{"data":[{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Opus 4.8 是 Opus 4.7 的重点升级，是 Anthropic 用于编码、代理任务和企业工作流程的最佳通用模型。它建立在以前 Opus 模型的优势之上，在复杂的多步骤编码任务上具有更强的性能。 Anthropic 建议将其用于长期编码和代理任务。它在专业工作方面也更强，包括文件起草、数据分析和演示。","context_length":1000000,"created":1780358400,"description":"Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic's best generally available model for coding, agentic tasks, and enterprise workflows. It builds on the strengths of previous Opus models with stronger performance on complex, multi-step coding tasks. Anthropic recommends using it on long-horizon coding and agentic tasks. It is also stronger on professional work, including document drafting, data analysis, and presentations.","developer":"knox","id":"anthropic/claude-opus-4.8","is_provider_model":true,"last_updated":1780432631,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Opus 4.8","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"25.00","image":"","input_cache_read":"0.50","input_cache_write":"6.25","prompt":"5.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-02","root":"anthropic/claude-opus-4.8","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Claude Sonnet 4.6 是迄今为止功能最强大的 Sonnet 系列模型，在编码、代理和专业工作方面均展现出卓越的性能。它尤其擅长迭代开发、复杂代码库导航、端到端项目管理（含内存管理）、文档创建以及在 Web 质量保证和工作流自动化方面的出色计算机应用。","context_length":1000000,"created":1780358400,"description":"Claude Sonnet 4.6 is the 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.","developer":"knox","id":"anthropic/claude-sonnet-4.6","is_provider_model":true,"last_updated":1780432631,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Sonnet 4.6","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"15.00","image":"","input_cache_read":"0.30","input_cache_write":"3.75","prompt":"3.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-02","root":"anthropic/claude-sonnet-4.6","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"instruct_type":"","modality":"text","output_modalities":["text"],"tokenizer":""},"chinese_description":"Claude Haiku 4.5 在编码、计算机使用和代理任务方面与 Sonnet 4 的性能相当，但成本更低，速度更快。它以接近前沿的性能和 Claude 的独特特性，提供适合大规模子代理部署、免费产品以及预算有限的智能敏感型应用的价格。","context_length":200000,"created":1780358400,"description":"Claude Haiku 4.5 matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. It delivers near-frontier performance and Claude’s unique character at a price point that works for scaled sub-agent deployments, free tier products, and intelligence-sensitive applications with budget constraints.","developer":"knox","id":"anthropic/claude-haiku-4.5","is_provider_model":true,"last_updated":1780432631,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"Claude Haiku 4.5","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"5.00","image":"","input_cache_read":"0.10","input_cache_write":"1.25","prompt":"1.00","web_search":"10.00"},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-06-02","root":"anthropic/claude-haiku-4.5","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1780185600,"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,...","developer":"minimax","id":"minimax/minimax-m3","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"MiniMax: MiniMax M3","object":"model","owned_by":"minimax","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000012","image":null,"input_cache_read":"0.00000006","input_cache_write":null,"prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-31","root":"minimax/minimax-m3","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":256000,"created":1779926400,"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...","developer":"stepfun","id":"stepfun/step-3.7-flash","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"StepFun: Step 3.7 Flash","object":"model","owned_by":"stepfun","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000115","image":null,"input_cache_read":"0.00000004","input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-28","root":"stepfun/step-3.7-flash","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tools","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":256000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"chinese_description":null,"context_length":1000000,"created":1779840000,"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","developer":"anthropic","id":"anthropic/claude-opus-4.8-fast","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","object":"model","owned_by":"anthropic","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00005","image":null,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-27","root":"anthropic/claude-opus-4.8-fast","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"chinese_description":null,"context_length":1000000,"created":1779321600,"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,...","developer":"qwen","id":"qwen/qwen3.7-max","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Qwen: Qwen3.7 Max","object":"model","owned_by":"qwen","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000075","image":null,"input_cache_read":null,"input_cache_write":"0.000003125","prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-21","root":"qwen/qwen3.7-max","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1779148800,"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...","developer":"google","id":"google/gemini-3.5-flash","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemini 3.5 Flash","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000009","image":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.00000008333333333333334","prompt":"0.0000015","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-19","root":"google/gemini-3.5-flash","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1778112000,"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...","developer":"google","id":"google/gemini-3.1-flash-lite","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemini 3.1 Flash Lite","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.00000008333333333333334","prompt":"0.00000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-05-07","root":"google/gemini-3.1-flash-lite","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":1000000,"created":1777507200,"description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","developer":"x-ai","id":"x-ai/grok-4.3","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"xAI: Grok 4.3","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.00000125","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-30","root":"x-ai/grok-4.3","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"chinese_description":null,"context_length":262144,"created":1777248000,"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...","developer":"qwen","id":"qwen/qwen3.6-max-preview","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Qwen: Qwen3.6 Max Preview","object":"model","owned_by":"qwen","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000078","image":null,"input_cache_read":null,"input_cache_write":"0.000001625","prompt":"0.0000013","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-27","root":"qwen/qwen3.6-max-preview","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":"","modality":"image","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":"GPT Image 2 是 OpenAI 最先进的图像生成模型，能够快速、高质量地完成图像生成与编辑。该模型支持灵活的图像尺寸和高保真图像输入。","context_length":272000,"created":1777075200,"description":"GPT Image 2 is OpenAI's state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs.","developer":"knox","id":"openai/gpt-image-2","is_provider_model":true,"last_updated":1780432631,"logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","name":"GPT Image 2","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"30.00","image":"0.30","input_cache_read":"1.25","input_cache_write":"","prompt":"5.00","web_search":""},"pricing_in_display_units":true,"provider_info":{"provider_logo_url":"https://images.knox.chat/avatars/1/avatar_8c4a62840519.png","provider_name":"knox"},"release_date":"2026-04-25","root":"openai/gpt-image-2","source":"provider","supported_parameters":["tools","temperature","top_p","top_k","max_tokens","presence_penalty","frequency_penalty","stop","response_format","seed","stream"],"top_provider":{"context_length":272000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1776988800,"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...","developer":"openai","id":"openai/gpt-5.5","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.5","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00003","image":null,"input_cache_read":"0.0000005","input_cache_write":null,"prompt":"0.000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"openai/gpt-5.5","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":1048576,"created":1776988800,"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,...","developer":"deepseek","id":"deepseek/deepseek-v4-pro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"DeepSeek: DeepSeek V4 Pro","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000087","image":null,"input_cache_read":"0.00000003625","input_cache_write":null,"prompt":"0.000000435","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"deepseek/deepseek-v4-pro","source":"openrouter","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"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":384000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":1048576,"created":1776988800,"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...","developer":"deepseek","id":"deepseek/deepseek-v4-flash","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"DeepSeek: DeepSeek V4 Flash","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000028","image":null,"input_cache_read":"0.000000028","input_cache_write":null,"prompt":"0.00000014","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-24","root":"deepseek/deepseek-v4-flash","source":"openrouter","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"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":384000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1776816000,"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....","developer":"xiaomi","id":"xiaomi/mimo-v2.5-pro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Xiaomi: MiMo-V2.5-Pro","object":"model","owned_by":"xiaomi","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-22","root":"xiaomi/mimo-v2.5-pro","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["image","text","file"],"instruct_type":null,"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":272000,"created":1776729600,"description":"[GPT-5.4](https://openrouter.ai/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...","developer":"openai","id":"openai/gpt-5.4-image-2","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.4 Image 2","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.000002","input_cache_write":null,"prompt":"0.000008","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-21","root":"openai/gpt-5.4-image-2","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","top_logprobs"],"top_provider":{"context_length":272000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":256000,"created":1776643200,"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...","developer":"moonshotai","id":"moonshotai/kimi-k2.6","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"MoonshotAI: Kimi K2.6","object":"model","owned_by":"moonshotai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000004655","image":null,"input_cache_read":"0.0000001463","input_cache_write":null,"prompt":"0.0000007448","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-20","root":"moonshotai/kimi-k2.6","source":"openrouter","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"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":202752,"created":1775520000,"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...","developer":"z-ai","id":"z-ai/glm-5.1","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Z.ai: GLM 5.1","object":"model","owned_by":"z-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000035","image":null,"input_cache_read":"0.000000525","input_cache_write":null,"prompt":"0.00000105","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-07","root":"z-ai/glm-5.1","source":"openrouter","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"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text","image","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"chinese_description":null,"context_length":1000000,"created":1775088000,"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...","developer":"qwen","id":"qwen/qwen3.6-plus","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Qwen: Qwen3.6 Plus","object":"model","owned_by":"qwen","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000195","image":null,"input_cache_read":null,"input_cache_write":"0.00000040625","prompt":"0.000000325","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-02","root":"qwen/qwen3.6-plus","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"chinese_description":null,"context_length":262144,"created":1775088000,"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...","developer":"google","id":"google/gemma-4-31b-it","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemma 4 31B","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000038","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000013","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-04-02","root":"google/gemma-4-31b-it","source":"openrouter","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"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":2000000,"created":1774915200,"description":"Grok 4.20 Multi-Agent is a variant of xAI’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...","developer":"x-ai","id":"x-ai/grok-4.20-multi-agent","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"xAI: Grok 4.20 Multi-Agent","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-31","root":"x-ai/grok-4.20-multi-agent","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":2000000,"created":1774915200,"description":"Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently...","developer":"x-ai","id":"x-ai/grok-4.20","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"xAI: Grok 4.20","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-31","root":"x-ai/grok-4.20","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1048576,"created":1773792000,"description":"MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like...","developer":"xiaomi","id":"xiaomi/mimo-v2-pro","is_provider_model":false,"last_updated":1780004091,"logo_url":null,"name":"Xiaomi: MiMo-V2-Pro","object":"model","owned_by":"xiaomi","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":"0.0000002","input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-18","root":"xiaomi/mimo-v2-pro","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":400000,"created":1773705600,"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,...","developer":"openai","id":"openai/gpt-5.4-mini","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.4 Mini","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000045","image":null,"input_cache_read":"0.000000075","input_cache_write":null,"prompt":"0.00000075","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-17","root":"openai/gpt-5.4-mini","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":202752,"created":1773532800,"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...","developer":"z-ai","id":"z-ai/glm-5-turbo","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Z.ai: GLM 5 Turbo","object":"model","owned_by":"z-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000004","image":null,"input_cache_read":"0.00000024","input_cache_write":null,"prompt":"0.0000012","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-15","root":"z-ai/glm-5-turbo","source":"openrouter","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"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":262144,"created":1773187200,"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...","developer":"nvidia","id":"nvidia/nemotron-3-super-120b-a12b","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"NVIDIA: Nemotron 3 Super","object":"model","owned_by":"nvidia","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000045","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000009","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-11","root":"nvidia/nemotron-3-super-120b-a12b","source":"openrouter","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"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":1050000,"created":1772668800,"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...","developer":"openai","id":"openai/gpt-5.4","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.4","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":"0.00000025","input_cache_write":null,"prompt":"0.0000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-05","root":"openai/gpt-5.4","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":128000,"created":1772582400,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","developer":"inception","id":"inception/mercury-2","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Inception: Mercury 2","object":"model","owned_by":"inception","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000075","image":null,"input_cache_read":"0.000000025","input_cache_write":null,"prompt":"0.00000025","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-04","root":"inception/mercury-2","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":50000}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":128000,"created":1772496000,"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...","developer":"openai","id":"openai/gpt-5.3-chat","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.3 Chat","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000014","image":null,"input_cache_read":"0.000000175","input_cache_write":null,"prompt":"0.00000175","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-03-03","root":"openai/gpt-5.3-chat","source":"openrouter","supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":131072,"created":1772064000,"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...","developer":"google","id":"google/gemini-3.1-flash-image-preview","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.0000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-02-26","root":"google/gemini-3.1-flash-image-preview","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"chinese_description":null,"context_length":400000,"created":1771891200,"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...","developer":"openai","id":"openai/gpt-5.3-codex","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"OpenAI: GPT-5.3-Codex","object":"model","owned_by":"openai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000014","image":null,"input_cache_read":"0.000000175","input_cache_write":null,"prompt":"0.00000175","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-02-24","root":"openai/gpt-5.3-codex","source":"openrouter","supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["audio","file","image","text","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1771459200,"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...","developer":"google","id":"google/gemini-3.1-pro-preview","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemini 3.1 Pro Preview","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-02-19","root":"google/gemini-3.1-pro-preview","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":128000,"created":1769472000,"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...","developer":"upstage","id":"upstage/solar-pro-3","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Upstage: Solar Pro 3","object":"model","owned_by":"upstage","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000006","image":null,"input_cache_read":"0.000000015","input_cache_write":null,"prompt":"0.00000015","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-01-27","root":"upstage/solar-pro-3","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":1040000,"created":1768953600,"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...","developer":"writer","id":"writer/palmyra-x5","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Writer: Palmyra X5","object":"model","owned_by":"writer","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000006","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.0000006","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-01-21","root":"writer/palmyra-x5","source":"openrouter","supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":1040000,"is_moderated":true,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":65536,"created":1767657600,"description":"Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction following. As part of the Olmo 3.1 family, this...","developer":"allenai","id":"allenai/olmo-3.1-32b-instruct","is_provider_model":false,"last_updated":1777835764,"logo_url":null,"name":"AllenAI: Olmo 3.1 32B Instruct","object":"model","owned_by":"allenai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000006","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-01-06","root":"allenai/olmo-3.1-32b-instruct","source":"openrouter","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"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["file","image","text"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"chinese_description":null,"context_length":-1,"created":1767225600,"description":"Knox Memory System - AI model with unlimited context length through intelligent memory management. Orchestrates multiple underlying models via Plan-Task-Memory architecture.","developer":"knox","id":"knox/knox-ms","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Knox-MS","object":"model","owned_by":"knox","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"-1","image":"-1","input_cache_read":"0","input_cache_write":"0","prompt":"-1","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2026-01-01","root":"knox/knox-ms","source":"openrouter","supported_parameters":["enable_vector_search","include_reasoning","max_tokens","memory_mode","project_id","reasoning","rerank_threshold","response_format","session_id","stop","structured_outputs","temperature","tool_choice","tools","top_k","vector_top_k","verbosity"],"top_provider":{"context_length":-1,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":262144,"created":1765670400,"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. The model is fully...","developer":"nvidia","id":"nvidia/nemotron-3-nano-30b-a3b","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","object":"model","owned_by":"nvidia","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000002","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-14","root":"nvidia/nemotron-3-nano-30b-a3b","source":"openrouter","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"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":228000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":262144,"created":1765238400,"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. Devstral 2 supports exploring...","developer":"mistralai","id":"mistralai/devstral-2512","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Mistral: Devstral 2 2512","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000002","image":null,"input_cache_read":"0.00000004","input_cache_write":null,"prompt":"0.0000004","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-09","root":"mistralai/devstral-2512","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":256000,"created":1765152000,"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. In contrast to RAG, relace-search performs agentic...","developer":"relace","id":"relace/relace-search","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Relace: Relace Search","object":"model","owned_by":"relace","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-08","root":"relace/relace-search","source":"openrouter","supported_parameters":["max_tokens","seed","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":32768,"created":1765065600,"description":"Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance...","developer":"essentialai","id":"essentialai/rnj-1-instruct","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"EssentialAI: Rnj 1 Instruct","object":"model","owned_by":"essentialai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000015","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000015","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-07","root":"essentialai/rnj-1-instruct","source":"openrouter","supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"chinese_description":null,"context_length":131072,"created":1764547200,"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...","developer":"deepseek","id":"deepseek/deepseek-v3.2","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"DeepSeek: DeepSeek V3.2","object":"model","owned_by":"deepseek","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000000378","image":null,"input_cache_read":"0.0000000252","input_cache_write":null,"prompt":"0.000000252","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-01","root":"deepseek/deepseek-v3.2","source":"openrouter","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"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":262144,"created":1764547200,"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.","developer":"mistralai","id":"mistralai/mistral-large-2512","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Mistral: Mistral Large 3 2512","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":null,"input_cache_read":"0.00000005","input_cache_write":null,"prompt":"0.0000005","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-12-01","root":"mistralai/mistral-large-2512","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":65536,"created":1763596800,"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...","developer":"google","id":"google/gemini-3-pro-image-preview","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-11-20","root":"google/gemini-3-pro-image-preview","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","file"],"instruct_type":null,"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":2000000,"created":1763510400,"description":"Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using...","developer":"x-ai","id":"x-ai/grok-4.1-fast","is_provider_model":false,"last_updated":1777835764,"logo_url":null,"name":"xAI: Grok 4.1 Fast","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000005","image":null,"input_cache_read":"0.00000005","input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-11-19","root":"x-ai/grok-4.1-fast","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":30000}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":200000,"created":1761782400,"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. Pricing is based...","developer":"perplexity","id":"perplexity/sonar-pro-search","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Perplexity: Sonar Pro Search","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-30","root":"perplexity/sonar-pro-search","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},{"architecture":{"input_modalities":["image","text","video"],"instruct_type":null,"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":131072,"created":1761609600,"description":"NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...","developer":"nvidia","id":"nvidia/nemotron-nano-12b-v2-vl","is_provider_model":false,"last_updated":1777835764,"logo_url":null,"name":"NVIDIA: Nemotron Nano 12B 2 VL","object":"model","owned_by":"nvidia","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000006","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-28","root":"nvidia/nemotron-nano-12b-v2-vl","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":131000,"created":1760918400,"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...","developer":"ibm-granite","id":"ibm-granite/granite-4.0-h-micro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"IBM: Granite 4.0 Micro","object":"model","owned_by":"ibm-granite","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000011","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000017","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-20","root":"ibm-granite/granite-4.0-h-micro","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","temperature","top_k","top_p"],"top_provider":{"context_length":131000,"is_moderated":false,"max_completion_tokens":131000}},{"architecture":{"input_modalities":["image","text"],"instruct_type":null,"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":32768,"created":1759795200,"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,...","developer":"google","id":"google/gemini-2.5-flash-image","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-10-07","root":"google/gemini-2.5-flash-image","source":"openrouter","supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":256000,"created":1758844800,"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...","developer":"relace","id":"relace/relace-apply-3","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Relace: Relace Apply 3","object":"model","owned_by":"relace","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000125","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000085","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-09-26","root":"relace/relace-apply-3","source":"openrouter","supported_parameters":["max_tokens","seed","stop"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":131072,"created":1757030400,"description":"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...","developer":"nvidia","id":"nvidia/nemotron-nano-9b-v2","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"NVIDIA: Nemotron Nano 9B V2","object":"model","owned_by":"nvidia","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000016","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000004","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-09-05","root":"nvidia/nemotron-nano-9b-v2","source":"openrouter","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"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":131072,"created":1756166400,"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...","developer":"nousresearch","id":"nousresearch/hermes-4-405b","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Nous: Hermes 4 405B","object":"model","owned_by":"nousresearch","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000003","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-26","root":"nousresearch/hermes-4-405b","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"chinese_description":null,"context_length":131072,"created":1756166400,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...","developer":"nousresearch","id":"nousresearch/hermes-4-70b","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Nous: Hermes 4 70B","object":"model","owned_by":"nousresearch","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000004","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.00000013","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-26","root":"nousresearch/hermes-4-70b","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Grok"},"chinese_description":null,"context_length":256000,"created":1756166400,"description":"Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...","developer":"x-ai","id":"x-ai/grok-code-fast-1","is_provider_model":false,"last_updated":1777835764,"logo_url":null,"name":"xAI: Grok Code Fast 1","object":"model","owned_by":"x-ai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000015","image":null,"input_cache_read":"0.00000002","input_cache_write":null,"prompt":"0.0000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-26","root":"x-ai/grok-code-fast-1","source":"openrouter","supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":10000}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"chinese_description":null,"context_length":256000,"created":1754006400,"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\n[Blog Post](https://mistral.ai/news/codestral-25-08)","developer":"mistralai","id":"mistralai/codestral-2508","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Mistral: Codestral 2508","object":"model","owned_by":"mistralai","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000009","image":null,"input_cache_read":"0.00000003","input_cache_write":null,"prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-08-01","root":"mistralai/codestral-2508","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["file","image","text","audio","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1750118400,"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...","developer":"google","id":"google/gemini-2.5-flash","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemini 2.5 Flash","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.0000025","image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.00000008333333333333334","prompt":"0.0000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-06-17","root":"google/gemini-2.5-flash","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text","image","file","audio","video"],"instruct_type":null,"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"chinese_description":null,"context_length":1048576,"created":1750118400,"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...","developer":"google","id":"google/gemini-2.5-pro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Google: Gemini 2.5 Pro","object":"model","owned_by":"google","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00001","image":"0.00000125","input_cache_read":"0.000000125","input_cache_write":"0.000000375","prompt":"0.00000125","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-06-17","root":"google/gemini-2.5-pro","source":"openrouter","supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"instruct_type":"deepseek-r1","modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":128000,"created":1741305600,"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) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","developer":"perplexity","id":"perplexity/sonar-reasoning-pro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Perplexity: Sonar Reasoning Pro","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000008","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-03-07","root":"perplexity/sonar-reasoning-pro","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":200000,"created":1741305600,"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) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","developer":"perplexity","id":"perplexity/sonar-pro","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Perplexity: Sonar Pro","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000015","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000003","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-03-07","root":"perplexity/sonar-pro","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},{"architecture":{"input_modalities":["text"],"instruct_type":"deepseek-r1","modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":128000,"created":1741305600,"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...","developer":"perplexity","id":"perplexity/sonar-deep-research","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Perplexity: Sonar Deep Research","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000008","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000002","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-03-07","root":"perplexity/sonar-deep-research","source":"openrouter","supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":127072,"created":1737936000,"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...","developer":"perplexity","id":"perplexity/sonar","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Perplexity: Sonar","object":"model","owned_by":"perplexity","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.000001","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000001","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-01-27","root":"perplexity/sonar","source":"openrouter","supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":127072,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"chinese_description":null,"context_length":16384,"created":1736467200,"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. At 14 billion...","developer":"microsoft","id":"microsoft/phi-4","is_provider_model":false,"last_updated":1780421522,"logo_url":null,"name":"Microsoft: Phi 4","object":"model","owned_by":"microsoft","parent":null,"permission":[{"allow_create_engine":true,"allow_fine_tuning":false,"allow_logprobs":true,"allow_sampling":true,"allow_search_indices":false,"allow_view":true,"created":1626777600,"group":null,"id":"modelperm-LwHkVFn8AcMItP432fKKDIKJ","is_blocking":false,"object":"model_permission","organization":"*"}],"pricing":{"completion":"0.00000014","image":null,"input_cache_read":null,"input_cache_write":null,"prompt":"0.000000065","web_search":null},"pricing_in_display_units":false,"provider_info":null,"release_date":"2025-01-10","root":"microsoft/phi-4","source":"openrouter","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"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":16384}}],"object":"list"}