI's fast, high-fidelity image generation and editing model. It accepts text prompts and optional reference images, producing photorealistic outputs at 1K or 2K across a...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"input_image","price_rub":1.27,"unit":"image"},{"sku":"output_image","price_rub":6.32,"unit":"image"},{"sku":"output_image","price_rub":8.85,"unit":"image"}],"is_free":false}},{"id":"mistralai/ministral-8b-2512","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Ministral 3 8B 2512","description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":18.96,"currency":"RUB","is_free":false}},{"id":"google/chirp-3","object":"model","created":1789025650,"owned_by":"google","display_name":"Google: Chirp 3","description":"Chirp 3 is Google's latest multilingual speech-to-text model. It offers enhanced transcription accuracy across 24 GA languages and 77+ preview languages, with support for automatic language detection, automatic punctuation, and...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":2.03,"unit":"minute"}],"is_free":false}},{"id":"recraft/recraft-v4.1-pro-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1 Pro Vector","description":"Recraft V4.1 Pro Vector is the vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics. It supports text and image inputs and produces higher-resolution SVG image output across...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":37.91,"unit":"image"}],"is_free":false}},{"id":"minimax/minimax-m2-her","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M2-her","description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.","context_window":65536,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"writer/palmyra-x5","object":"model","created":1789025613,"owned_by":"writer","display_name":"Writer: Palmyra X5","description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million tokens, powered by a novel transformer architecture and hybrid attention mechanisms. This enables faster inference and expanded memory for processing large volumes of enterprise data, critical for scaling AI agents.","context_window":1040000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"openai/gpt-audio","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT Audio","description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.","context_window":128000,"modalities":["text","audio"],"input_modalities":["text","audio"],"output_modalities":["text","audio"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-flash-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 3 Flash Preview","description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":379.09,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"openai/whisper-large-v3-turbo","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: Whisper Large V3 Turbo","description":"Whisper Large V3 Turbo is an optimized version of OpenAI's Whisper Large V3 speech recognition model, designed for speed and cost efficiency. It supports transcription across 99+ languages with a...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"nvidia/nemotron-3-nano-30b-a3b","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Nano 30B A3B","description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-120b","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: gpt-oss-120b","description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":4.68,"output_rub_per_million":21.49,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-1.6-flash","object":"model","created":1789025613,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seed 1.6 Flash","description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.","context_window":262144,"modalities":["text"],"input_modalities":["image","text","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m2.1","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M2.1","description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"amazon/nova-premier-v1","object":"model","created":1789025613,"owned_by":"amazon","display_name":"Amazon: Nova Premier 1.0","description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","is_free":false}},{"id":"openai/o3","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3","description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1010.89,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-4.7","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.7","description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":221.14,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-saba","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Saba","description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post here","context_window":32768,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.2-chat","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2 Chat","description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.2 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.","context_window":128000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":221.14,"output_rub_per_million":1769.06,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m2","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M2","description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.\nBenchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.23,"output_rub_per_million":128.89,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.2-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2 Pro","description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":2653.58,"output_rub_per_million":21228.62,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.2-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2 Pro (batch)","description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1326.79,"output_rub_per_million":10614.31,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.2:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.2 (batch)","description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","context_window":400000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":110.57,"output_rub_per_million":884.53,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/o3-mini-high","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3 Mini High","description":"OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high.\no3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","context_window":200000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":139,"output_rub_per_million":555.99,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-8b-thinking","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 8B Thinking","description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and long-context processing (native 256K, expandable to 1M tokens) for tasks such as scientific visual analysis, causal inference, and mathematical reasoning over image or video inputs.\nCompared to the Instruct edition, the Thinking version introduces deeper visual-language fusion and deliberate reasoning pathways that improve performance on long-chain logic tasks, STEM problem-solving, and multi-step video understanding. It achieves stronger temporal grounding via Interleaved-MRoPE and timestamp-aware embeddings, while maintaining robust OCR, multilingual comprehension, and text generation on par with large text-only LLMs.","context_window":131072,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":22.75,"output_rub_per_million":265.36,"currency":"RUB","is_free":false}},{"id":"relace/relace-search","object":"model","created":1789025613,"owned_by":"relace","display_name":"Relace: Relace Search","description":"The relace-search model uses 4-12 view_file and grep tools in parallel to explore a codebase and return relevant files to the user request.\nIn contrast to RAG, relace-search performs agentic multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an \"oracle\" coding agent, who orchestrates/performs the rest of the coding task.\nTo use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the Relace documentation.","context_window":256000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":379.09,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.2","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3.2","description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.\nUsers can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":34,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-pro-image-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding.\nIt offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.","context_window":65536,"modalities":["image","text"],"input_modalities":["image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1516.33,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.77,"unit":"1k calls"}],"is_free":false}},{"id":"sesame/csm-1b","object":"model","created":1789025656,"owned_by":"sesame","display_name":"Sesame: CSM 1B","description":"CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it...","context_window":4096,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"supported_voices":["conversational_a","conversational_b","read_speech_a","read_speech_b","read_speech_c","read_speech_d","none"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":884.53,"unit":"m characters"}],"is_free":false}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 30B A3B Thinking","description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":303.27,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Vector","description":"Recraft V4 Vector is the vector (SVG) variant of Recraft V4. It supports text and image inputs and produces vector image output across multiple aspect ratios. Compared to the raster...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":10.11,"unit":"image"}],"is_free":false}},{"id":"deepseek/deepseek-r1-distill-llama-70b","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: R1 Distill Llama 70B","description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n• AIME 2024 pass@1: 70.0\n• MATH-500 pass@1: 94.5\n• CodeForces Rating: 1633\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":101.09,"currency":"RUB","is_free":false}},{"id":"openai/whisper-large-v3","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: Whisper Large V3","description":"Whisper Large V3 is OpenAI's open-source automatic speech recognition model offering both audio transcription and translation. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm,...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"openai/gpt-5.1-codex","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.1-Codex","description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter. Read the docs here\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","context_window":400000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v3","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V3","description":"Recraft V3 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. Supports the following `image_config` parameters:...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":5.06,"unit":"image"}],"is_free":false}},{"id":"microsoft/phi-4","object":"model","created":1789025613,"owned_by":"microsoft","display_name":"Microsoft: Phi 4","description":"Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.\nAt 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs.\nFor more information, please see Phi-4 Technical Report","context_window":16384,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.85,"output_rub_per_million":17.7,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-9b:batch","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3.5-9B (batch)","description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":21.49,"output_rub_per_million":31.6,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.6","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.6","description":"Compared with GLM-4.5, this generation brings several key improvements:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","context_window":204800,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":54.34,"output_rub_per_million":221.14,"currency":"RUB","is_free":false}},{"id":"ibm-granite/granite-4.0-h-micro","object":"model","created":1789025613,"owned_by":"ibm-granite","display_name":"IBM: Granite 4.0 Micro","description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling.","context_window":131000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":2.15,"output_rub_per_million":14.16,"currency":"RUB","is_free":false}},{"id":"cohere/command-r7b-12-2024","object":"model","created":1789025613,"owned_by":"cohere","display_name":"Cohere: Command R7B (12-2024)","description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.\nUse of this model is subject to Cohere's Usage Policy and SaaS Agreement.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":4.74,"output_rub_per_million":18.96,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2-thinking","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2 Thinking","description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-image-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Image Mini","description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text rendering, and detailed image editing with reduced latency and cost. It excels at high-quality visual creation while maintaining strong text understanding, making it ideal for applications that require both efficient image generation and text processing at scale.","context_window":400000,"modalities":["image","text"],"input_modalities":["file","image","text"],"output_modalities":["image","text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":252.73,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-haiku-4.5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Haiku 4.5 (batch)","description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","context_window":200000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":315.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-4-turbo","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4 Turbo","description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\nTraining data: up to December 2023.","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":1263.61,"output_rub_per_million":3790.83,"currency":"RUB","is_free":false}},{"id":"black-forest-labs/flux.2-max","object":"model","created":1789025643,"owned_by":"black-forest-labs","display_name":"Black Forest Labs: FLUX.2 Max","description":"FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet. Pricing is as follows, [per...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":8.85,"unit":"megapixel"}],"is_free":false}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 VL 235B A22B Thinking","description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":505.45,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Pro (batch)","description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":947.71,"output_rub_per_million":7581.65,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-oss-safeguard-20b","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: gpt-oss-safeguard-20b","description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.\nLearn more about this model in OpenAI's gpt-oss-safeguard user guide.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.1-terminus","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3.1 Terminus","description":"DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":34.12,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-120b:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: gpt-oss-120b (batch)","description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2-0905","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2 0905","description":"Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k.\nThis update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5v","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.5V","description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a \"thinking mode\" for deep reasoning and a \"non-thinking mode\" for fast responses. Reasoning behavior can be toggled via the reasoning enabled boolean. Learn more in our docs","context_window":65536,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":227.45,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo-0613","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-3.5 Turbo (older v0613)","description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\nTraining data up to Sep 2021.","context_window":4095,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.2-exp","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3.2 Exp","description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\nThe model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":34.12,"output_rub_per_million":51.81,"currency":"RUB","is_free":false}},{"id":"perplexity/pplx-embed-v1-4b","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Embed V1 4B","description":"pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval quality.","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":3.8,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2","object":"model","created":1789025613,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2 0711","description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":72.03,"output_rub_per_million":290.63,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4-pro-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Pro Vector","description":"Recraft V4 Pro Vector is the vector (SVG) variant of Recraft V4 Pro. It supports text and image inputs and produces vector image output across multiple aspect ratios at the...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":37.91,"unit":"image"}],"is_free":false}},{"id":"qwen/qwen-plus-2025-07-28","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen Plus 0728","description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.86,"output_rub_per_million":98.57,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-guard-4-12b","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama Guard 4 12B","description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.","context_window":163840,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":22.75,"output_rub_per_million":22.75,"currency":"RUB","is_free":false}},{"id":"openai/o4-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o4 Mini (batch)","description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":69.5,"output_rub_per_million":278,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-235b-a22b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 235B A22B","description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and code tasks, and a \"non-thinking\" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":57.5,"output_rub_per_million":229.98,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-next-80b-a3b-thinking","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Next 80B A3B Thinking","description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-4-maverick","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 4 Maverick","description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":87.95,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-30b-a3b-thinking-2507","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 30B A3B Thinking 2507","description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.\nCompared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.","context_window":81920,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":303.27,"currency":"RUB","is_free":false}},{"id":"nousresearch/hermes-4-405b","object":"model","created":1789025613,"owned_by":"nousresearch","display_name":"Nous: Hermes 4 405B","description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\nThe model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":379.09,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo-instruct","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-3.5 Turbo Instruct","description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","context_window":4095,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":189.55,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-chat-v3.1","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3.1","description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.\nIt succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":120.05,"currency":"RUB","is_free":false}},{"id":"baai/bge-large-en-v1.5","object":"model","created":1789025613,"owned_by":"baai","display_name":"BAAI: bge-large-en-v1.5","description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks in English.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-3.2-24b-instruct","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Small 3.2 24B","description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).","context_window":131072,"modalities":["text"],"input_modalities":["image","text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash-lite:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Flash Lite (batch)","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, \"thinking\" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.","context_window":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5 Mini (batch)","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","context_window":400000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":15.8,"output_rub_per_million":126.37,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"baai/bge-m3","object":"model","created":1789025613,"owned_by":"baai","display_name":"BAAI: bge-m3","description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","context_window":8194,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Flash","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","context_window":1048576,"modalities":["text"],"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash:batch","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Flash (batch)","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).","context_window":1048576,"modalities":["text"],"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"openai/o3-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3 Pro","description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations","context_window":200000,"modalities":["text"],"input_modalities":["text","file","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":2527.22,"output_rub_per_million":10108.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-14b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 14B","description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, programming, and logical inference, and a \"non-thinking\" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":28.75,"output_rub_per_million":114.99,"currency":"RUB","is_free":false}},{"id":"rekaai/reka-flash-3","object":"model","created":1789025613,"owned_by":"rekaai","display_name":"Reka Flash 3","description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags (\"<reasoning>\") to indicate its internal thought process.\nReka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.","context_window":65536,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3.1:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Medium 3.1 (batch)","description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","context_window":131072,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-20b","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: gpt-oss-20b","description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":3.8,"output_rub_per_million":16.43,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-20b:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: gpt-oss-20b (batch)","description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-embedding-8b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Embedding 8B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.","context_window":32768,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":1.27,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-r1-0528","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: R1 0528","description":"May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\nFully open-source model.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":271.68,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Coder 30B A3B Instruct","description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.\nThis model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.85,"output_rub_per_million":35.39,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 30B A3B Instruct 2507","description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":11.38,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.5","description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":75.82,"output_rub_per_million":278,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5-air","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 4.5 Air","description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a \"thinking mode\" for advanced reasoning and tool use, and a \"non-thinking mode\" for real-time interaction. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":16.43,"output_rub_per_million":107.41,"currency":"RUB","is_free":false}},{"id":"openai/o4-mini-high","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o4 Mini High","description":"OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.\nOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","context_window":200000,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":139,"output_rub_per_million":555.99,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/mistral-nemo","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Nemo","description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.\nThe model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.\nIt supports function calling and is released under the Apache 2.0 license.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":2.41,"output_rub_per_million":3.8,"currency":"RUB","is_free":false}},{"id":"morph/morph-v3-large","object":"model","created":1789025613,"owned_by":"morph","display_name":"Morph: Morph V3 Large","description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\nThe model requires the prompt to be in the following format:\n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\nZero Data Retention is enabled for Morph. Learn more about this model in their documentation","context_window":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"pricing":{"unit":"token","input_rub_per_million":113.73,"output_rub_per_million":240.09,"currency":"RUB","is_free":false}},{"id":"morph/morph-v3-fast","object":"model","created":1789025613,"owned_by":"morph","display_name":"Morph: Morph V3 Fast","description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations.\nThe model requires the prompt to be in the following format:\n<instruction>{instruction}</instruction>\n<code>{initial_code}</code>\n<update>{edit_snippet}</update>\nZero Data Retention is enabled for Morph. Learn more about this model in their documentation","context_window":81920,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m1","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M1","description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks.\nTrained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.","context_window":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":69.5,"output_rub_per_million":278,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1-nano","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1 Nano","description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-pro-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini 2.5 Pro Preview 06-05","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","context_window":1048576,"modalities":["text"],"input_modalities":["file","image","text","audio"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"baai/bge-base-en-v1.5","object":"model","created":1789025613,"owned_by":"baai","display_name":"BAAI: bge-base-en-v1.5","description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features improved similarity-score distribution and stronger retrieval performance out of the box.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-27b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 3 27B","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":10.11,"output_rub_per_million":56.87,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seedream-5-0-pro","object":"model","created":1789025643,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seedream 5.0 Pro","description":"Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed. It is suited for commercial visual-production workflows that require precise editing control, lifelike scenes, and natural rendering.","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":5.69,"unit":"image"},{"sku":"output_image","price_rub":11.38,"unit":"image"},{"sku":"input_image","price_rub":0.38,"unit":"image"}],"is_free":false}},{"id":"mistralai/mistral-medium-3","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Medium 3","description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.\nThe model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.","context_window":131072,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-30b-a3b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 30B A3B","description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":15.17,"output_rub_per_million":63.19,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-8b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 8B","description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math, coding, and logical inference, and \"non-thinking\" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":14.79,"output_rub_per_million":57.5,"currency":"RUB","is_free":false}},{"id":"recraft/recraft-v4-styles","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Styles","description":"Recraft V4 Styles is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's rendering...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":4.43,"unit":"image"}],"is_free":false}},{"id":"qwen/qwen3-32b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 32B","description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, coding, and logical inference, and a \"non-thinking\" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":10.11,"output_rub_per_million":35.39,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-deep-research","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Sonar Deep Research","description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events.\nNotes on Pricing (Source)\n• Input tokens comprise of Prompt tokens (user prompt) + Citation tokens (these are processed tokens from running searches)\n• Deep Research runs multiple searches to conduct exhaustive research.\n• Reasoning is a distinct step in Deep Research since it does extensive automated reasoning through all the material it gathers during its research phase. Reasoning tokens here are a bit different than the CoTs in the answer - these are tokens that we use to reason through the research material prior to generating the outputs via the CoTs.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1010.89,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-asr-flash-2026-02-10","object":"model","created":1789025650,"owned_by":"qwen","display_name":"Qwen: Qwen3 ASR Flash","description":"Qwen3-ASR-Flash is Alibaba's automatic speech recognition service, built on the Qwen3-Omni foundation and trained on tens of millions of hours of multimodal speech data. The model handles 11 languages —...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"recraft/recraft-v4.1-pro","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4.1 Pro","description":"Recraft V4.1 Pro is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":26.54,"unit":"image"}],"is_free":false}},{"id":"sourceful/riverflow-v2-pro","object":"model","created":1789025643,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2 Pro","description":"Riverflow V2 Pro is the most powerful variant of Sourceful's Riverflow 2.0 lineup, best for top-tier control and perfect text rendering. The Riverflow 2.0 series represents SOTA performance on image...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":18.96,"unit":"image"},{"sku":"output_image","price_rub":18.96,"unit":"image"},{"sku":"output_image","price_rub":41.7,"unit":"image"},{"sku":"input_font","price_rub":3.8,"unit":"image"},{"sku":"input_reference","price_rub":25.28,"unit":"image"}],"is_free":false}},{"id":"openai/gpt-4.1","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4.1","description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","context_window":1047576,"modalities":["text"],"input_modalities":["image","text","file"],"output_modalities":["text"],"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1010.89,"currency":"RUB","is_free":false}},{"id":"canopylabs/orpheus-3b-0.1-ft","object":"model","created":1789025656,"owned_by":"canopylabs","display_name":"Canopy Labs: Orpheus 3B","description":"Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. It offers 7 preset voices and is suited for narration, voice assistants, and...","context_window":4096,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"supported_voices":["tara","leah","jess","leo","dan","mia","zac"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":884.53,"unit":"m characters"}],"is_free":false}},{"id":"openai/gpt-4o-mini-transcribe","object":"model","created":1789025650,"owned_by":"openai","display_name":"OpenAI: GPT-4o Mini Transcribe","description":"GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that...","context_window":128000,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-chat-v3-0324","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3 0324","description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\nIt succeeds the DeepSeek V3 model and performs really well on a variety of tasks.","context_window":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.65,"output_rub_per_million":144.06,"currency":"RUB","is_free":false}},{"id":"openai/o1-pro","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o1-pro","description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","context_window":200000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"pricing":{"unit":"token","input_rub_per_million":18954.13,"output_rub_per_million":75816.5,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-3.1-24b-instruct","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Small 3.1 24B","description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is Mistral Small 3.2","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":44.36,"output_rub_per_million":70.14,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-4b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 3 4B","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":12.64,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-12b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 3 12B","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B","context_window":131072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":18.96,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-2.5-coder-32b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen2.5 Coder 32B Instruct","description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\n• Significantly improvements in code generation, code reasoning and code fixing.\n• A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.\nTo read more about its evaluation results, check out Qwen 2.5 Coder's blog.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":83.4,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-reasoning-pro","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Sonar Reasoning Pro","description":"Note: Sonar Pro pricing includes Perplexity search pricing. See details here\nSonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for advanced use cases, it supports in-depth, multi-step queries with a larger context window and can surface more citations per search, enabling more comprehensive and extensible responses.","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":1010.89,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"perplexity/sonar-pro","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Sonar Pro","description":"Note: Sonar Pro pricing includes Perplexity search pricing. See details here\nFor enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions.","context_window":200000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"meta-llama/llama-3.2-3b-instruct","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 3.2 3B Instruct","description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.\nTrained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.\nClick here for the original model card.\nUsage of this model is subject to Meta's Acceptable Use Policy.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":41.7,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-rp-llama-3.1-8b","object":"model","created":1789025613,"owned_by":"aion-labs","display_name":"AionLabs: Aion-RP 1.0 (8B)","description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":202.18,"currency":"RUB","is_free":false}},{"id":"qwen/qwen2.5-vl-72b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen2.5 VL 72B Instruct","description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":126.37,"currency":"RUB","is_free":false}},{"id":"sao10k/l3.1-euryale-70b","object":"model","created":1789025613,"owned_by":"sao10k","display_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":107.41,"output_rub_per_million":107.41,"currency":"RUB","is_free":false}},{"id":"openai/o3-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3 Mini","description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\nThis model supports the reasoning_effort parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to \"high\".\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","context_window":200000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":139,"output_rub_per_million":555.99,"currency":"RUB","is_free":false}},{"id":"nousresearch/hermes-3-llama-3.1-70b","object":"model","created":1789025613,"owned_by":"nousresearch","display_name":"Nous: Hermes 3 70B Instruct","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\nHermes 3 70B is a competitive, if not superior finetune of the Llama-3.1 70B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":88.46,"output_rub_per_million":88.46,"currency":"RUB","is_free":false}},{"id":"openai/o3-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: o3 Mini (batch)","description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\nThis model supports the reasoning_effort parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to \"high\".\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","context_window":200000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":69.5,"output_rub_per_million":278,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.1-8b-instruct","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 3.1 8B Instruct","description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\nTo read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.32,"output_rub_per_million":10.11,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m3:batch","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax M3 (batch)","description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.","context_window":524288,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":37.91,"output_rub_per_million":151.64,"currency":"RUB","is_free":false}},{"id":"sourceful/riverflow-v2-fast","object":"model","created":1789025643,"owned_by":"sourceful","display_name":"Sourceful: Riverflow V2 Fast","description":"Riverflow V2 Fast is the fastest variant of Sourceful's Riverflow 2.0 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.0 series represents SOTA performance on image generation and...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":2.53,"unit":"image"},{"sku":"output_image","price_rub":5.06,"unit":"image"},{"sku":"input_font","price_rub":3.8,"unit":"image"},{"sku":"input_reference","price_rub":25.28,"unit":"image"}],"is_free":false}},{"id":"google/gemma-2-27b-it","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemma 2 27B","description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models.\nGemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning.\nSee the launch announcement for more details. Usage of Gemma is subject to Google's Gemma Terms of Use.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":82.14,"output_rub_per_million":82.14,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Sonar","description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.","context_window":127072,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":126.37,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":0.64,"unit":"1k calls"}],"is_free":false}},{"id":"deepseek/deepseek-r1","object":"model","created":1789025613,"owned_by":"deepseek","display_name":"DeepSeek: R1","description":"DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\nFully open-source model & technical report.\nMIT licensed: Distill & commercialize freely!","context_window":64000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":88.46,"output_rub_per_million":315.91,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-01","object":"model","created":1789025613,"owned_by":"minimax","display_name":"MiniMax: MiniMax-01","description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens.\nThe text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.\nTo read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2","context_window":1000192,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":139,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-4.5:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 4.5 (batch)","description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":189.55,"output_rub_per_million":947.71,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-4o-mini-2024-07-18","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o-mini (2024-07-18)","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.\nCheck out the launch announcement to learn more.\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-2603:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Small 4 (batch)","description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"sao10k/l3.3-euryale-70b","object":"model","created":1789025613,"owned_by":"sao10k","display_name":"Sao10K: Llama 3.3 Euryale 70B","description":"Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":82.14,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.3-70b-instruct","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 3.3 70B Instruct","description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.\nModel Card","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":40.44,"currency":"RUB","is_free":false}},{"id":"voyageai/voyage-4-large","object":"model","created":1789025613,"owned_by":"voyageai","display_name":"VoyageAI by MongoDB: voyage-4-large","description":"voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options. Learn more about voyage-4-large here: blog.voyageai.com/2026/01/15/voyage-4","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":[],"pricing":{"unit":"token","input_rub_per_million":15.17,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"amazon/nova-pro-v1","object":"model","created":1789025613,"owned_by":"amazon","display_name":"Amazon: Nova Pro 1.0","description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.\nNOTE: Video input is not supported at this time.","context_window":300000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":101.09,"output_rub_per_million":404.36,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-2024-11-20","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o (2024-11-20)","description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"google/gemini-embedding-2-preview","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini Embedding 2 Preview","description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Llama Nemotron Embed VL 1B V2 (free)","description":"The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model supports images containing text, tables, charts, and infographics.","context_window":131072,"modalities":["embeddings"],"input_modalities":["text","image"],"output_modalities":["embeddings"],"supported_parameters":["max_tokens","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"thedrummer/unslopnemo-12b","object":"model","created":1789025613,"owned_by":"thedrummer","display_name":"TheDrummer: UnslopNemo 12B","description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","context_window":1024000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-2.5-7b-instruct","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen2.5 7B Instruct","description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:\n•\nSignificantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\n•\nSignificant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\n•\nLong-context Support up to 128K tokens and can generate up to 8K tokens.\n•\nMultilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\nUsage of this model is subject to Tongyi Qianwen LICENSE AGREEMENT.","context_window":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":25.28,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.2-1b-instruct","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 3.2 1B Instruct","description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.\nSupporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.\nClick here for the original model card.\nUsage of this model is subject to Meta's Acceptable Use Policy.","context_window":60000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":3.42,"output_rub_per_million":25.4,"currency":"RUB","is_free":false}},{"id":"cohere/command-r-08-2024","object":"model","created":1789025613,"owned_by":"cohere","display_name":"Cohere: Command R (08-2024)","description":"command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and is competitive with the previous version of the larger Command R+ model.\nRead the launch post here.\nUse of this model is subject to Cohere's Usage Policy and SaaS Agreement.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"sentence-transformers/paraphrase-minilm-l6-v2","object":"model","created":1789025613,"owned_by":"sentence-transformers","display_name":"Sentence Transformers: paraphrase-MiniLM-L6-v2","description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval tasks.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"cohere/command-r-plus-08-2024","object":"model","created":1789025613,"owned_by":"cohere","display_name":"Cohere: Command R+ (08-2024)","description":"command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same.\nRead the launch post here.\nUse of this model is subject to Cohere's Usage Policy and SaaS Agreement.","context_window":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"sentence-transformers/all-minilm-l12-v2","object":"model","created":1789025613,"owned_by":"sentence-transformers","display_name":"Sentence Transformers: all-MiniLM-L12-v2","description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and similarity-scoring.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"sao10k/l3-lunaris-8b","object":"model","created":1789025613,"owned_by":"sao10k","display_name":"Sao10K: Llama 3 8B Lunaris","description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge.\nCreated by Sao10k, this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.\nFor best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":5.06,"output_rub_per_million":6.32,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-2024-08-06","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o (2024-08-06)","description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here.\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\nFor benchmarking against other models, it was briefly called \"im-also-a-good-gpt2-chatbot\"","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1263.61,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.1-70b-instruct","object":"model","created":1789025613,"owned_by":"meta-llama","display_name":"Meta: Llama 3.1 70B Instruct","description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.\nTo read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.","context_window":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":50.55,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-mini","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o-mini","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.\nCheck out the launch announcement to learn more.\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":75.82,"currency":"RUB","is_free":false}},{"id":"sentence-transformers/all-mpnet-base-v2","object":"model","created":1789025613,"owned_by":"sentence-transformers","display_name":"Sentence Transformers: all-mpnet-base-v2","description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and text ranking.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"mistralai/codestral-embed-2505","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Codestral Embed 2505","description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o (batch)","description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\nFor benchmarking against other models, it was briefly called \"im-also-a-good-gpt2-chatbot\"\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":631.81,"currency":"RUB","is_free":false}},{"id":"openai/text-embedding-3-large","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: Text Embedding 3 Large","description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":16.43,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"mistralai/mixtral-8x22b-instruct","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mixtral 8x22B Instruct","description":"Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:\n• strong math, coding, and reasoning\n• large context length (64k)\n• fluency in English, French, Italian, German, and Spanish\nSee benchmarks on the launch announcement here.\n#moe","context_window":65536,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"microsoft/wizardlm-2-8x22b","object":"model","created":1789025613,"owned_by":"microsoft","display_name":"WizardLM-2 8x22B","description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.\nIt is an instruct finetune of Mixtral 8x22B.\nTo read more about the model release, click here.\n#moe","context_window":65535,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":78.35,"output_rub_per_million":78.35,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4-turbo:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4 Turbo (batch)","description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\nTraining data: up to December 2023.","context_window":128000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":631.81,"output_rub_per_million":1895.42,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-3-haiku","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude 3 Haiku","description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\nSee the launch announcement and benchmark results here\n#multimodal","context_window":200000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":157.96,"currency":"RUB","is_free":false}},{"id":"openai/text-embedding-3-small","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: Text Embedding 3 Small","description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":2.53,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral Large","description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.\nIt supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.","context_window":128000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":252.73,"output_rub_per_million":758.17,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo-16k","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-3.5 Turbo 16k","description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.","context_window":16385,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":379.09,"output_rub_per_million":505.45,"currency":"RUB","is_free":false}},{"id":"mancer/weaver","object":"model","created":1789025613,"owned_by":"mancer","display_name":"Mancer: Weaver (alpha)","description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_window":8000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"undi95/remm-slerp-l2-13b","object":"model","created":1789025613,"owned_by":"undi95","display_name":"ReMM SLERP 13B","description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_window":6144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":44.23,"output_rub_per_million":82.14,"currency":"RUB","is_free":false}},{"id":"gryphe/mythomax-l2-13b","object":"model","created":1789025613,"owned_by":"gryphe","display_name":"MythoMax 13B","description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_window":8192,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":7.59,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-3.5 Turbo","description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\nTraining data up to Sep 2021.","context_window":16385,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":63.19,"output_rub_per_million":189.55,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4","description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.","context_window":8191,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":3790.83,"output_rub_per_million":7581.65,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.6:batch","object":"model","created":1789025613,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 4.6 (batch)","description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.\nFor users upgrading from earlier Opus versions, see our official migration guide here","context_window":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1579.52,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"voyageai/voyage-code-4","object":"model","created":1789025613,"owned_by":"voyageai","display_name":"VoyageAI by MongoDB: voyage-code-4","description":"voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048, 1024, 512, and 256 dimensions and multiple quantization options. Learn more about voyage-code-4 here: blog.voyageai.com/2026/08/13/voyage-code-4","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":[],"pricing":{"unit":"token","input_rub_per_million":15.17,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"voyageai/voyage-4","object":"model","created":1789025613,"owned_by":"voyageai","display_name":"VoyageAI by MongoDB: voyage-4","description":"voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embeddings in 2048, 1024, 512, and 256 dimensions, with multiple quantization options. Learn more about voyage-4 here: blog.voyageai.com/2026/01/15/voyage-4","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":[],"pricing":{"unit":"token","input_rub_per_million":7.59,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-embed-1b:free","object":"model","created":1789025613,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3 Embed 1B (free)","description":"NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller deployment footprint.","context_window":32768,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["max_tokens","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"google/gemini-embedding-2","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini Embedding 2","description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":25.28,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"perplexity/pplx-embed-v1-0.6b","object":"model","created":1789025613,"owned_by":"perplexity","display_name":"Perplexity: Embed V1 0.6B","description":"pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency embedding generation.","context_window":32000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":0.51,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"deepgram/aura-2","object":"model","created":1789025656,"owned_by":"deepgram","display_name":"Deepgram: Aura-2","description":"Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":[],"supported_voices":["aura-2-thalia-en","aura-2-agathe-fr","aura-2-agustina-es","aura-2-alvaro-es","aura-2-ama-ja","aura-2-amalthea-en","aura-2-andromeda-en","aura-2-antonia-es","aura-2-apollo-en","aura-2-aquila-es","aura-2-arcas-en","aura-2-aries-en","aura-2-asteria-en","aura-2-athena-en","aura-2-atlas-en","aura-2-aurelia-de","aura-2-aurora-en","aura-2-beatrix-nl","aura-2-callista-en","aura-2-carina-es","aura-2-celeste-es","aura-2-cesare-it","aura-2-cinzia-it","aura-2-cora-en","aura-2-cordelia-en","aura-2-cornelia-nl","aura-2-daphne-nl","aura-2-delia-en","aura-2-demetra-it","aura-2-diana-es","aura-2-dionisio-it","aura-2-draco-en","aura-2-ebisu-ja","aura-2-elara-de","aura-2-electra-en","aura-2-elio-it","aura-2-estrella-es","aura-2-fabian-de","aura-2-flavio-it","aura-2-fujin-ja","aura-2-gloria-es","aura-2-harmonia-en","aura-2-hector-fr","aura-2-helena-en","aura-2-hera-en","aura-2-hermes-en","aura-2-hestia-nl","aura-2-hyperion-en","aura-2-iris-en","aura-2-izanami-ja","aura-2-janus-en","aura-2-javier-es","aura-2-julius-de","aura-2-juno-en","aura-2-jupiter-en","aura-2-kara-de","aura-2-lara-de","aura-2-lars-nl","aura-2-leda-nl","aura-2-livia-it","aura-2-luciano-es","aura-2-luna-en","aura-2-maia-it","aura-2-mars-en","aura-2-melia-it","aura-2-minerva-en","aura-2-neptune-en","aura-2-nestor-es","aura-2-odysseus-en","aura-2-olivia-es","aura-2-ophelia-en","aura-2-orion-en","aura-2-orpheus-en","aura-2-pandora-en","aura-2-phoebe-en","aura-2-pluto-en","aura-2-rhea-nl","aura-2-roman-nl","aura-2-sander-nl","aura-2-saturn-en","aura-2-selena-es","aura-2-selene-en","aura-2-silvia-es","aura-2-sirio-es","aura-2-theia-en","aura-2-uzume-ja","aura-2-valerio-es","aura-2-vesta-en","aura-2-viktoria-de","aura-2-zeus-en"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":3790.83,"unit":"m characters"}],"is_free":false}},{"id":"intfloat/e5-base-v2","object":"model","created":1789025613,"owned_by":"intfloat","display_name":"Intfloat: E5-Base-v2","description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring, retrieval and clustering.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"mistralai/devstral-2512","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Devstral 2 2512","description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.\nDevstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.","context_window":262144,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":50.55,"output_rub_per_million":252.73,"currency":"RUB","is_free":false}},{"id":"sentence-transformers/all-minilm-l6-v2","object":"model","created":1789025613,"owned_by":"sentence-transformers","display_name":"Sentence Transformers: all-MiniLM-L6-v2","description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering, similarity scoring, and text ranking.","context_window":512,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":0.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-embed-2312","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Embed 2312","description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively capture semantic relationships in text.","context_window":8192,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":12.64,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"google/gemini-embedding-001","object":"model","created":1789025613,"owned_by":"google","display_name":"Google: Gemini Embedding 001","description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.","context_window":20000,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-embedding-4b","object":"model","created":1789025613,"owned_by":"qwen","display_name":"Qwen: Qwen3 Embedding 4B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.","context_window":32768,"modalities":["embeddings"],"input_modalities":["text"],"output_modalities":["embeddings"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":2.53,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.5:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.5 (batch)","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":315.91,"output_rub_per_million":1895.42,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"mistralai/codestral-2508:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Codestral 2508 (batch)","description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\nBlog Post","context_window":256000,"modalities":["text"],"input_modalities":["text","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.96,"output_rub_per_million":56.87,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.2:batch","object":"model","created":1789025613,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.2 (batch)","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.\nReasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.","context_window":1048576,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":88.46,"output_rub_per_million":278,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-mini:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-4o-mini (batch)","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.\nCheck out the launch announcement to learn more.\n#multimodal","context_window":128000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":37.91,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large-2512:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Mistral Large 3 2512 (batch)","description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_window":262144,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-8b-2512:batch","object":"model","created":1789025613,"owned_by":"mistralai","display_name":"Mistral: Ministral 3 8B 2512 (batch)","description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_window":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.48,"output_rub_per_million":9.48,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 (batch)","description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","context_window":1050000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":157.96,"output_rub_per_million":947.71,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.4-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Pro (batch)","description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","context_window":1050000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":11372.48,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.5-pro:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.5 Pro (batch)","description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":1895.42,"output_rub_per_million":11372.48,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-terra:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-5.6 Terra (batch)","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","context_window":1050000,"modalities":["text"],"input_modalities":["file","image","text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":126.37,"output_rub_per_million":758.17,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1.27,"unit":"1k calls"}],"is_free":false}},{"id":"recraft/recraft-v4-styles-pro-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Styles Pro Vector","description":"Recraft V4 Styles Pro Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":15.17,"unit":"image"}],"is_free":false}},{"id":"openai/gpt-3.5-turbo:batch","object":"model","created":1789025613,"owned_by":"openai","display_name":"OpenAI: GPT-3.5 Turbo (batch)","description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\nTraining data up to Sep 2021.","context_window":16385,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":31.6,"output_rub_per_million":94.78,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seedream-4.5","object":"model","created":1789025643,"owned_by":"bytedance-seed","display_name":"ByteDance Seed: Seedream 4.5","description":"Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...","context_window":0,"modalities":["image"],"input_modalities":["image","text"],"output_modalities":["image"],"supported_parameters":["resolution","aspect_ratio","n","input_references","seed"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":5.06,"unit":"image"}],"is_free":false}},{"id":"recraft/recraft-v4-styles-pro","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Styles Pro","description":"Recraft V4 Styles Pro is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":12.64,"unit":"image"}],"is_free":false}},{"id":"recraft/recraft-v4-styles-vector","object":"model","created":1789025643,"owned_by":"recraft","display_name":"Recraft: Recraft V4 Styles Vector","description":"Recraft V4 Styles Vector is a style-consistent image generation model from Recraft. Every request requires at least one style reference image and generates a new image that reproduces the reference's...","context_window":0,"modalities":["image"],"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["aspect_ratio","output_format","n","input_references"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"output_image","price_rub":6.32,"unit":"image"}],"is_free":false}},{"id":"microsoft/mai-transcribe-2","object":"model","created":1789025650,"owned_by":"microsoft","display_name":"MicrosoftAI: MAI-Transcribe 2","description":"MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["max_completion_tokens","max_tokens","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Hours","price_rub":12.64,"unit":"hour"}],"is_free":false}},{"id":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","object":"model","created":1789025650,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B","description":"Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Seconds","price_rub":0.01,"unit":"second"}],"is_free":false}},{"id":"microsoft/mai-transcribe-1.5","object":"model","created":1789025650,"owned_by":"microsoft","display_name":"MicrosoftAI: MAI-Transcribe 1.5","description":"MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable transcription across 43 languages, diverse...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["max_completion_tokens","max_tokens","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Hours","price_rub":45.49,"unit":"hour"}],"is_free":false}},{"id":"nvidia/parakeet-tdt-0.6b-v3","object":"model","created":1789025650,"owned_by":"nvidia","display_name":"NVIDIA: Parakeet TDT 0.6B v3","description":"Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","top_k","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":0.19,"unit":"minute"}],"is_free":false}},{"id":"mistralai/voxtral-mini-transcribe","object":"model","created":1789025650,"owned_by":"mistralai","display_name":"Mistral: Voxtral Mini Transcribe","description":"Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,...","context_window":0,"modalities":["transcription"],"input_modalities":["audio"],"output_modalities":["transcription"],"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Audio Minutes","price_rub":0.38,"unit":"minute"}],"is_free":false}},{"id":"qwen/qwen-audio-3.0-tts-flash","object":"model","created":1789025656,"owned_by":"qwen","display_name":"Qwen: Qwen-Audio-3.0-TTS Flash","description":"Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","context_window":0,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"supported_voices":["loongjohn","longanhuan_v3.6"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":1895.42,"unit":"m characters"}],"is_free":false}},{"id":"x-ai/grok-voice-tts-1.0","object":"model","created":1789025656,"owned_by":"x-ai","display_name":"SpaceXAI: Grok Voice TTS 1.0","description":"Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara,...","context_window":15000,"modalities":["speech"],"input_modalities":["text"],"output_modalities":["speech"],"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","top_logprobs","top_p"],"supported_voices":["eve","ara","rex","sal","leo"],"pricing":{"unit":"unit","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","per_unit":[{"sku":"Characters","price_rub":1895.42,"unit":"m characters"}],"is_free":false}}]}