{"object":"list","data":[{"id":"~unbiased/pareto-latest","object":"model","created":1792918533,"owned_by":"unbiased","display_name":"Pareto Latest","description":"This model always redirects to the latest model in the Pareto family.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":96.2,"output_rub_per_million":384.77,"currency":"RUB","is_free":false}},{"id":"unbiased/pareto-26.9","object":"model","created":1792918533,"owned_by":"unbiased","display_name":"Pareto 26.9","description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_window":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":300.6,"output_rub_per_million":901.79,"currency":"RUB","is_free":false}},{"id":"liquid/lfm-2.5-2.6b","object":"model","created":1792918635,"owned_by":"liquid","display_name":"LiquidAI: LFM2.5-2.6B","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":128000,"context_length":128000,"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":42.09,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.6","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3005.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-5.5","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: Claude Opus 5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.\nThe model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.","context_window":1000000,"context_length":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":480.96,"output_rub_per_million":2404.77,"currency":"RUB","is_free":false}},{"id":"meta/muse-spark-open","object":"model","created":1792918533,"owned_by":"meta","display_name":"Meta: Muse Spark Open","description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers actually work in.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file","audio"],"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":150.3,"output_rub_per_million":511.02,"currency":"RUB","is_free":false}},{"id":"~deepseek/deepseek-pro-latest","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek Pro Latest","description":"This model always redirects to the latest model in the DeepSeek Pro family.","context_window":1048576,"context_length":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":14.29,"output_rub_per_million":961.91,"currency":"RUB","is_free":false}},{"id":"nousresearch/hermes-3-llama-3.1-70b","object":"model","created":1792918533,"owned_by":"nousresearch","display_name":"Nous: Hermes 3 70B Instruct","description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), 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](/models/meta-llama/llama-3.1-70b-instruct), 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,"context_length":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":84.17,"output_rub_per_million":84.17,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-super-vl","object":"model","created":1792918533,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Super VL","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.\nIt uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.","context_window":1048576,"context_length":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":18.04,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-lite-image","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":180.36,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.1-codex","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"gryphe/mythomax-l2-13b","object":"model","created":1792918533,"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,"context_length":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":9.62,"output_rub_per_million":13.23,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-12b-it","object":"model","created":1792918533,"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](google/gemma-3-27b-it)","context_window":131072,"context_length":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":6.02,"output_rub_per_million":18.04,"currency":"RUB","is_free":false}},{"id":"inference-net/schematron-v2-small","object":"model","created":1792918533,"owned_by":"inference-net","display_name":"Inference.net: Schematron V2 Small","description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.","context_window":128000,"context_length":128000,"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":6.02,"output_rub_per_million":27.66,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4.1-flash-1017","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental [V4 Flash Vision Exp](/models/deepseek/deepseek-v4-flash-vision-exp).\nIt is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds [V4 Pro](/models/deepseek/deepseek-v4-pro-0813) on performance, speed, and task completion time.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"elorian/glimpse","object":"model","created":1792918533,"owned_by":"elorian","display_name":"Elorian: Glimpse","description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than converting them to text first, so it can find small details in dense scenes, track events across video frames, and ground its answers in what is actually on screen. It is suited for agentic visual workflows such as visual search, video captioning, and dense counting, and for physical-world use cases in robotics, construction, engineering, and manufacturing.","context_window":262144,"context_length":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","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":72.15,"output_rub_per_million":360.72,"currency":"RUB","is_free":false}},{"id":"inception/mercury-2.5","object":"model","created":1792918533,"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](https://www.inceptionlabs.ai/blog/introducing-mercury-2-5).","context_window":260000,"context_length":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":4.81,"output_rub_per_million":18.04,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash-lite","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large-4-0","object":"model","created":1792918533,"owned_by":"mistralai","display_name":"Mistral: Mistral Large 4","description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up to 256K output tokens, and supports tool calling and structured outputs.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image"],"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_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":163.53,"output_rub_per_million":502.6,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-flash-preview","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":360.72,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"inclusionai/ling-3.0-flash-vl","object":"model","created":1792918533,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.0 Flash VL","description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual agent capabilities. Hybrid instant/reasoning model with tool calling.","context_window":131072,"context_length":131072,"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","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":7.22,"output_rub_per_million":21.65,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":961.91,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-luna","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":24.05,"output_rub_per_million":144.29,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.6-sol","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":480.96,"output_rub_per_million":2404.77,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"liquid/lfm-2.5-24b-a2b","object":"model","created":1792918533,"owned_by":"liquid","display_name":"LiquidAI: LFM2.5-24B-A2B","description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.","context_window":128000,"context_length":128000,"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"],"pricing":{"unit":"token","input_rub_per_million":6.02,"output_rub_per_million":84.17,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-terra-pro","object":"model","created":1792918533,"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](/models/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Terra](/models/openai/gpt-5.6-terra) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"~openai/gpt-terra-latest","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT Terra Latest","description":"This model always redirects to the latest model in the GPT Terra family.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"meta/muse-spark-1.3","object":"model","created":1792918533,"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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file"],"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":150.3,"output_rub_per_million":511.02,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"sakana/fugu-ultra-v2","object":"model","created":1792918533,"owned_by":"sakana","display_name":"Sakana: Fugu Ultra v2","description":"Fugu Ultra v2 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 fixed pool of open and specialized models and to recursively call instances of itself.\nFugu Ultra v2 prioritizes answer quality on complex multi-step reasoning, autonomous research, and full-stack software development, and does not rely on individual proprietary frontier models in its pool. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search. Prompts above 272K tokens are billed at a higher rate. Orchestration tokens consumed by the system are billed as standard input/output tokens.","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"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":601.2,"output_rub_per_million":3607.16,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-6-luna-pro","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6 Luna Pro","description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](/models/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6 Luna](/models/openai/gpt-6-luna) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":12.03,"output_rub_per_million":60.12,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-6-sol","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6 Sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.5-flash-02-23","object":"model","created":1792918533,"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,"context_length":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":7.82,"output_rub_per_million":31.27,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-omni-flash","object":"model","created":1792918533,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 Omni Flash","description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization, video editing and production workflows, audio-video dialogue, coding, knowledge work, and GUI interaction, and it is particularly strong at long-form multimedia tasks that combine speech, sound, and visual context. It also supports two-channel and four-channel spatial audio understanding.","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","audio","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":18.04,"output_rub_per_million":56.52,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-26b-a4b-it","object":"model","created":1792918533,"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,"context_length":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":8.12,"output_rub_per_million":27.06,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","object":"model","created":1792918533,"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,"context_length":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":25.26,"output_rub_per_million":228.46,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-3.5-mini","object":"model","created":1792918533,"owned_by":"aion-labs","display_name":"AionLabs: Aion 3.5 Mini","description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses the same 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":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":84.17,"output_rub_per_million":168.34,"currency":"RUB","is_free":false}},{"id":"stepfun/step-5-preview","object":"model","created":1792918533,"owned_by":"stepfun","display_name":"StepFun: Step 5 Preview","description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.\nIt is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.","context_window":1048576,"context_length":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":120.24,"output_rub_per_million":324.65,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.7","object":"model","created":1792918533,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.7","description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.\nThe model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.","context_window":500000,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"xingchen-agi/xing4.0-29b-a4b:free","object":"model","created":1792918533,"owned_by":"xingchen-agi","display_name":"XingChen: Xing4.0 29B A4B (free)","description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token and a native 256K-token context window. It was trained entirely on Ascend NPUs with the MindSpore framework and is tuned for complex engineering and agent work: tool calling, multi-step planning, and long-context execution. Reasoning is on by default and can be turned off.","context_window":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","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":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"moonshotai/kimi-k3.1-pro","object":"model","created":1792918533,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K3.1 Pro","description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m3.1-flash","object":"model","created":1792918533,"owned_by":"minimax","display_name":"MiniMax: MiniMax M3.1 Flash","description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.","context_window":1048576,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"inception/mercury-3","object":"model","created":1792918533,"owned_by":"inception","display_name":"Inception: Mercury 3","description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such as search agents, voice pipelines, and coding subagents. Its distinguishing trait is speed: more than 40x larger than the first Mercury model while generating at the same throughput, because it produces and refines tokens in parallel rather than one at a time.","context_window":1000000,"context_length":1000000,"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":12.03,"output_rub_per_million":42.09,"currency":"RUB","is_free":false}},{"id":"thedrummer/unslopnemo-12b","object":"model","created":1792918533,"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,"context_length":1024000,"modalities":["text"],"input_modalities":["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":48.1,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"moondream/moondream3-preview","object":"model","created":1792918533,"owned_by":"moondream","display_name":"Moondream: Moondream 3 Preview","description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.","context_window":32000,"context_length":32000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.08,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-super-vl:free","object":"model","created":1792918533,"owned_by":"nvidia","display_name":"NVIDIA: Nemotron 3.5 Super VL (free)","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.\nIt uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","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":"scaledown/summarize","object":"model","created":1792918533,"owned_by":"scaledown","display_name":"ScaleDown: Summarize","description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for document review, transcript digests, and RAG pre-processing where retrieved content must be shortened before reaching another model. Format, focus, language, and length are steered through the system prompt, while sampling is fixed to a configuration tuned for faithful output.\nLearn more in ScaleDown's docs: https://docs.scaledown.ai/api-reference/summarize-overview","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["max_tokens"],"pricing":{"unit":"token","input_rub_per_million":4.81,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"scaledown/extract","object":"model","created":1792918533,"owned_by":"scaledown","display_name":"ScaleDown: Extract","description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the model returns each matching span with a confidence score, character offsets, and surrounding context. It is suited for pulling structured values out of contracts, invoices, emails, and transcripts, and includes built-in OCR so scanned images and PDFs work without a separate step.\nLearn more in ScaleDown's docs: https://docs.scaledown.ai/api-reference/extract-overview","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"output_modalities":["text"],"supported_parameters":["max_tokens"],"pricing":{"unit":"token","input_rub_per_million":4.81,"output_rub_per_million":0,"currency":"RUB","is_free":false}},{"id":"meta/muse-wonder","object":"model","created":1792918533,"owned_by":"meta","display_name":"Meta: Muse Wonder","description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.\nThe model handles long-horizon work: it plans, delegates to sub-agents, calls tools in parallel, and recovers from errors, so multi-step tasks run to completion without step-by-step direction. It can also operate browsers and desktop and mobile applications, and works across many files in existing repositories to make and verify changes. Muse Wonder carries important context across conversations and retrieves the details relevant to the task at hand. And it's trained for Active Focus, so it works toward your goal even when a task gets challenging.\nIn Meta's testing, it performs well on complex engineering tasks, extended agentic sessions, and multi-file refactors to tackle developers' most demanding work.","context_window":1048576,"context_length":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":480.96,"output_rub_per_million":2404.77,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-6.1-sol","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6.1 Sol","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"meta/muse-spark-1.2-contributor","object":"model","created":1792918533,"owned_by":"meta","display_name":"Meta: Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark 1.2. Your prompts and outputs may be used to improve Meta’s products, making it ideal for experimentation, learning, and early-stage projects without worry about spend.\nIt is a reasoning model from Meta, tailored for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window. The 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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file"],"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":12.03,"output_rub_per_million":24.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"perceptron/perceptron-mk1.5","object":"model","created":1792918533,"owned_by":"perceptron","display_name":"Perceptron: Perceptron Mk1.5","description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks, and clips.\nIt supports graded reasoning through the standard reasoning controls, function tool calling, and structured outputs via JSON Schema. Structured annotations are emitted inline with text only when requested via the `annotation_format` parameter (`\"point\"`, `\"box\"`, or `\"polygon\"` for spatial localization on images, `\"clip\"` for temporal segments in video). Video soundtracks are analyzed only when enabled per request via `provider.options.perceptron.enable_audio_in_video: true`.","context_window":36864,"context_length":36864,"modalities":["text"],"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.04,"output_rub_per_million":180.36,"currency":"RUB","is_free":false}},{"id":"fireworks/ember-1","object":"model","created":1792918533,"owned_by":"fireworks","display_name":"Fireworks: Ember-1","description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](/models/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.","context_window":1048576,"context_length":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":360.72,"output_rub_per_million":1803.58,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.3-prime","object":"model","created":1792918533,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3 Prime","description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token context window and up to 128K output tokens, and targets coding and agentic workloads, including long-horizon multi-turn agent orchestration, real-time conversation, and streaming code generation.\nReasoning is always on and cannot be disabled. Reasoning efforts `low`, `high`, and `max` are supported; `max` is the default.","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":336.67,"output_rub_per_million":1058.1,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k3","object":"model","created":1792918533,"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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":28.74,"output_rub_per_million":1298.58,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-3.5","object":"model","created":1792918533,"owned_by":"aion-labs","display_name":"AionLabs: Aion 3.5","description":"Aion 3.5 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":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":360.72,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"cohere/command-a-plus","object":"model","created":1792918533,"owned_by":"cohere","display_name":"Cohere: Command A+","description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured outputs (JSON object and JSON schema), optional reasoning, and configurable safety modes.","context_window":192000,"context_length":192000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.08,"output_rub_per_million":180.36,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.6-flash","object":"model","created":1792918533,"owned_by":"xiaomi","display_name":"Xiaomi: MiMo-V2.6-Flash","description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","context_window":1050000,"context_length":1050000,"modalities":["text"],"input_modalities":["text","image","video","audio"],"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":16.84,"output_rub_per_million":33.67,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.6-pro","object":"model","created":1792918533,"owned_by":"xiaomi","display_name":"Xiaomi: MiMo-V2.6-Pro","description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding workloads. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","context_window":1050000,"context_length":1050000,"modalities":["text"],"input_modalities":["text","image","video","audio"],"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":52.31,"output_rub_per_million":104.61,"currency":"RUB","is_free":false}},{"id":"~deepseek/deepseek-flash-latest","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek Flash Latest","description":"This model always redirects to the latest model in the DeepSeek Flash family.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":2.41,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","object":"model","created":1792918533,"owned_by":"xiaomi","display_name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x the output speed. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":523.04,"output_rub_per_million":1046.08,"currency":"RUB","is_free":false}},{"id":"~openai/gpt-sol-latest","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT Sol Latest","description":"This model always redirects to the latest model in the GPT Sol family.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-5.3-flashx","object":"model","created":1792918533,"owned_by":"z-ai","display_name":"Z.ai: GLM 5.3 FlashX","description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture (320B total parameters, 18B active), it is suited for efficient coding, visual understanding, and long-horizon agent tasks with a 1M-token context window.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":44.49,"output_rub_per_million":150.3,"currency":"RUB","is_free":false}},{"id":"~openai/gpt-astra-latest","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT Astra Latest","description":"This model always redirects to the latest model in the GPT Astra family.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"prism-ml/ternary-bonsai-2-27b","object":"model","created":1792918533,"owned_by":"prism-ml","display_name":"PrismML: Ternary Bonsai 2 27B","description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.","context_window":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","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":9.02,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"~openai/gpt-luna-latest","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT Luna Latest","description":"This model always redirects to the latest model in the GPT Luna family.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":12.03,"output_rub_per_million":60.12,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"inference-net/schematron-v2-turbo","object":"model","created":1792918533,"owned_by":"inference-net","display_name":"Inference.net: Schematron V2 Turbo","description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.","context_window":128000,"context_length":128000,"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":3.61,"output_rub_per_million":18.04,"currency":"RUB","is_free":false}},{"id":"sakana/fugu-max","object":"model","created":1792918533,"owned_by":"sakana","display_name":"Sakana: Fugu Max","description":"Fugu Max is the cost-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 fixed pool of open-weights and specialized models, including NVIDIA's Nemotron family, and to recursively call instances of itself.\nFugu Max dynamically selects efficient combinations of expert agents to improve quality and cost together, and is priced flat regardless of context length. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search and web fetch. Orchestration tokens consumed by the system are billed as standard input/output tokens.","context_window":1000000,"context_length":1000000,"modalities":["text"],"input_modalities":["text","image","file"],"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":240.48,"output_rub_per_million":721.44,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"nex-agi/nex-n2.5-mini","object":"model","created":1792918533,"owned_by":"nex-agi","display_name":"Nex AGI: Nex-N2.5-Mini","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,"context_length":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":3.01,"output_rub_per_million":12.03,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4.1-flash","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental [V4 Flash Vision Exp](/models/deepseek/deepseek-v4-flash-vision-exp).\nIt is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds [V4 Pro](/models/deepseek/deepseek-v4-pro-0813) on performance, speed, and task completion time.","context_window":1048576,"context_length":1048576,"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","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":2.41,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"nex-agi/nex-n2.5-pro","object":"model","created":1792918533,"owned_by":"nex-agi","display_name":"Nex AGI: Nex-N2.5-Pro","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,"context_length":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.02,"output_rub_per_million":30.06,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-2.5-72b-instruct","object":"model","created":1792918533,"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](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","context_window":32768,"context_length":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":43.29,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra-pro","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6 Astra Pro","description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](/models/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Astra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6 Astra](/models/openai/gpt-6-astra) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-opus-4.8","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3005.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"meta/muse-spark-1.3-contributor","object":"model","created":1792918533,"owned_by":"meta","display_name":"Meta: Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed. Prompts and outputs may be used to improve Meta’s products.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file"],"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":12.03,"output_rub_per_million":24.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.8-27b","object":"model","created":1792918533,"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,"context_length":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":24.05,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"dots-studio/dots-3-note-preview:free","object":"model","created":1792918533,"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,"context_length":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":1792918533,"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,"context_length":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":90.18,"output_rub_per_million":450.9,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-4.6","object":"model","created":1792918533,"owned_by":"x-ai","display_name":"SpaceXAI: Grok 4.6","description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_window":500000,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"liquid/lfm-2.5-2.6b:free","object":"model","created":1792918533,"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,"context_length":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"],"pricing":{"unit":"token","input_rub_per_million":0,"output_rub_per_million":0,"currency":"RUB","is_free":true}},{"id":"nvidia/nemotron-3.5-lightning","object":"model","created":1792918533,"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,"context_length":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":8.42,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-5","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"upstage/solar-pro4","object":"model","created":1792918533,"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.\nWhen using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.","context_window":524288,"context_length":524288,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"meta/muse-glimmer-30b","object":"model","created":1792918533,"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,"context_length":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","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":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling-small","object":"model","created":1792918533,"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":524288,"context_length":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","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":54.11,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.5","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy-mt2-30b-a3b","object":"model","created":1792918533,"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,"context_length":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":8.9,"output_rub_per_million":35.48,"currency":"RUB","is_free":false}},{"id":"~deepseek/deepseek-v4-flash-latest","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V4 Flash Latest","description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_window":1048576,"context_length":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_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":5.08,"output_rub_per_million":20.37,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-pro-preview","object":"model","created":1792918533,"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,"context_length":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":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-3.0-mini","object":"model","created":1792918533,"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,"context_length":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":84.17,"output_rub_per_million":168.34,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-3.0","object":"model","created":1792918533,"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,"context_length":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":360.72,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.2","object":"model","created":1792918533,"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,"context_length":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":4.11,"output_rub_per_million":841.67,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-luna","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6 Luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":12.03,"output_rub_per_million":60.12,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"meta/muse-spark-1.2","object":"model","created":1792918533,"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, 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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file"],"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":150.3,"output_rub_per_million":511.02,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"deepseek/deepseek-v4-flash-0731","object":"model","created":1792918533,"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":1048576,"context_length":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_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":5.08,"output_rub_per_million":20.37,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.6-flash","object":"model","created":1792918533,"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,"context_length":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":90.18,"output_rub_per_million":450.9,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"bytedance-seed/seed-2-1-turbo","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-image","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":360.72,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"inclusionai/ling-3.0-flash","object":"model","created":1792918533,"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,"context_length":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":2.53,"output_rub_per_million":7.58,"currency":"RUB","is_free":false}},{"id":"stepfun/step-3.7-flash","object":"model","created":1792918533,"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,"context_length":262144,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","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":24.05,"output_rub_per_million":138.28,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.7-max","object":"model","created":1792918533,"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,"context_length":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":177.36,"output_rub_per_million":532.06,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-luna-pro","object":"model","created":1792918533,"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](/models/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Luna](/models/openai/gpt-5.6-luna) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":24.05,"output_rub_per_million":144.29,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3.5-flash-lite","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":300.6,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-nano-banana-2.1","object":"model","created":1792918533,"owned_by":"google","display_name":"Google: Nano Banana 2.1","description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter.","context_window":65536,"context_length":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","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":180.36,"output_rub_per_million":901.79,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"x-ai/grok-build-0.1","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":240.48,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"meituan/longcat-2.0","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-terra","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.6-35b-a3b","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":114.23,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-pro","object":"model","created":1792918533,"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,"context_length":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":25.11,"output_rub_per_million":50.22,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.5","object":"model","created":1792918533,"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,"context_length":1050000,"modalities":["text"],"input_modalities":["text","audio","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":14.31,"output_rub_per_million":28.62,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.1","object":"model","created":1792918533,"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,"context_length":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":168.34,"output_rub_per_million":529.05,"currency":"RUB","is_free":false}},{"id":"cohere/north-mini-code:free","object":"model","created":1792918533,"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,"context_length":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":"moonshotai/kimi-k2.7-code","object":"model","created":1792918533,"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,"context_length":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":80.71,"output_rub_per_million":402.8,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":288.58,"currency":"RUB","is_free":false}},{"id":"unbiased/pareto-26.10","object":"model","created":1792918533,"owned_by":"unbiased","display_name":"Pareto 26.10","description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":96.2,"output_rub_per_million":384.77,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.3-flash","object":"model","created":1792918533,"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":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"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":18.04,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"google/lyria-3-pro-preview","object":"model","created":1792918533,"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,"context_length":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":9.62,"unit":"song"}],"is_free":false}},{"id":"nvidia/nemotron-3-super-120b-a12b:free","object":"model","created":1792918533,"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,"context_length":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":"google/gemini-3.1-flash-lite-preview","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":180.36,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"writer/palmyra-x5","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"~x-ai/grok-latest","object":"model","created":1792918533,"owned_by":"x-ai","display_name":"xAI: Grok Latest","description":"This model always redirects to the latest Grok model from xAI.","context_window":500000,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3.8-flash","object":"model","created":1792918533,"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,"context_length":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":99.2,"output_rub_per_million":495.99,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.7-plus","object":"model","created":1792918533,"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,"context_length":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":38.48,"output_rub_per_million":153.91,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.2-codex","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":210.42,"output_rub_per_million":1683.34,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.5-flash","object":"model","created":1792918533,"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,"context_length":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":180.36,"output_rub_per_million":1082.15,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-oss-safeguard-20b","object":"model","created":1792918533,"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](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).","context_window":131072,"context_length":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":9.02,"output_rub_per_million":36.08,"currency":"RUB","is_free":false}},{"id":"mistralai/devstral-2512","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"recursive/flint-v1.0:free","object":"model","created":1792918533,"owned_by":"recursive","display_name":"Recursive: Flint (free)","description":"Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited for investigating codebases, fixing bugs, implementing features, and writing tests.","context_window":262144,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","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":"reflection/beam-1.0-501b-a23b","object":"model","created":1792918533,"owned_by":"reflection","display_name":"Reflection: Beam 1.0 501B A23B","description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a 1M-token context window.\nBeam targets software engineering, multi-step tool use, and mathematical and scientific reasoning, with an emphasis on token efficiency. It takes text input and produces text output, supports configurable reasoning effort, function calling and structured outputs, and is released under Apache 2.0.","context_window":1048576,"context_length":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":30.06,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"moondream/moondream3.1-9b-a2b","object":"model","created":1792918533,"owned_by":"moondream","display_name":"Moondream: Moondream 3.1","description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.","context_window":32000,"context_length":32000,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.08,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":180.36,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-haiku-5.5","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: Claude Haiku 5.5","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.\nIt is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.","context_window":1000000,"context_length":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":12.03,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"thinkingmachines/inkling","object":"model","created":1792918533,"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":524288,"context_length":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":120.24,"output_rub_per_million":486.97,"currency":"RUB","is_free":false}},{"id":"inclusionai/ling-3.1-flash","object":"model","created":1792918533,"owned_by":"inclusionai","display_name":"inclusionAI: Ling 3.1 Flash","description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","context_window":262144,"context_length":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":9.02,"output_rub_per_million":27.06,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m3","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"openai/gpt-chat-latest","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3607.16,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-sonnet-5.5","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.\nThinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.","context_window":1000000,"context_length":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":240.48,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-max-prime","object":"model","created":1792918533,"owned_by":"qwen","display_name":"Qwen: Qwen3.8 Max Prime","description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. Tool calling, structured outputs, and configurable reasoning effort are supported, matching Qwen3.8 Max.","context_window":1000000,"context_length":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":480.96,"output_rub_per_million":1442.87,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.1-terminus","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: DeepSeek V3.1 Terminus","description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-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,"context_length":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","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":32.47,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder-flash","object":"model","created":1792918533,"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,"context_length":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":23.45,"output_rub_per_million":117.24,"currency":"RUB","is_free":false}},{"id":"xiaomi/mimo-v2.5-pro","object":"model","created":1792918533,"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,"context_length":1050000,"modalities":["text"],"input_modalities":["text"],"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":36.62,"output_rub_per_million":73.23,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.6v","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":108.22,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.5","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3005.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.1","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-flash-image","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-image-2","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-5.4 Image 2","description":"[GPT-5.4](/models/openai/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,"context_length":272000,"modalities":["image","text"],"input_modalities":["image","text","file"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","top_logprobs","verbosity"],"pricing":{"unit":"token","input_rub_per_million":961.91,"output_rub_per_million":1803.58,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"moonshotai/kimi-k2.6","object":"model","created":1792918533,"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,"context_length":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":78.16,"output_rub_per_million":410.02,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-sonnet-4.5","object":"model","created":1792918533,"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,"context_length":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":360.72,"output_rub_per_million":1803.58,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5-mini","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":30.06,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-astra","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.8-max-0902","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-fable-5.1","object":"model","created":1792918533,"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,"context_length":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":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-nano","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":6.02,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5.3","object":"model","created":1792918533,"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":1048576,"context_length":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":9.5,"output_rub_per_million":168.34,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-plus","object":"model","created":1792918533,"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,"context_length":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":39.08,"output_rub_per_million":234.47,"currency":"RUB","is_free":false}},{"id":"cohere/command-a","object":"model","created":1792918533,"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,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2.0-code","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":360.72,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.1","object":"model","created":1792918533,"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,"context_length":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":1803.58,"output_rub_per_million":9017.88,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-27b","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-pro-0813","object":"model","created":1792918533,"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,"context_length":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":79.36,"output_rub_per_million":238.08,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-pro-preview","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"anthropic/claude-sonnet-4.6","object":"model","created":1792918533,"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,"context_length":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":360.72,"output_rub_per_million":1803.58,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","object":"model","created":1792918533,"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,"context_length":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":10.83,"output_rub_per_million":36.08,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5-air","object":"model","created":1792918533,"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,"context_length":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":15.64,"output_rub_per_million":102.21,"currency":"RUB","is_free":false}},{"id":"openai/o1","object":"model","created":1792918533,"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](https://openai.com/o1).","context_window":200000,"context_length":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":1803.58,"output_rub_per_million":7214.31,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-5","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: 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,"context_length":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":601.2,"output_rub_per_million":3005.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-235b-a22b-2507","object":"model","created":1792918533,"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,"context_length":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":10.83,"output_rub_per_million":66.14,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.6-sol-pro","object":"model","created":1792918533,"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](/models/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-5.6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-5.6 Sol](/models/openai/gpt-5.6-sol) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":480.96,"output_rub_per_million":2404.77,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"minimax/minimax-m1","object":"model","created":1792918533,"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,"context_length":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":66.14,"output_rub_per_million":264.53,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-fable-5","object":"model","created":1792918533,"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,"context_length":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":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-32b","object":"model","created":1792918533,"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,"context_length":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_a","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":9.62,"output_rub_per_million":33.67,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-content-safety","object":"model","created":1792918533,"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,"context_length":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","seed","stop","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":24.05,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5v-turbo","object":"model","created":1792918533,"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,"context_length":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":144.29,"output_rub_per_million":480.96,"currency":"RUB","is_free":false}},{"id":"google/gemini-4-argon","object":"model","created":1792918533,"owned_by":"google","display_name":"Google: Gemini 4 Argon","description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.","context_window":1048576,"context_length":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":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-4.1-mini","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":192.39,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3-5","object":"model","created":1792918533,"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,"context_length":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":180.36,"output_rub_per_million":901.79,"currency":"RUB","is_free":false}},{"id":"thedrummer/skyfall-36b-v2","object":"model","created":1792918533,"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,"context_length":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":66.14,"output_rub_per_million":96.2,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","object":"model","created":1792918533,"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,"context_length":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":"bytedance-seed/seed-2.0-mini","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-saba","object":"model","created":1792918533,"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](https://mistral.ai/en/news/mistral-saba)","context_window":32768,"context_length":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":24.05,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"openai/gpt-audio","object":"model","created":1792918533,"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,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash","object":"model","created":1792918533,"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,"context_length":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":10.95,"output_rub_per_million":21.89,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-35b-a3b","object":"model","created":1792918533,"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,"context_length":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":16.84,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large-2407","object":"model","created":1792918533,"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](https://mistral.ai/news/mistral-large-2407/).\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,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-2024-05-13","object":"model","created":1792918533,"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](/models/openai/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\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n#multimodal","context_window":128000,"context_length":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":601.2,"output_rub_per_million":1803.58,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4-turbo","object":"model","created":1792918533,"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,"context_length":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":1202.39,"output_rub_per_million":3607.16,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","object":"model","created":1792918533,"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,"context_length":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":"minimax/minimax-m2.1","object":"model","created":1792918533,"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,"context_length":204800,"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":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"anthropic/claude-opus-4.7","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3005.96,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"google/lyria-3-clip-preview","object":"model","created":1792918533,"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,"context_length":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":4.81,"unit":"song"}],"is_free":false}},{"id":"qwen/qwen3.5-397b-a17b","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":432.86,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-nano","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":24.05,"output_rub_per_million":150.3,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-2603","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.2-pro","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":2525.01,"output_rub_per_million":20200.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.4-pro","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":3607.16,"output_rub_per_million":21642.91,"currency":"RUB","is_free":false}},{"id":"google/gemma-2-27b-it","object":"model","created":1792918533,"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](/models?q=gemini).\nGemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning.\nSee the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).","context_window":8192,"context_length":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":78.16,"output_rub_per_million":78.16,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.2","object":"model","created":1792918533,"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,"context_length":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":33.67,"output_rub_per_million":50.51,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.5","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":601.2,"output_rub_per_million":3607.16,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy4-preview","object":"model","created":1792918533,"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,"context_length":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","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":100.28,"output_rub_per_million":300.72,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":300.6,"output_rub_per_million":1803.58,"currency":"RUB","is_free":false}},{"id":"tencent/hy-mt2-1.8b","object":"model","created":1792918533,"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,"context_length":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":5.3,"output_rub_per_million":21.29,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-flash-image-preview","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":360.72,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"z-ai/glm-5","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":384.77,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder-next","object":"model","created":1792918533,"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,"context_length":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":14.43,"output_rub_per_million":96.2,"currency":"RUB","is_free":false}},{"id":"stepfun/step-3.5-flash","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":36.08,"currency":"RUB","is_free":false}},{"id":"ibm-granite/granite-4.0-h-micro","object":"model","created":1792918533,"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,"context_length":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":2.05,"output_rub_per_million":13.47,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6.1-sol-pro","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6.1 Sol Pro","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](/models/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6.1 Sol](/models/openai/gpt-6.1-sol) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"moonshotai/kimi-k2.5","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.7-flash","object":"model","created":1792918533,"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":200000,"context_length":200000,"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":7.28,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2-thinking","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"openai/gpt-6-sol-pro","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-6 Sol Pro","description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](/models/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\nCost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use [GPT-6 Sol](/models/openai/gpt-6-sol) instead.\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","context_window":1050000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.2","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":210.42,"output_rub_per_million":1683.34,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"minimax/minimax-m2","object":"model","created":1792918533,"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](https://artificialanalysis.ai/models/minimax-m2), 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,"context_length":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":30.67,"output_rub_per_million":122.65,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-plus-02-15","object":"model","created":1792918533,"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,"context_length":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":31.27,"output_rub_per_million":187.58,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-14b-2512","object":"model","created":1792918533,"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,"context_length":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":24.05,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-pro","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1803.58,"output_rub_per_million":14428.61,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5-image-mini","object":"model","created":1792918533,"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](/models/openai/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,"context_length":400000,"modalities":["image","text"],"input_modalities":["file","image","text"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":300.6,"output_rub_per_million":240.48,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"arcee-ai/trinity-large-thinking","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":96.2,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5-image","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-5 Image","description":"[GPT-5](/models/openai/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,"context_length":400000,"modalities":["image","text"],"input_modalities":["image","text","file"],"output_modalities":["image","text"],"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"pricing":{"unit":"token","input_rub_per_million":1202.39,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy3","object":"model","created":1792918533,"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,"context_length":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":15.88,"output_rub_per_million":63.49,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-2.0-lite","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","object":"model","created":1792918533,"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,"context_length":262144,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":34.87,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5v","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":216.43,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.3-codex","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":210.42,"output_rub_per_million":1683.34,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-2.0","object":"model","created":1792918533,"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,"context_length":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":96.2,"output_rub_per_million":192.39,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v3.2-exp","object":"model","created":1792918533,"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,"context_length":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":32.47,"output_rub_per_million":49.3,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-next-80b-a3b-instruct","object":"model","created":1792918533,"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,"context_length":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":10.83,"output_rub_per_million":132.27,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3.1","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"thedrummer/cydonia-24b-v4.1","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-next-80b-a3b-thinking","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.7","object":"model","created":1792918533,"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,"context_length":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":64.93,"output_rub_per_million":238.08,"currency":"RUB","is_free":false}},{"id":"~google/gemini-pro-latest","object":"model","created":1792918533,"owned_by":"google","display_name":"Google: Gemini Pro Latest","description":"This model always redirects to the latest model in the Gemini Pro family.","context_window":1048576,"context_length":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":240.48,"output_rub_per_million":1202.39,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3.5-plus-20260420","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":216.43,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large-2512","object":"model","created":1792918533,"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,"context_length":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":60.12,"output_rub_per_million":180.36,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","object":"model","created":1792918533,"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,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","max_tokens","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":8.42,"output_rub_per_million":33.67,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-pro-search","object":"model","created":1792918533,"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,"context_length":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":360.72,"output_rub_per_million":1803.58,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":2164.3,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen3-coder","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"openai/o3","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":961.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"meta-llama/llama-3.1-70b-instruct","object":"model","created":1792918533,"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](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","context_window":131072,"context_length":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":48.1,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-26b-a4b-it:free","object":"model","created":1792918533,"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,"context_length":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":"x-ai/grok-4.20-multi-agent","object":"model","created":1792918533,"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,"context_length":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":150.3,"output_rub_per_million":300.6,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"meta-llama/llama-guard-4-12b","object":"model","created":1792918533,"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,"context_length":163840,"modalities":["text"],"input_modalities":["image","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":21.65,"output_rub_per_million":21.65,"currency":"RUB","is_free":false}},{"id":"rekaai/reka-edge","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":12.03,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-5-turbo","object":"model","created":1792918533,"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,"context_length":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":144.29,"output_rub_per_million":480.96,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.5","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":264.53,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-4-maverick","object":"model","created":1792918533,"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":524288,"context_length":524288,"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","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":22.55,"output_rub_per_million":78.46,"currency":"RUB","is_free":false}},{"id":"google/gemini-2.5-pro","object":"model","created":1792918533,"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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"aion-labs/aion-rp-llama-3.1-8b","object":"model","created":1792918533,"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,"context_length":32768,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":96.2,"output_rub_per_million":192.39,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-medium-3","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4.1-nano","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-chat-v3-0324","object":"model","created":1792918533,"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](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.","context_window":163840,"context_length":163840,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logprobs","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":34.87,"output_rub_per_million":137.08,"currency":"RUB","is_free":false}},{"id":"openai/o1-pro","object":"model","created":1792918533,"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,"context_length":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":18035.76,"output_rub_per_million":72143.01,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-1.6-flash","object":"model","created":1792918533,"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,"context_length":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":9.02,"output_rub_per_million":36.08,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-nano-30b-a3b","object":"model","created":1792918533,"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,"context_length":262144,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","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":7.22,"output_rub_per_million":28.86,"currency":"RUB","is_free":false}},{"id":"rekaai/reka-flash-3","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.1-codex-max","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-reasoning-pro","object":"model","created":1792918533,"owned_by":"perplexity","display_name":"Perplexity: Sonar Reasoning Pro","description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\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,"context_length":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":240.48,"output_rub_per_million":961.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"openai/o3-mini","object":"model","created":1792918533,"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,"context_length":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":132.27,"output_rub_per_million":529.05,"currency":"RUB","is_free":false}},{"id":"amazon/nova-lite-v1","object":"model","created":1792918533,"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,"context_length":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":7.22,"output_rub_per_million":28.86,"currency":"RUB","is_free":false}},{"id":"nousresearch/hermes-4-405b","object":"model","created":1792918533,"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,"context_length":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","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":120.24,"output_rub_per_million":360.72,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-2.5-coder-32b-instruct","object":"model","created":1792918533,"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](https://qwenlm.github.io/blog/qwen2.5-coder-family/).","context_window":32768,"context_length":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","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":79.36,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"anthracite-org/magnum-v4-72b","object":"model","created":1792918533,"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](/models/qwen/qwen-2.5-72b-instruct).","context_window":32768,"context_length":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":300.6,"output_rub_per_million":601.2,"currency":"RUB","is_free":false}},{"id":"sao10k/l3.1-euryale-70b","object":"model","created":1792918533,"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](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_window":131072,"context_length":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":102.21,"output_rub_per_million":102.21,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2","object":"model","created":1792918533,"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,"context_length":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":68.54,"output_rub_per_million":276.55,"currency":"RUB","is_free":false}},{"id":"tencent/hunyuan-a13b-instruct","object":"model","created":1792918533,"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,"context_length":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":16.84,"output_rub_per_million":68.54,"currency":"RUB","is_free":false}},{"id":"morph/morph-v3-large","object":"model","created":1792918533,"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](https://docs.morphllm.com/quickstart)","context_window":262144,"context_length":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":108.22,"output_rub_per_million":228.46,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-2024-08-06","object":"model","created":1792918533,"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](https://openai.com/index/introducing-structured-outputs-in-the-api/).\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](/models/openai/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\"](https://twitter.com/LiamFedus/status/1790064963966370209)","context_window":128000,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"morph/morph-v3-fast","object":"model","created":1792918533,"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](https://docs.morphllm.com/quickstart)","context_window":262144,"context_length":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":96.2,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-nemo","object":"model","created":1792918533,"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,"context_length":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":3.49,"output_rub_per_million":3.61,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-mini","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT-4o-mini","description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), 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](/models/openai/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](https://arena.lmsys.org/).\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n#multimodal","context_window":128000,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-mini-2024-07-18","object":"model","created":1792918533,"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](/models/openai/gpt-4o), 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](/models/openai/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](https://arena.lmsys.org/).\nCheck out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more.\n#multimodal","context_window":128000,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo-16k","object":"model","created":1792918533,"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,"context_length":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":360.72,"output_rub_per_million":480.96,"currency":"RUB","is_free":false}},{"id":"mancer/weaver","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":90.18,"currency":"RUB","is_free":false}},{"id":"openai/o4-mini-high","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: o4 Mini High","description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/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,"context_length":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":132.27,"output_rub_per_million":529.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen2.5-vl-72b-instruct","object":"model","created":1792918533,"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,"context_length":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":96.2,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-4b-it","object":"model","created":1792918533,"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,"context_length":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","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":4.81,"output_rub_per_million":6.02,"currency":"RUB","is_free":false}},{"id":"cohere/command-r7b-12-2024","object":"model","created":1792918533,"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](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","context_window":128000,"context_length":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":4.51,"output_rub_per_million":18.04,"currency":"RUB","is_free":false}},{"id":"amazon/nova-micro-v1","object":"model","created":1792918533,"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,"context_length":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":4.21,"output_rub_per_million":16.84,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-pro","object":"model","created":1792918533,"owned_by":"perplexity","display_name":"Perplexity: Sonar Pro","description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro)\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,"context_length":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":360.72,"output_rub_per_million":1803.58,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"openai/o3-mini-high","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: o3 Mini High","description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/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,"context_length":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":132.27,"output_rub_per_million":529.05,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-24b-instruct-2501","object":"model","created":1792918533,"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.](https://mistral.ai/news/mistral-small-3/)","context_window":32768,"context_length":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":6.02,"output_rub_per_million":9.62,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":120.24,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"minimax/minimax-01","object":"model","created":1792918533,"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,"context_length":1000192,"modalities":["text"],"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":24.05,"output_rub_per_million":132.27,"currency":"RUB","is_free":false}},{"id":"microsoft/phi-4","object":"model","created":1792918533,"owned_by":"microsoft","display_name":"Microsoft: Phi 4","description":"[Microsoft Research](/microsoft) 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](https://arxiv.org/pdf/2412.08905)","context_window":16384,"context_length":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":8.42,"output_rub_per_million":16.84,"currency":"RUB","is_free":false}},{"id":"amazon/nova-pro-v1","object":"model","created":1792918533,"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,"context_length":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":96.2,"output_rub_per_million":384.77,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-large","object":"model","created":1792918533,"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](https://mistral.ai/news/mistral-large-2407/).\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,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.2-1b-instruct","object":"model","created":1792918533,"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](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","context_window":60000,"context_length":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":3.25,"output_rub_per_million":24.17,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.2-3b-instruct","object":"model","created":1792918533,"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](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","context_window":131072,"context_length":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":6.02,"output_rub_per_million":39.68,"currency":"RUB","is_free":false}},{"id":"poolside/laguna-s-2.1:free","object":"model","created":1792918533,"owned_by":"poolside","display_name":"Poolside: Laguna S 2.1 (free)","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](https://poolside.ai/). 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](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/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]](/cdn-cgi/l/email-protection#6516000610170c111c25150a0a09160c01004b040c).\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,"context_length":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":"upstage/solar-mini4","object":"model","created":1792918533,"owned_by":"upstage","display_name":"Upstage: Solar Mini 4","description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads.\nWhen using BYOK with ZDR enforcement, the Console API key must belong to a ZDR-enabled Upstage organization. Contact Upstage to enable ZDR on your org.","context_window":524288,"context_length":524288,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":6.02,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"poolside/laguna-s-2.1","object":"model","created":1792918533,"owned_by":"poolside","display_name":"Poolside: Laguna S 2.1","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](https://poolside.ai/). 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](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/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]](/cdn-cgi/l/email-protection#5320363026213a272a13233c3c3f203a37367d323a).\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,"context_length":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":10.83,"output_rub_per_million":21.65,"currency":"RUB","is_free":false}},{"id":"~z-ai/glm-flash-latest","object":"model","created":1792918533,"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":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"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":6.17,"output_rub_per_million":8.43,"currency":"RUB","is_free":false}},{"id":"ibm-granite/granite-4.2-8b","object":"model","created":1792918533,"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,"context_length":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":7.22,"output_rub_per_million":30.06,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-flash","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":56.52,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1792918533,"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](/models/deepseek/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,"context_length":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":25.93,"output_rub_per_million":77.78,"currency":"RUB","is_free":false}},{"id":"~z-ai/glm-latest","object":"model","created":1792918533,"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":1048576,"context_length":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":8.46,"output_rub_per_million":527.17,"currency":"RUB","is_free":false}},{"id":"tencent/hy-mt2-7b","object":"model","created":1792918533,"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,"context_length":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":8.9,"output_rub_per_million":35.48,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.8-2.4t-a95b","object":"model","created":1792918533,"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](/qwen/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,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-lightning:free","object":"model","created":1792918533,"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,"context_length":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":"qwen/qwen3.7-flash","object":"model","created":1792918533,"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,"context_length":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":3.61,"output_rub_per_million":15.64,"currency":"RUB","is_free":false}},{"id":"~moonshotai/kimi-latest","object":"model","created":1792918533,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi Latest","description":"This model always redirects to the latest model in the Kimi family.","context_window":1048576,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","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":21.59,"output_rub_per_million":1074.94,"currency":"RUB","is_free":false}},{"id":"~google/gemini-flash-latest","object":"model","created":1792918533,"owned_by":"google","display_name":"Google: Gemini Flash Latest","description":"This model always redirects to the latest model in the Gemini Flash family.","context_window":1048576,"context_length":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":90.18,"output_rub_per_million":450.9,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"~anthropic/claude-sonnet-latest","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: Claude Sonnet Latest","description":"This model always redirects to the latest model in the Claude Sonnet family.","context_window":1000000,"context_length":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":240.48,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"meta/muse-spark-1.1","object":"model","created":1792918533,"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, 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,"context_length":1048576,"modalities":["text"],"input_modalities":["text","image","video","file"],"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":150.3,"output_rub_per_million":511.02,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":300.6,"unit":"1k calls"}],"is_free":false}},{"id":"poolside/laguna-xs-2.1","object":"model","created":1792918533,"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](https://poolside.ai/) 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](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/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]](/cdn-cgi/l/email-protection#3d4e585e484f5449447d4d5252514e545958135c54).\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,"context_length":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":7.22,"output_rub_per_million":14.43,"currency":"RUB","is_free":false}},{"id":"poolside/laguna-xs-2.1:free","object":"model","created":1792918533,"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](https://poolside.ai/) 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](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/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]](/cdn-cgi/l/email-protection#a3d0c6c0d6d1cad7dae3d3cccccfd0cac7c68dc2ca).\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,"context_length":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":"sakana/fugu-ultra","object":"model","created":1792918533,"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,"context_length":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":601.2,"output_rub_per_million":3607.16,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"google/gemini-3-pro-image","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"~anthropic/claude-fable-latest","object":"model","created":1792918533,"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,"context_length":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":1202.39,"output_rub_per_million":6011.92,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3.5-content-safety:free","object":"model","created":1792918533,"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,"context_length":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":"qwen/qwen3-vl-8b-instruct","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":90.18,"currency":"RUB","is_free":false}},{"id":"perceptron/perceptron-mk1","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":180.36,"currency":"RUB","is_free":false}},{"id":"x-ai/grok-4.3","object":"model","created":1792918533,"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,"context_length":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":150.3,"output_rub_per_million":300.6,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"~anthropic/claude-haiku-latest","object":"model","created":1792918533,"owned_by":"anthropic","display_name":"Anthropic: Claude Haiku Latest","description":"This model always redirects to the latest model in the Claude Haiku family.","context_window":1000000,"context_length":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":12.03,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"~openai/gpt-mini-latest","object":"model","created":1792918533,"owned_by":"openai","display_name":"OpenAI: GPT Mini Latest","description":"This model always redirects to the latest model in the GPT Mini family.","context_window":400000,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":90.18,"output_rub_per_million":541.08,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.6-flash","object":"model","created":1792918533,"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,"context_length":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":22.55,"output_rub_per_million":135.27,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.5-pro","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":3607.16,"output_rub_per_million":21642.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"tencent/hy3-preview","object":"model","created":1792918533,"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,"context_length":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":21.65,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"~anthropic/claude-opus-latest","object":"model","created":1792918533,"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,"context_length":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":480.96,"output_rub_per_million":2404.77,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-31b-it","object":"model","created":1792918533,"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,"context_length":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":24.05,"output_rub_per_million":48.1,"currency":"RUB","is_free":false}},{"id":"google/gemma-4-31b-it:free","object":"model","created":1792918533,"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,"context_length":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":"x-ai/grok-4.20","object":"model","created":1792918533,"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,"context_length":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":150.3,"output_rub_per_million":300.6,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"minimax/minimax-m2.7","object":"model","created":1792918533,"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,"context_length":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","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5.4-mini","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":90.18,"output_rub_per_million":541.08,"currency":"RUB","is_free":false}},{"id":"nvidia/nemotron-3-super-120b-a12b","object":"model","created":1792918533,"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,"context_length":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","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":36.08,"output_rub_per_million":288.58,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-9b","object":"model","created":1792918533,"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,"context_length":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":20.45,"output_rub_per_million":30.06,"currency":"RUB","is_free":false}},{"id":"inception/mercury-2","object":"model","created":1792918533,"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](https://www.inceptionlabs.ai/blog/introducing-mercury-2).","context_window":128000,"context_length":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":30.06,"output_rub_per_million":90.18,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-27b","object":"model","created":1792918533,"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,"context_length":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":32.47,"output_rub_per_million":259.72,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3.5-122b-a10b","object":"model","created":1792918533,"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,"context_length":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":48.1,"output_rub_per_million":384.77,"currency":"RUB","is_free":false}},{"id":"google/gemini-3.1-pro-preview-customtools","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":1442.87,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m2.5","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"hubris/free","object":"model","created":1792918533,"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,"context_length":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":"upstage/solar-pro-3","object":"model","created":1792918533,"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,"context_length":131072,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"pricing":{"unit":"token","input_rub_per_million":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"minimax/minimax-m2-her","object":"model","created":1792918533,"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,"context_length":65536,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","temperature","top_p"],"pricing":{"unit":"token","input_rub_per_million":36.08,"output_rub_per_million":144.29,"currency":"RUB","is_free":false}},{"id":"openai/gpt-audio-mini","object":"model","created":1792918533,"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,"context_length":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":72.15,"output_rub_per_million":288.58,"currency":"RUB","is_free":false}},{"id":"bytedance-seed/seed-1.6","object":"model","created":1792918533,"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,"context_length":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":30.06,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"relace/relace-search","object":"model","created":1792918533,"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](https://docs.relace.ai/docs/fast-agentic-search/agent).","context_window":256000,"context_length":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":120.24,"output_rub_per_million":360.72,"currency":"RUB","is_free":false}},{"id":"amazon/nova-2-lite-v1","object":"model","created":1792918533,"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,"context_length":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":36.08,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-8b-2512","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":18.04,"currency":"RUB","is_free":false}},{"id":"mistralai/ministral-3b-2512","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":12.03,"currency":"RUB","is_free":false}},{"id":"google/gemini-3-pro-image-preview","object":"model","created":1792918533,"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,"context_length":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":240.48,"output_rub_per_million":1442.87,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1683.34,"unit":"1k calls"}],"is_free":false}},{"id":"openai/gpt-5.1-codex-mini","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":30.06,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"mistralai/voxtral-small-24b-2507","object":"model","created":1792918533,"owned_by":"mistralai","display_name":"Mistral: Voxtral Small 24B 2507","description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.","context_window":32768,"context_length":32768,"modalities":["text"],"input_modalities":["text","audio","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":12.03,"output_rub_per_million":36.08,"currency":"RUB","per_unit":[{"sku":"Input Audio","price_rub":0.73,"unit":"minute"}],"is_free":false}},{"id":"anthropic/claude-haiku-4.5","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":601.2,"currency":"RUB","is_free":false}},{"id":"z-ai/glm-4.6","object":"model","created":1792918533,"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,"context_length":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":66.14,"output_rub_per_million":264.53,"currency":"RUB","is_free":false}},{"id":"relace/relace-apply-3","object":"model","created":1792918533,"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](https://docs.relace.ai/api-reference/instant-apply/apply)","context_window":256000,"context_length":256000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["max_tokens","seed","stop"],"pricing":{"unit":"token","input_rub_per_million":102.21,"output_rub_per_million":150.3,"currency":"RUB","is_free":false}},{"id":"moonshotai/kimi-k2-0905","object":"model","created":1792918533,"owned_by":"moonshotai","display_name":"MoonshotAI: Kimi K2 0905","description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). 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,"context_length":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":72.15,"output_rub_per_million":300.6,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-chat-v3.1","object":"model","created":1792918533,"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](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.","context_window":163840,"context_length":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":30.06,"output_rub_per_million":114.23,"currency":"RUB","is_free":false}},{"id":"openai/gpt-5","object":"model","created":1792918533,"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,"context_length":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","verbosity"],"pricing":{"unit":"token","input_rub_per_million":150.3,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-120b","object":"model","created":1792918533,"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,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"openai/gpt-oss-20b","object":"model","created":1792918533,"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,"context_length":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":2.17,"output_rub_per_million":10.83,"currency":"RUB","is_free":false}},{"id":"mistralai/codestral-2508","object":"model","created":1792918533,"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.\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_window":256000,"context_length":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":36.08,"output_rub_per_million":108.22,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","object":"model","created":1792918533,"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":128000,"context_length":128000,"modalities":["text"],"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"pricing":{"unit":"token","input_rub_per_million":54.11,"output_rub_per_million":420.84,"currency":"RUB","is_free":false}},{"id":"bytedance/ui-tars-1.5-7b","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","object":"model","created":1792918533,"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,"context_length":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":24.05,"output_rub_per_million":108.22,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-3.2-24b-instruct","object":"model","created":1792918533,"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":256000,"context_length":256000,"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":9.02,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"openai/o3-pro","object":"model","created":1792918533,"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,"context_length":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":2404.77,"output_rub_per_million":9619.07,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"deepseek/deepseek-r1-0528","object":"model","created":1792918533,"owned_by":"deepseek","display_name":"DeepSeek: R1 0528","description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/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,"context_length":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":60.12,"output_rub_per_million":258.52,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-30b-a3b","object":"model","created":1792918533,"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":40960,"context_length":40960,"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":14.43,"output_rub_per_million":60.12,"currency":"RUB","is_free":false}},{"id":"qwen/qwen3-14b","object":"model","created":1792918533,"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":40960,"context_length":40960,"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":14.43,"output_rub_per_million":28.86,"currency":"RUB","is_free":false}},{"id":"openai/o4-mini","object":"model","created":1792918533,"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,"context_length":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":132.27,"output_rub_per_million":529.05,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":1202.39,"unit":"1k calls"}],"is_free":false}},{"id":"meta-llama/llama-4-scout","object":"model","created":1792918533,"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,"context_length":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":12.03,"output_rub_per_million":36.08,"currency":"RUB","is_free":false}},{"id":"mistralai/mistral-small-3.1-24b-instruct","object":"model","created":1792918533,"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](mistralai/mistral-small-3.2-24b-instruct)","context_window":128000,"context_length":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","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"unit":"token","input_rub_per_million":42.21,"output_rub_per_million":66.74,"currency":"RUB","is_free":false}},{"id":"google/gemma-3-27b-it","object":"model","created":1792918533,"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](google/gemma-2-27b-it)","context_window":131072,"context_length":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":9.62,"output_rub_per_million":42.09,"currency":"RUB","is_free":false}},{"id":"perplexity/sonar-deep-research","object":"model","created":1792918533,"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](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-deep-research))\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,"context_length":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":240.48,"output_rub_per_million":961.91,"currency":"RUB","per_unit":[{"sku":"Web Search","price_rub":601.2,"unit":"1k calls"}],"is_free":false}},{"id":"qwen/qwen-plus","object":"model","created":1792918533,"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,"context_length":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":31.27,"output_rub_per_million":93.79,"currency":"RUB","is_free":false}},{"id":"deepseek/deepseek-chat","object":"model","created":1792918533,"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](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).","context_window":163840,"context_length":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":30.95,"output_rub_per_million":123.69,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.3-70b-instruct","object":"model","created":1792918533,"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.\n[Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)","context_window":131072,"context_length":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":12.03,"output_rub_per_million":38.48,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o-2024-11-20","object":"model","created":1792918533,"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](/models/openai/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,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"qwen/qwen-2.5-7b-instruct","object":"model","created":1792918533,"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](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).","context_window":32768,"context_length":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":12.03,"output_rub_per_million":24.05,"currency":"RUB","is_free":false}},{"id":"cohere/command-r-08-2024","object":"model","created":1792918533,"owned_by":"cohere","display_name":"Cohere: Command R (08-2024)","description":"command-r-08-2024 is an update of the [Command R](/models/cohere/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](https://docs.cohere.com/changelog/command-gets-refreshed).\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","context_window":128000,"context_length":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":18.04,"output_rub_per_million":72.15,"currency":"RUB","is_free":false}},{"id":"cohere/command-r-plus-08-2024","object":"model","created":1792918533,"owned_by":"cohere","display_name":"Cohere: Command R+ (08-2024)","description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) 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](https://docs.cohere.com/changelog/command-gets-refreshed).\nUse of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).","context_window":128000,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"nousresearch/hermes-3-llama-3.1-405b","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":120.24,"currency":"RUB","is_free":false}},{"id":"sao10k/l3-lunaris-8b","object":"model","created":1792918533,"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](https://huggingface.co/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,"context_length":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":4.81,"output_rub_per_million":6.02,"currency":"RUB","is_free":false}},{"id":"meta-llama/llama-3.1-8b-instruct","object":"model","created":1792918533,"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](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).","context_window":131072,"context_length":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":6.02,"output_rub_per_million":9.62,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4o","object":"model","created":1792918533,"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](/models/openai/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\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n#multimodal","context_window":128000,"context_length":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":300.6,"output_rub_per_million":1202.39,"currency":"RUB","is_free":false}},{"id":"mistralai/mixtral-8x22b-instruct","object":"model","created":1792918533,"owned_by":"mistralai","display_name":"Mistral: Mixtral 8x22B Instruct","description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/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](https://mistral.ai/news/mixtral-8x22b/).\n#moe","context_window":65536,"context_length":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":240.48,"output_rub_per_million":721.44,"currency":"RUB","is_free":false}},{"id":"openai/gpt-3.5-turbo-0613","object":"model","created":1792918533,"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,"context_length":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":120.24,"output_rub_per_million":240.48,"currency":"RUB","is_free":false}},{"id":"undi95/remm-slerp-l2-13b","object":"model","created":1792918533,"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,"context_length":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":42.09,"output_rub_per_million":78.16,"currency":"RUB","is_free":false}},{"id":"openai/gpt-4","object":"model","created":1792918533,"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,"context_length":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":3607.16,"output_rub_per_million":7214.31,"currency":"RUB","is_free":false}}]}