{"object":"list","data":[{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is DeepSeek's latest efficiency-optimized Mixture-of-Experts model with a 1M-token context window and up to 384K output tokens. It adds native multimodal vision understanding, supports thinking mode (on by default), tool calls, JSON output and prompt caching, and per DeepSeek surpasses V4 Pro on quality, cost and speed. Served upstream under the official model id deepseek-flash.","icon":"DeepSeek","owned_by":"deepseek","model_protocol":"openai","series":"deepseek","mode":"chat","context_window":1000000,"max_output_tokens":384000,"pricing":{"input":"0.0000003","output":"0.0000012","input_cache_read":"0.000000006"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["deepseek"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-09-10T00:00:00Z","is_deprecated":false,"aliases":["deepseek-v4.1-flash","deepseek-flash"],"provider_price":{"provider_type":"deepseek","pricing":{"input":"0.0000003","output":"0.0000012","input_cache_read":"0.000000006"},"is_override":false}},{"id":"openai/gpt-image-2.5-flare","canonical_slug":"gpt-image-2.5-flare","display_name":"OpenAI: GPT Image 2.5 Flare","description":"Fast, high-quality everyday image generation.","icon":"OpenAI","owned_by":"openai","model_protocol":"openai","series":"gpt","mode":"image_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-09-09T00:00:00Z","is_deprecated":false,"aliases":["gpt-image-2.5-flare"],"image_attributes":{"supported_params":["prompt","n","stream","user"]},"provider_price":{"provider_type":"openai","pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"is_override":false}},{"id":"openai/gpt-image-2.5-sunburst","canonical_slug":"gpt-image-2.5-sunburst","display_name":"OpenAI: GPT Image 2.5 Sunburst","description":"Our most capable model for image generation and editing.","icon":"OpenAI","owned_by":"openai","model_protocol":"openai","series":"gpt","mode":"image_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-09-09T00:00:00Z","is_deprecated":false,"aliases":["gpt-image-2.5-sunburst"],"image_attributes":{"supported_params":["prompt","n","stream","user"]},"provider_price":{"provider_type":"openai","pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"is_override":false}},{"id":"openai/gpt-6-astra","canonical_slug":"openai/gpt-6-astra-20260903","display_name":"OpenAI: GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon tasks.","icon":"OpenAI","owned_by":"openrouter","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.00001","output":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["openai","azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-09-04T00:00:00Z","is_deprecated":false,"aliases":["gpt-6-astra","gpt-6-astra-2026-09-03"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.00001","output":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01"},"is_override":false}},{"id":"google/gemini-3.8-flash","canonical_slug":"gemini-3.8-flash","display_name":"Google: Gemini 3.8 Flash","description":"Gemini 3.8 Flash is Google's most intelligent Flash model, with significant gains over 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. All input modalities (text/image/video/audio) unified pricing; batch tier at 50% discount. Thinking model with configurable levels. 1M context. Released September 2, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":65536,"pricing":{"input":"0.0000015","output":"0.0000075","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_audio":"0.00000015","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-09-02T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.8-flash"],"provider_price":{"provider_type":"google_vertex","pricing":{"input":"0.00000075","output":"0.00000375","audio":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000415","input_cache_write_1h":"0.0000005","input_cached_audio":"0.000000075","web_search":"0.014"},"is_override":true}},{"id":"qwen/qwen3.8-max-0902","canonical_slug":"qwen3.8-max-0902","display_name":"Qwen: Qwen3.8 Max 0902","description":"阿里云百炼 Qwen3.8 Max 2026-09-02 升级快照: 编码与协作 Agent 能力显著增强, 视觉理解优化; 保留 1M context、深度推理 (思考模式) 与图像/视频输入. 通过 DashScope OpenAI-compatible 端点提供.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1000000,"max_output_tokens":131072,"pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-09-02T00:00:00Z","is_deprecated":false,"aliases":["qwen3.8-max-0902","qwen3.8-max-2026-09-02","bailian/qwen3.8-max-0902"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"is_override":false}},{"id":"anthropic/claude-fable-5.1","canonical_slug":"claude-fable-5-1","display_name":"Anthropic: Claude Fable 5.1","description":"Anthropic Claude Fable 5.1 - Mythos-class frontier model (successor to Fable 5): ambitious coding, long-horizon agents, enterprise knowledge work; adaptive thinking always on","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.00001","output":"0.00005","input_cache_read":"0.00000025","input_cache_write_5m":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["aws_bedrock"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-09-01T00:00:00Z","is_deprecated":false,"aliases":["claude-fable-5-1","claude-fable-5-1-20260901"],"provider_price":null},{"id":"z-ai/glm-5.3-flash","canonical_slug":"glm-5.3-flash","display_name":"Z.ai: GLM-5.3-Flash","description":"GLM-5.3-Flash 是 z.ai 国际站 (api.z.ai) 轻量高速模型, 原生多模态输入 (图片/视频), 面向高效编码与长程 agent 任务. 1M context, 常驻 thinking (不可关闭, 支持 low/high/max 三档 reasoning effort), 支持 prompt caching / tool calling / web search. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":1048576,"max_output_tokens":131072,"pricing":{"input":"0.00000015","output":"0.0000005","input_cache_read":"0.00000003","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine","zai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-26T00:00:00Z","is_deprecated":false,"aliases":["glm-5.3-flash"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.00000015","output":"0.0000005","input_cache_read":"0.00000003","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.8-flash","canonical_slug":"qwen3.8-flash","display_name":"Qwen: Qwen3.8 Flash","description":"阿里云百炼 Qwen3.8 系列 Flash 轻量高速原生多模态模型, 1M context, 支持图像/视频理解与深度推理 (reasoning_content, 可按请求开关), 面向高并发低成本场景, 兼顾编程与办公任务. 通过 DashScope OpenAI-compatible 端点提供.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1131072,"max_output_tokens":131072,"pricing":{"input":"0.00000011","output":"0.00000039","input_cache_read":"0.000000011","input_cache_write":"0.00000014","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-25T00:00:00Z","is_deprecated":false,"aliases":["qwen3.8-flash","bailian/qwen3.8-flash"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000011","output":"0.00000039","input_cache_read":"0.000000011","input_cache_write":"0.00000014","web_search":"0.01"},"is_override":false}},{"id":"alibaba/wan-3.0","canonical_slug":"alibaba/wan-3.0-20260824","display_name":"Wan 3.0","description":"阿里通义万相 3.0 视频生成模型，单模型统一支持文生视频、图生视频（首帧/首尾帧）与参考生视频，可混合输入文本、图片、视频、音频等多模态素材（最多 10 张参考图、5 段参考视频/音频）。480P/720P/1080P 分辨率、2-30 秒时长、6 种宽高比与自适应，默认输出同步音频，支持视频续写与编辑。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"wan","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.054","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.054"},{"resolution":"720p","price":"0.11"},{"resolution":"1080p","price":"0.21"},{"price":"0.21"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-08-24T00:00:00Z","is_deprecated":false,"aliases":["wan-3.0","wan-3.0-20260824"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p","1080p"],"default_resolution":"1080p","min_duration_seconds":2,"max_duration_seconds":30,"supports_audio":true,"aspect_ratios":["16:9","4:3","1:1","3:4","9:16","adaptive"]},"provider_price":{"provider_type":"alicloud","pricing":{"input":"0","output":"0","output_video_per_second":"0.054","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.054"},{"resolution":"720p","price":"0.11"},{"resolution":"1080p","price":"0.21"},{"price":"0.21"}]}},"is_override":false}},{"id":"alibaba/wan-3.0-prime","canonical_slug":"alibaba/wan-3.0-prime-20260824","display_name":"Wan 3.0 Prime","description":"阿里通义万相 3.0 优速版视频生成模型，在保持 3.0 生成质量的同时大幅提升生成速度。单模型统一支持文生视频、图生视频（首帧/首尾帧）与参考生视频，可混合输入文本、图片、视频、音频等多模态素材。480P/720P/1080P 分辨率、2-30 秒时长、6 种宽高比与自适应，默认输出同步音频。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"wan","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.064","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.064"},{"resolution":"720p","price":"0.13"},{"resolution":"1080p","price":"0.26"},{"price":"0.26"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-08-24T00:00:00Z","is_deprecated":false,"aliases":["wan-3.0-prime","wan-3.0-prime-20260824"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p","1080p"],"default_resolution":"1080p","min_duration_seconds":2,"max_duration_seconds":30,"supports_audio":true,"aspect_ratios":["16:9","4:3","1:1","3:4","9:16","adaptive"]},"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_video_per_second":"0.064","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.064"},{"resolution":"720p","price":"0.13"},{"resolution":"1080p","price":"0.26"},{"price":"0.26"}]}},"is_override":false}},{"id":"qwen/qwen3.8-27b","canonical_slug":"qwen3.8-27b","display_name":"Qwen: Qwen3.8 27B","description":"阿里云百炼 Qwen3.8 系列 27B 原生视觉语言 Dense 模型, 1M context, 支持图像/视频理解与深度推理 (reasoning_content, 可按请求开关), 相比 3.6-27B 重点提升文本与视觉模态下的编程与办公场景能力. 通过 DashScope OpenAI-compatible 端点提供.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1131072,"max_output_tokens":131072,"pricing":{"input":"0.0000005","output":"0.00000171","input_cache_read":"0.000000043","input_cache_write":"0.00000063","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-19T00:00:00Z","is_deprecated":false,"aliases":["qwen3.8-27b","bailian/qwen3.8-27b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000005","output":"0.00000171","input_cache_read":"0.000000043","input_cache_write":"0.00000063","web_search":"0.01"},"is_override":false}},{"id":"z-ai/glm-5.3","canonical_slug":"glm-5.3","display_name":"Z.ai: GLM-5.3","description":"GLM-5.3 是 z.ai 国际站 (api.z.ai) 旗舰推理模型, 在 GLM-5.2 基础上提升编码能力与性能/token 效率平衡, 面向复杂软件工程与长程 agent 任务. 1M context, 常驻 thinking (不可关闭, 支持 low/high/max 三档 reasoning effort), 支持 prompt caching / tool calling / web search. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":1048576,"max_output_tokens":128000,"pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["volcengine","zai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-19T00:00:00Z","is_deprecated":false,"aliases":["glm-5.3"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"is_override":false}},{"id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek-v4-pro-20260813","display_name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro (0813) is the official release of DeepSeek's flagship Mixture-of-Experts model with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. This version greatly enhances agent capabilities — tool use, code execution, and long-horizon multi-step workflows — alongside strong reasoning, coding, and software engineering performance.","icon":"DeepSeek","owned_by":"deepseek","model_protocol":"openai","series":"deepseek","mode":"chat","context_window":1000000,"max_output_tokens":384000,"pricing":{"input":"0.00000132","output":"0.00000396","input_cache_read":"0.000000044"},"capabilities":{"vision":false,"function_calling":true,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-13T00:00:00Z","is_deprecated":false,"aliases":["deepseek-v4-pro","deepseek-v4-pro-0813","deepseek-v4-pro-20260813"],"provider_price":null},{"id":"google/gemini-3.7-flash","canonical_slug":"gemini-3.7-flash","display_name":"Google: Gemini 3.7 Flash","description":"Gemini 3.7 Flash is Google's multimodal workhorse model for fast agentic workflows, coding, and complex multi-step reasoning, improving on 3.6 Flash in agentic benchmarks (GPQA Diamond ~94%, TAU-Bench ~80%). All input modalities (text/image/video/audio) unified pricing; batch tier at 50% discount. Thinking model with configurable levels. 1M context. Released August 13, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":65536,"pricing":{"input":"0.0000015","output":"0.0000075","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_audio":"0.00000015","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-08-13T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.7-flash"],"provider_price":{"provider_type":"google_vertex","pricing":{"input":"0.00000075","output":"0.00000375","audio":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000415","input_cache_write_1h":"0.0000005","input_cached_audio":"0.000000075","web_search":"0.014"},"is_override":true}},{"id":"x-ai/grok-4.6","canonical_slug":"grok-4.6","display_name":"xAI: Grok 4.6","description":"Grok 4.6 is xAI's most intelligent and fastest model, with frontier performance on coding, knowledge work, and STEM. 500K context, reasoning model, prompt caching supported. OpenAI-compatible protocol. Released August 12, 2026.","icon":"Grok","owned_by":"xai","model_protocol":"openai","series":"grok","mode":"chat","context_window":500000,"max_output_tokens":65536,"pricing":{"input":"0.000002","output":"0.000006","input_cache_read":"0.0000005"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["grok"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-12T00:00:00Z","is_deprecated":false,"aliases":["grok-4.6"],"provider_price":{"provider_type":"grok","pricing":{"input":"0.000002","output":"0.000006","input_cache_read":"0.0000005"},"is_override":false}},{"id":"bytedance/seedance-2.5","canonical_slug":"bytedance/seedance-2.5-20260807","display_name":"Seedance 2.5","description":"字节豆包新一代多模态创作视频模型，单段最长 30 秒。支持文本、图片、视频、音频混合输入（最多 30 图 + 10 视频 + 10 音频共 50 个参考素材）。4-30 秒任意整数时长、480p/720p 分辨率、6 种宽高比 + 自适应，默认输出带同步音频，支持多语言提示词。指令遵循、多镜头叙事与长时序一致性全面升级。","icon":"Jimeng","owned_by":"openai","model_protocol":"openai","series":"seedance","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.11","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.11"},{"resolution":"720p","input_type":"t2v","price":"0.24"},{"resolution":"1080p","input_type":"t2v","price":"0.6"},{"resolution":"480p","input_type":"v2v","price":"0.14"},{"resolution":"720p","input_type":"v2v","price":"0.3"},{"resolution":"1080p","input_type":"v2v","price":"0.71"},{"price":"0.71"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine","byteplus"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-08-07T00:00:00Z","is_deprecated":false,"aliases":["seedance-2.5","seedance-2.5-20260807"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p","1080p"],"default_resolution":"720p","min_duration_seconds":4,"max_duration_seconds":30,"supports_audio":true,"aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16","adaptive"]},"provider_price":{"provider_type":"volcengine","pricing":{"input":"0","output":"0","output_video_per_second":"0.11","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.11"},{"resolution":"720p","input_type":"t2v","price":"0.24"},{"resolution":"1080p","input_type":"t2v","price":"0.48"},{"resolution":"480p","input_type":"v2v","price":"0.14"},{"resolution":"720p","input_type":"v2v","price":"0.3"},{"resolution":"1080p","input_type":"v2v","price":"0.568"},{"price":"0.568"}]}},"is_override":true}},{"id":"qwen/qwen-image-3.0","canonical_slug":"qwen-image-3.0","display_name":"Qwen-Image 3.0","description":"Qwen-Image-3.0 是阿里巴巴 2026 年 8 月正式发布的生图模型, 支持文生图与参考图输入, 可精准渲染小至 10px 的文字与细节, 在图文一致性、复杂结构与画面质感上较前代全面提升。","icon":"Bailian","owned_by":"bailian","model_protocol":"openai","series":"qwen","mode":"image_generation","context_window":100000,"max_output_tokens":100000,"pricing":{"input":"0","output":"0","output_image_per_num":"0.03"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/generations"]},"released_at":"2026-08-05T00:00:00Z","is_deprecated":false,"aliases":["qwen-image-3.0","bailian/qwen-image-3.0"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_image_per_num":"0.03"},"is_override":false}},{"id":"qwen/qwen-image-3.0-pro","canonical_slug":"qwen-image-3.0-pro","display_name":"Qwen-Image 3.0 Pro","description":"Qwen-Image-3.0-Pro 是阿里巴巴 2026 年 8 月正式发布的生图旗舰模型 (Qwen-Image 3.0 系列高端档), 支持文生图与参考图输入, 可精准渲染小至 10px 的文字与细节, 在图文一致性、复杂结构、文字渲染与画面质感上全面领先。","icon":"Bailian","owned_by":"bailian","model_protocol":"openai","series":"qwen","mode":"image_generation","context_window":100000,"max_output_tokens":100000,"pricing":{"input":"0","output":"0","output_image_per_num":"0.07"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/generations"]},"released_at":"2026-08-05T00:00:00Z","is_deprecated":false,"aliases":["qwen-image-3.0-pro","bailian/qwen-image-3.0-pro"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_image_per_num":"0.07"},"is_override":false}},{"id":"qwen/qwen3.8-max","canonical_slug":"qwen3.8-max","display_name":"Qwen: Qwen3.8 Max","description":"阿里云百炼 Qwen3.8 系列 Max 旗舰模型, 1M context, 支持深度推理 (reasoning_content) 与更长思维链, 强编码与长程自治执行能力. 通过 DashScope OpenAI-compatible 端点提供.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1131072,"max_output_tokens":131072,"pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-08-03T00:00:00Z","is_deprecated":false,"aliases":["qwen3.8-max","bailian/qwen3.8-max"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"is_override":false}},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek-v4-flash-20260731","display_name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.","icon":"DeepSeek","owned_by":"deepseek","model_protocol":"openai","series":"deepseek","mode":"chat","context_window":1000000,"max_output_tokens":384000,"pricing":{"input":"0.00000044","output":"0.00000132","input_cache_read":"0.000000014"},"capabilities":{"vision":false,"function_calling":true,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-31T00:00:00Z","is_deprecated":false,"aliases":["deepseek-v4-flash","deepseek-v4-flash-0731","deepseek-v4-flash-20260731"],"provider_price":null},{"id":"minimax/hailuo-3","canonical_slug":"minimax/hailuo-3-20260731","display_name":"MiniMax H3","description":"MiniMax 新一代全模态视频生成模型，原生输出带同步音轨。支持文本、图片、视频、音频混合输入，可用首帧/尾帧锚定画面，或用参考图/参考视频/参考音频引导风格。4-15 秒任意整数时长，768P 与 2K 两档分辨率，7 种画幅（含自适应）。","icon":"Minimax","owned_by":"openai","model_protocol":"openai","series":"hailuo","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.08","video_pricing":{"unit":"per_second","tiers":[{"resolution":"768p","price":"0.08"},{"resolution":"2k","price":"0.13"},{"price":"0.13"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["minimax","novita"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-07-31T00:00:00Z","is_deprecated":false,"aliases":["hailuo-3","minimax-h3"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["768p","2k"],"default_resolution":"768p","min_duration_seconds":4,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16","adaptive"]},"provider_price":{"provider_type":"minimax","pricing":{"input":"0","output":"0","output_video_per_second":"0.08","video_pricing":{"unit":"per_second","tiers":[{"resolution":"768p","price":"0.08"},{"resolution":"2k","price":"0.13"},{"price":"0.13"}]}},"is_override":false}},{"id":"minimax/hailuo-3-max","canonical_slug":"minimax/hailuo-3-max-20260731","display_name":"MiniMax H3 Max","description":"MiniMax H3 的高速版本，同样原生输出带同步音轨。支持文本、图片、视频、音频混合输入与首尾帧锚定。5-15 秒任意整数时长，480P 与 768P 两档分辨率，7 种画幅（含自适应）。参考素材不额外计费。","icon":"Minimax","owned_by":"openai","model_protocol":"openai","series":"hailuo","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.05","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.05"},{"resolution":"768p","price":"0.08"},{"price":"0.08"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["minimax","novita"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-07-31T00:00:00Z","is_deprecated":false,"aliases":["hailuo-3-max","minimax-h3-max"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","768p"],"default_resolution":"768p","min_duration_seconds":5,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16","adaptive"]},"provider_price":{"provider_type":"minimax","pricing":{"input":"0","output":"0","output_video_per_second":"0.05","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","price":"0.05"},{"resolution":"768p","price":"0.08"},{"price":"0.08"}]}},"is_override":false}},{"id":"openai/gpt-transcribe","canonical_slug":"gpt-transcribe-20260728","display_name":"OpenAI: GPT Transcribe","description":"GPT Transcribe is OpenAI's speech-to-text model released alongside gpt-live-transcribe. It delivers lower word error rates than the GPT-4o transcription family across multilingual benchmarks and is billed by audio duration, making costs predictable for transcription workloads.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"audio_transcription","context_window":128000,"max_output_tokens":128000,"pricing":{"input":"0","output":"0"},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":true,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/audio/transcriptions"]},"released_at":"2026-07-28T00:00:00Z","is_deprecated":false,"aliases":["gpt-transcribe","gpt-transcribe-20260728"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0","output":"0"},"is_override":false}},{"id":"anthropic/claude-opus-5","canonical_slug":"claude-opus-5","display_name":"Anthropic: Claude Opus 5","description":"Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is particularly strong at end-to-end software tasks - implementing features, code review and bug finding, multi-stage debugging - as well as visual analysis of documents and diagrams, and coordinating multiple agents on complex deliverables. It maintains strong instruction-following and tool use across extended interactions, and remains efficient for latency-sensitive workloads.","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.000005","output":"0.000025","input_cache_read":"0.0000005","input_cache_write_5m":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.015"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["aws_bedrock"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-25T00:00:00Z","is_deprecated":false,"aliases":["claude-opus-5","claude-opus-5-20260725"],"provider_price":null},{"id":"google/gemini-3.5-flash-lite","canonical_slug":"gemini-3.5-flash-lite","display_name":"Google: Gemini 3.5 Flash Lite","description":"Gemini 3.5 Flash-Lite is Google's high-throughput, low-latency multimodal model with upgraded agentic capabilities, suited for subagents executing focused tasks within complex multi-agent workflows, agentic search, and document processing. All input modalities (text/image/video/audio) unified at $0.30/1M; batch tier at 50% discount. Successor to Gemini 3.1 Flash Lite. Released July 21, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":65536,"pricing":{"input":"0.0000003","output":"0.0000025","audio":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_audio":"0.00000003","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-07-21T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.5-flash-lite"],"provider_price":null},{"id":"google/gemini-3.6-flash","canonical_slug":"gemini-3.6-flash","display_name":"Google: Gemini 3.6 Flash","description":"Gemini 3.6 Flash is Google's token-efficient workhorse model: 17% fewer output tokens than 3.5 Flash, fewer reasoning steps and tool calls in multi-step agentic workflows, and higher-precision code edits with reduced execution loops. All input modalities (text/image/video/audio) unified at $1.50/1M; batch tier at 50% discount. Thinking model with configurable levels. Released July 21, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":65536,"pricing":{"input":"0.00000075","output":"0.00000375","audio":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_audio":"0.000000075","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-07-21T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.6-flash"],"provider_price":{"provider_type":"google_vertex","pricing":{"input":"0.00000075","output":"0.00000375","audio":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000415","input_cache_write_1h":"0.0000005","input_cached_audio":"0.000000075","web_search":"0.014"},"is_override":true}},{"id":"moonshotai/kimi-k3","canonical_slug":"kimi-k3-20260716","display_name":"MoonshotAI: Kimi K3","description":"Kimi K3 是 Moonshot 官方 (api.moonshot.cn) 2026-07-16 发布的旗舰模型 (2.8T MoE), 1M token 上下文, 内嵌 thinking (reasoning_content), 支持视觉输入。OpenAI 协议直用; Anthropic 协议不强制 thinking 参数, 经 bifrost 转换正常 (与 K2.7 不同)。","icon":"Moonshot","owned_by":"MoonshotAI","model_protocol":"openai","series":"kimi","mode":"chat","context_window":1048576,"max_output_tokens":1048576,"pricing":{"input":"0.000003","output":"0.000015","input_cache_read":"0.0000003","web_search":"0.005"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["moonshot","azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-16T00:00:00Z","is_deprecated":false,"aliases":["kimi-k3"],"provider_price":{"provider_type":"moonshot","pricing":{"input":"0.000003","output":"0.000015","input_cache_read":"0.0000003","web_search":"0.005"},"is_override":false}},{"id":"openai/gpt-5.6-luna","canonical_slug":"gpt-5.6-luna","display_name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.000001","output":"0.000006","input_cache_read":"0.0000001","input_cache_write":"0.00000125","output_image":"0.000032","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["openai","azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-09T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.6-luna","gpt-5.6-luna-2026-07-09"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.0000002","output":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"openai/gpt-5.6-sol","canonical_slug":"gpt-5.6-sol","display_name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.000005","output":"0.00003","input_cache_read":"0.0000005","input_cache_write":"0.00000625","output_image":"0.000032","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-09T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.6-sol","gpt-5.6-sol-2026-07-09"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.0000025","output":"0.000015","input_cache_read":"0.00000025","input_cache_write":"0.000003125","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"openai/gpt-5.6-terra","canonical_slug":"gpt-5.6-terra","display_name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.0000025","output":"0.000015","input_cache_read":"0.00000025","input_cache_write":"0.000003125","output_image":"0.000032","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-09T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.6-terra","gpt-5.6-terra-2026-07-09"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.000002","output":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"volcengine/doubao-seedream-5.0-pro","canonical_slug":"doubao-seedream-5-0-pro-260628","display_name":"Doubao Seedream 5.0 Pro","description":"Doubao-Seedream-5.0-pro是字节跳动2026年7月发布的图像创作旗舰模型。相比前代在图文匹配、结构合理性、文字渲染与画面美感等基础能力上全面提升，具备四大突破：复杂信息可视化、交互式精准编辑（点选/圈选/草图渲染/图层分离/多图融合）、真实影像与人像质感、原生多语种（十余种语言）输入生成。支持文生图、图生图、参考图一致性编辑，面向企业级专业视觉创作。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"image_generation","context_window":100000,"max_output_tokens":100000,"pricing":{"input":"0","output":"0","output_image_per_num":"0.05"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/generations"]},"released_at":"2026-07-08T00:00:00Z","is_deprecated":false,"aliases":["doubao-seedream-5.0-pro","doubao-seedream-5-0-pro-260628"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0","output":"0","output_image_per_num":"0.04"},"is_override":true}},{"id":"x-ai/grok-4.5","canonical_slug":"grok-4.5","display_name":"xAI: Grok 4.5","description":"Grok 4.5 is xAI's frontier model with strong performance on coding, knowledge work, and STEM. 500K context, reasoning model, prompt caching supported. OpenAI-compatible protocol. Released July 8, 2026.","icon":"Grok","owned_by":"xai","model_protocol":"openai","series":"grok","mode":"chat","context_window":500000,"max_output_tokens":65536,"pricing":{"input":"0.000002","output":"0.000006","input_cache_read":"0.0000003"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["grok"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-08T00:00:00Z","is_deprecated":false,"aliases":["grok-4.5"],"provider_price":{"provider_type":"grok","pricing":{"input":"0.000002","output":"0.000006","input_cache_read":"0.0000003"},"is_override":false}},{"id":"anthropic/claude-sonnet-5","canonical_slug":"claude-sonnet-5","display_name":"Anthropic: Claude Sonnet 5","description":"Anthropic Claude Sonnet 5 — 2026-07-01 发布的 Sonnet 系旗舰, 1M 上下文, 支持 adaptive thinking / vision / prompt caching / tools。走标准 Bedrock Converse。","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.000002","output":"0.00001","input_cache_read":"0.0000002","input_cache_write_5m":"0.0000025","input_cache_write_1h":"0.000004","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["anthropic","aws_bedrock"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-07-01T00:00:00Z","is_deprecated":false,"aliases":["claude-sonnet-5"],"provider_price":{"provider_type":"anthropic","pricing":{"input":"0.000002","output":"0.00001","input_cache_read":"0.0000002","input_cache_write_5m":"0.0000025","input_cache_write_1h":"0.000004","web_search":"0.01"},"is_override":false}},{"id":"google/gemini-3.1-flash-lite-image","canonical_slug":"gemini-3.1-flash-lite-image","display_name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","description":"Gemini 3.1 Flash Lite Image is Google's most cost-efficient image generation and editing model, supporting text-to-image, image editing, and multi-image composition. Outputs generated at 1K resolution across 14 aspect ratios, at the lowest price point in the Nano Banana family.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"image_generation","context_window":66000,"max_output_tokens":64000,"pricing":{"input":"0.00000025","output":"0.0000015","output_image":"0.00003"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-30T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.1-flash-lite-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]},"provider_price":null},{"id":"alibaba/happyhorse-1.0","canonical_slug":"alibaba/happyhorse-1.0-20260624","display_name":"HappyHorse 1.0","description":"阿里通义 HappyHorse（快马）1.0 视频生成模型，主打高度还原的动态画面生成，精准理解文本语义，输出流畅自然、主体稳定的高质量视频。支持文生视频（带同步音频、运镜景别指令）、图生视频（最多 9 张参考图）、视频编辑，集成唇形同步能力。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"happyhorse","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.13","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.14"},{"resolution":"1080p","price":"0.23"},{"price":"0.23"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-06-24T00:00:00Z","is_deprecated":false,"aliases":["happyhorse-1.0","happyhorse-1.0-20260624"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["720p","1080p"],"default_resolution":"1080p","min_duration_seconds":3,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1"]},"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_video_per_second":"0.13","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.14"},{"resolution":"1080p","price":"0.23"},{"price":"0.23"}]}},"is_override":false}},{"id":"alibaba/happyhorse-1.1","canonical_slug":"alibaba/happyhorse-1.1-20260624","display_name":"HappyHorse 1.1","description":"阿里通义 HappyHorse（快马）1.1 视频生成模型，在 1.0 基础上进一步提升画面还原度与主体一致性。支持文生视频、多图参考图生视频、视频风格化编辑，8 步去噪实现清晰输出，端到端提速约 1.2 倍，内置专用唇形同步。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"happyhorse","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.13","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.14"},{"resolution":"1080p","price":"0.18"},{"price":"0.18"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-06-24T00:00:00Z","is_deprecated":false,"aliases":["happyhorse-1.1","happyhorse-1.1-20260624"],"video_attributes":{"modes":["t2v","i2v"],"resolutions":["720p","1080p"],"default_resolution":"1080p","min_duration_seconds":3,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1"]},"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_video_per_second":"0.13","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.14"},{"resolution":"1080p","price":"0.18"},{"price":"0.18"}]}},"is_override":false}},{"id":"volcengine/doubao-seed-2.1-pro","canonical_slug":"doubao-seed-2-1-pro-260628","display_name":"Doubao Seed 2.1 Pro","description":"火山引擎豆包 Seed 2.1 Pro 旗舰推理模型, 内嵌 thinking。OpenAI + Anthropic 双协议。ARK 真实 id doubao-seed-2-1-pro-260628。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":256000,"pricing":{"input":"0.000000884","output":"0.00000442","input_cache_read":"0.000000177","input_cache_write":"0.0000000025","web_search":"0.0012"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-23T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.1-pro"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.0000007072","output":"0.000003536","input_cache_read":"0.0000001416","input_cache_write":"0.000000002","web_search":"0.0012"},"is_override":true}},{"id":"volcengine/doubao-seed-2.1-turbo","canonical_slug":"doubao-seed-2-1-turbo-260628","display_name":"Doubao Seed 2.1 Turbo","description":"火山引擎豆包 Seed 2.1 Turbo 高速推理模型, 内嵌 thinking。OpenAI + Anthropic 双协议。ARK 真实 id doubao-seed-2-1-turbo-260628。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":256000,"pricing":{"input":"0.000000442","output":"0.000002212","input_cache_read":"0.000000085","input_cache_write":"0.0000000024","web_search":"0.0012"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-23T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.1-turbo"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.0000003536","output":"0.0000017696","input_cache_read":"0.000000068","input_cache_write":"0.0000000019","web_search":"0.0012"},"is_override":true}},{"id":"volcengine/doubao-seed-character","canonical_slug":"doubao-seed-character-260628","display_name":"Doubao Seed Character","description":"火山引擎豆包 Seed Character 角色对话模型。仅 OpenAI 协议 (Anthropic messages_api 火山侧未授权, 见 issue 2026-06-24)。ARK 真实 id doubao-seed-character-260628。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":256000,"pricing":{"input":"0.000000177","output":"0.000000884","input_cache_read":"0.000000024","input_cache_write":"0.0000000025","web_search":"0.0012"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-23T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-character"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.000000177","output":"0.000000884","input_cache_read":"0.000000024","input_cache_write":"0.0000000025","web_search":"0.0012"},"is_override":false}},{"id":"volcengine/doubao-seed-evolving","canonical_slug":"doubao-seed-evolving-latest-version","display_name":"Doubao Seed Evolving","description":"火山引擎豆包 Seed Evolving 快速迭代推理模型 (latest-version 滚动更新), 内嵌 thinking。OpenAI + Anthropic + Responses 三端点。ARK id doubao-seed-evolving 解析为 -latest-version。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":256000,"pricing":{"input":"0.000000884","output":"0.00000442","input_cache_read":"0.000000177","input_cache_write":"0.0000000025","web_search":"0.0012"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-23T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-evolving"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.000000884","output":"0.00000442","input_cache_read":"0.000000177","input_cache_write":"0.0000000025","web_search":"0.0012"},"is_override":false}},{"id":"microsoft/mai-image-2.5-pro","canonical_slug":"mai-image-2.5-pro-2026-06-19","display_name":"Microsoft: MAI Image 2.5 Pro","description":"MAI-Image-2.5-Pro is the flagship of Microsoft's MAI image family, designed for complex compositions with strong object and character consistency, accurate material properties and coherent spatial reasoning. Best suited for photorealistic scenes, rich documentary-style imagery and demanding creative work. Supports text-to-image generation and image-to-image editing.","icon":"Azure","owned_by":"azure","model_protocol":"openai","mode":"image_generation","context_window":4100,"max_output_tokens":1000,"pricing":{"input":"0.000005","output":"0.000106","image":"0.000008","output_image":"0.000106"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-19T00:00:00Z","is_deprecated":false,"aliases":["mai-image-2.5-pro","mai-image-2.5-pro-2026-06-19","mai-image-2.5-pro-20260619"],"provider_price":null},{"id":"google/gemini-3.1-flash-image","canonical_slug":"gemini-3.1-flash-image","display_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google's state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. GA release of gemini-3.1-flash-image-preview, combining advanced contextual understanding with fast, cost-efficient inference.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"image_generation","context_window":131000,"max_output_tokens":64000,"pricing":{"input":"0.0000005","output":"0.000003","output_image":"0.00006","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-18T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.1-flash-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]},"provider_price":null},{"id":"google/gemini-3-pro-image","canonical_slug":"gemini-3-pro-image","display_name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","description":"Nano Banana Pro is Google's most advanced image-generation and editing model, built on Gemini 3 Pro. GA release of gemini-3-pro-image-preview. It generates context-rich graphics from infographics and diagrams to cinematic composites, with 2K/4K output, multi-image blending, identity preservation, and localized edits.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"image_generation","context_window":66000,"max_output_tokens":32000,"pricing":{"input":"0.000002","output":"0.000012","output_image":"0.00012","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-18T00:00:00Z","is_deprecated":false,"aliases":["gemini-3-pro-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]},"provider_price":null},{"id":"z-ai/glm-5.2","canonical_slug":"glm-5.2","display_name":"Z.ai: GLM-5.2","description":"GLM-5.2 是 z.ai 国际站 (api.z.ai) 旗舰推理模型, MoE 架构 open-weights, 1M context, 内嵌 thinking (reasoning_content), 支持 prompt caching / tool calling / web search. 强编码与长程自治执行. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":1048576,"max_output_tokens":128000,"pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["volcengine","zai","aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-16T00:00:00Z","is_deprecated":false,"aliases":["glm-5.2"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"is_override":false}},{"id":"bytedance/seedance-2.0-mini","canonical_slug":"doubao-seedance-2-0-mini-260615","display_name":"Seedance 2.0 Mini","description":"Seedance 2.0 轻量版，面向低成本快速视频生成，在保证画面质量的前提下进一步降低单位成本。支持文生视频与图生视频，适合预览、验证与大规模低成本生成。","icon":"Jimeng","owned_by":"openai","model_protocol":"openai","series":"seedance","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.04","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.04"},{"resolution":"720p","input_type":"t2v","price":"0.08"},{"resolution":"480p","input_type":"v2v","price":"0.05"},{"resolution":"720p","input_type":"v2v","price":"0.1"},{"price":"0.1"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine","byteplus"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-06-15T00:00:00Z","is_deprecated":false,"aliases":["seedance-2.0-mini","seedance-2.0-mini-20260615"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p"],"default_resolution":"720p","min_duration_seconds":4,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1","adaptive"]},"provider_price":{"provider_type":"volcengine","pricing":{"input":"0","output":"0","output_video_per_second":"0.02","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.02"},{"resolution":"720p","input_type":"t2v","price":"0.04"},{"resolution":"480p","input_type":"v2v","price":"0.03"},{"resolution":"720p","input_type":"v2v","price":"0.05"},{"price":"0.05"}]}},"is_override":true}},{"id":"moonshotai/kimi-k2.7-code","canonical_slug":"kimi-k2.7-code-20260612","display_name":"MoonshotAI: Kimi K2.7 Code","description":"Kimi K2.7 Code 是 Moonshot 官方 (api.moonshot.cn) 强编程推理模型, 内嵌 thinking。OpenAI 协议直用; Anthropic 协议需 thinking:type=enabled (bifrost 转换待修, 见 issue 2026-06-24)。","icon":"Moonshot","owned_by":"MoonshotAI","model_protocol":"openai","series":"kimi","mode":"chat","context_window":262144,"max_output_tokens":262144,"pricing":{"input":"0.00000095","output":"0.000004","input_cache_read":"0.00000019","web_search":"0.005"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun","azure_foundry","alicloud","moonshot"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-12T00:00:00Z","is_deprecated":false,"aliases":["kimi-k2.7-code"],"provider_price":{"provider_type":"moonshot","pricing":{"input":"0.00000095","output":"0.000004","input_cache_read":"0.00000019","web_search":"0.005"},"is_override":false}},{"id":"moonshotai/kimi-k2.7-code-highspeed","canonical_slug":"kimi-k2.7-code-highspeed-20260612","display_name":"MoonshotAI: Kimi K2.7 Code Highspeed","description":"Kimi K2.7 Code 高速档, 同模型加速推理。OpenAI 协议直用; Anthropic 协议同 code (bifrost thinking 待修)。","icon":"Moonshot","owned_by":"MoonshotAI","model_protocol":"openai","series":"kimi","mode":"chat","context_window":262144,"max_output_tokens":262144,"pricing":{"input":"0.0000019","output":"0.000008","input_cache_read":"0.00000038","web_search":"0.005"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["moonshot"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-06-12T00:00:00Z","is_deprecated":false,"aliases":["kimi-k2.7-code-highspeed"],"provider_price":{"provider_type":"moonshot","pricing":{"input":"0.0000019","output":"0.000008","input_cache_read":"0.00000038","web_search":"0.005"},"is_override":false}},{"id":"anthropic/claude-fable-5","canonical_slug":"claude-fable-5","display_name":"Anthropic: Claude Fable 5","description":"Anthropic Claude Fable 5 - Mythos-class, long-horizon agentic autonomy","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.00001","output":"0.00005","input_cache_read":"0.000001","input_cache_write_5m":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["aws_bedrock","anthropic"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-09T00:00:00Z","is_deprecated":false,"aliases":["claude-fable-5","claude-fable-5-20260609"],"provider_price":{"provider_type":"anthropic","pricing":{"input":"0.00001","output":"0.00005","input_cache_read":"0.000001","input_cache_write_5m":"0.0000125","input_cache_write_1h":"0.00002","web_search":"0.01"},"is_override":false}},{"id":"microsoft/mai-image-2.5","canonical_slug":"mai-image-2.5-2026-06-02","display_name":"Microsoft: MAI Image 2.5","description":"MAI-Image-2.5 is Microsoft's image generation and editing model. It excels at precise, surgical edits with consistency - targeted object edits, layout adaptation, text updates and artifact cleanup - while preserving visual consistency across iterations. Supports text-to-image generation and image-to-image editing with free aspect ratios up to 1 megapixel.","icon":"Azure","owned_by":"azure","model_protocol":"openai","mode":"image_generation","context_window":4100,"max_output_tokens":1000,"pricing":{"input":"0.000005","output":"0.000047","image":"0.000008","output_image":"0.000047"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-02T00:00:00Z","is_deprecated":false,"aliases":["mai-image-2.5","mai-image-2.5-2026-06-02","mai-image-2.5-20260602"],"provider_price":null},{"id":"microsoft/mai-image-2.5-flash","canonical_slug":"mai-image-2.5-flash-2026-06-02","display_name":"Microsoft: MAI Image 2.5 Flash","description":"MAI-Image-2.5-Flash is the low-latency variant of Microsoft's MAI image family, optimized for fast, high-volume image generation and editing. Produces diverse, coherent images across creative and design scenarios with median generation times several times faster than comparable models. Supports text-to-image generation and image-to-image editing.","icon":"Azure","owned_by":"azure","model_protocol":"openai","mode":"image_generation","context_window":4100,"max_output_tokens":1000,"pricing":{"input":"0.000005","output":"0.000026","image":"0.00000175","output_image":"0.0000195"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-06-02T00:00:00Z","is_deprecated":false,"aliases":["mai-image-2.5-flash","mai-image-2.5-flash-2026-06-02","mai-image-2.5-flash-20260602"],"provider_price":null},{"id":"minimax/minimax-m3","canonical_slug":"minimax-m3-2026-05-31","display_name":"MiniMax: MiniMax M3","description":"MiniMax-M3 是 MiniMax 官方渠道 (api.minimaxi.com) 旗舰推理模型, 1M context, 内嵌 thinking (\u003cthink\u003e 标签), 支持 prompt caching 与 tool calling. 通过 OpenAI-compatible + Anthropic 双协议接入 ofox china 池.","icon":"Minimax","owned_by":"minimax","model_protocol":"openai","series":"minimax","mode":"chat","context_window":1131000,"max_output_tokens":131000,"pricing":{"input":"0.0000006","output":"0.0000024","input_cache_read":"0.00000012"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["minimax"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-01T00:00:00Z","is_deprecated":false,"aliases":["minimax-m3"],"provider_price":{"provider_type":"minimax","pricing":{"input":"0.0000006","output":"0.0000024","input_cache_read":"0.00000012"},"is_override":false}},{"id":"qwen/qwen3.7-plus","canonical_slug":"qwen3.7-plus","display_name":"Qwen3.7 Plus","description":"阿里云百炼 Qwen3.7 系列 Plus 模型, 1M context, 支持深度推理 (reasoning), 性价比均衡定位 (input $0.4/output $1.6). 通过 DashScope OpenAI-compatible + Anthropic + Responses 三协议接入 ofox china 池.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1064000,"max_output_tokens":64000,"pricing":{"input":"0.0000004","output":"0.0000016","input_cache_read":"0.00000008","input_cache_write":"0.0000005","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["alicloud","aliyun"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-06-01T00:00:00Z","is_deprecated":false,"aliases":["qwen3.7-plus","bailian/qwen3.7-plus"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000004","output":"0.0000016","input_cache_read":"0.00000008","input_cache_write":"0.0000005","web_search":"0.01"},"is_override":false}},{"id":"anthropic/claude-opus-4.8","canonical_slug":"claude-opus-4-8","display_name":"Anthropic: Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters. It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.000005","output":"0.000025","input_cache_read":"0.0000005","input_cache_write_5m":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["anthropic","aws_bedrock"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-05-28T00:00:00Z","is_deprecated":false,"aliases":["claude-opus-4.8","claude-opus-4-8","claude-opus-4-8-20260528"],"provider_price":{"provider_type":"anthropic","pricing":{"input":"0.000005","output":"0.000025","input_cache_read":"0.0000005","input_cache_write_5m":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.7-max","canonical_slug":"qwen3.7-max","display_name":"Qwen: Qwen3.7 Max","description":"阿里云百炼 Qwen3.7 系列 Max 模型, 1M context, 支持深度推理 (reasoning_content), 强编码与长程自治执行能力. 通过 DashScope OpenAI-compatible 端点提供.","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1064000,"max_output_tokens":64000,"pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-05-21T00:00:00Z","is_deprecated":false,"aliases":["qwen3.7-max","bailian/qwen3.7-max"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000171","output":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"is_override":false}},{"id":"google/gemini-3.5-flash","canonical_slug":"gemini-3.5-flash","display_name":"Google: Gemini 3.5 Flash","description":"Gemini 3.5 Flash is Google's efficient multimodal model delivering near-Pro level coding and reasoning at Flash-tier cost and speed. Optimized for coding tasks and parallel agent execution with configurable thinking levels. Released May 20, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":65536,"pricing":{"input":"0.0000015","output":"0.000009","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cached_audio":"0.00000015","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-05-20T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.5-flash"],"provider_price":null},{"id":"google/gemini-3.1-flash-lite","canonical_slug":"gemini-3.1-flash-lite","display_name":"Google: Gemini 3.1 Flash Lite","description":"Gemini 3.1 Flash Lite (GA) is Google's high-efficiency multimodal model optimized for low-latency, high-volume workloads. GA version of the preview model. Supports full thinking levels (minimal, low, medium, high) for cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash. Released May 7, 2026.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1000000,"max_output_tokens":64000,"pricing":{"input":"0.00000025","output":"0.0000015","audio":"0.0000005","input_cache_read":"0.000000025","input_cache_write":"0.000001","input_cache_write_1h":"0.000001","input_cached_audio":"0.00000005","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-05-07T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.1-flash-lite"],"provider_price":null},{"id":"x-ai/grok-4.3","canonical_slug":"x-ai/grok-4.3-20260430","display_name":"xAI: Grok 4.3","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...","icon":"Grok","owned_by":"openrouter","model_protocol":"openai","series":"grok","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.00000125","output":"0.0000025","input_cache_read":"0.0000002","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["grok","azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-30T00:00:00Z","is_deprecated":false,"aliases":["grok-4.3","grok-4.3-20260430"],"provider_price":{"provider_type":"grok","pricing":{"input":"0.00000125","output":"0.0000025","input_cache_read":"0.0000002","web_search":"0.014"},"is_override":false}},{"id":"openai/gpt-5.5","canonical_slug":"gpt-5.5-2026-04-25","display_name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.000005","output":"0.00003","input_cache_read":"0.0000005","output_image":"0.000032","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-24T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.5","gpt-5.5-2026-04-24"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.000005","output":"0.00003","input_cache_read":"0.0000005","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"deepseek/deepseek-v4-flash-0423","canonical_slug":"deepseek-v4-flash-20260423","display_name":"DeepSeek V4 Flash 0423","description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.","icon":"DeepSeek","owned_by":"deepseek","model_protocol":"openai","series":"deepseek","mode":"chat","context_window":1000000,"max_output_tokens":384000,"pricing":{"input":"0.00000019","output":"0.00000051","input_cache_read":"0.000000028","web_search":"0.014"},"capabilities":{"vision":false,"function_calling":true,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-23T00:00:00Z","is_deprecated":false,"aliases":["deepseek-v4-flash-0423","deepseek-v4-flash-20260423","deepseek-v4-flash-20260424"],"provider_price":null},{"id":"deepseek/deepseek-v4-pro-0423","canonical_slug":"deepseek-v4-pro-20260423","display_name":"DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.","icon":"DeepSeek","owned_by":"deepseek","model_protocol":"openai","series":"deepseek","mode":"chat","context_window":1000000,"max_output_tokens":384000,"pricing":{"input":"0.00000132","output":"0.00000396","input_cache_read":"0.00000015","web_search":"0.014"},"capabilities":{"vision":false,"function_calling":true,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-23T00:00:00Z","is_deprecated":false,"aliases":["deepseek-v4-pro-0423","deepseek-v4-pro-20260423","deepseek-v4-pro-20260424"],"provider_price":null},{"id":"qwen/qwen3.6-27b","canonical_slug":"qwen3.6-27b","display_name":"Qwen: Qwen3.6 27B","description":"Qwen3.6系列27B原生视觉语言Dense模型，模型效果相较3.5-27B重点提升了Agentic coding能力、模型STEM与推理能力进一步增强；视觉模态方面在空间智能、物体定位与检测能力上显著增强，视频理解、文档OCR及视觉Agent能力稳步提升。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.00000043","output":"0.00000257","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-04-22T00:00:00Z","is_deprecated":false,"aliases":["qwen3.6-27b","bailian/qwen3.6-27b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000043","output":"0.00000257","web_search":"0.01"},"is_override":false}},{"id":"moonshotai/kimi-k2.6","canonical_slug":"kimi-k2.6-20260421","display_name":"MoonshotAI: Kimi K2.6","description":"Kimi K2.6 是 Kimi 最新最智能的模型，Kimi K2.6 的通用 Agent、代码、视觉理解等综合能力得到全面提升，其中在博士级难度的完整版人类最后的考试（Humanity’s Last Exam）、在考察模型真实软件工程能力的 SWE-Bench Pro、评估 Agent 深度检索能力的 DeepSearchQA 等基准测试中均取得行业领先的成绩，同时支持文本、图片与视频输入，思考与非思考模式，对话与 Agent 任务。","icon":"Moonshot","owned_by":"MoonshotAI","model_protocol":"openai","series":"kimi","mode":"chat","context_window":262144,"max_output_tokens":262144,"pricing":{"input":"0.00000095","output":"0.000004","input_cache_read":"0.00000016","web_search":"0.005"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","aliyun","moonshot"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-21T00:00:00Z","is_deprecated":false,"aliases":["kimi-k2.6","kimi-k2.6-20260421"],"provider_price":{"provider_type":"moonshot","pricing":{"input":"0.00000095","output":"0.000004","input_cache_read":"0.00000016","web_search":"0.005"},"is_override":false}},{"id":"openai/gpt-image-2","canonical_slug":"gpt-image-2-2026-04-21","display_name":"OpenAI: GPT Image 2","description":"GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds include better performance, quality, editing controls, and face preservation.\r\nThe model supports high input_fidelity and adding/removing one aspect of the image while retaining others. This model includes improvements in aspect ratio, resolution, and editing capabilities.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"image_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["openai","azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/images/edits","/v1/images/generations"]},"released_at":"2026-04-21T00:00:00Z","is_deprecated":false,"aliases":["gpt-image-2","gpt-image-2-2026-04-21","gpt-image-2-20260421"],"image_attributes":{"supported_params":["prompt","n","size","quality","output_format","stream","user"]},"provider_price":{"provider_type":"openai","pricing":{"input":"0.000005","output":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"is_override":false}},{"id":"qwen/qwen3.6-max-preview","canonical_slug":"qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","description":"Qwen3.6系列中规模最大、综合能力最强的Max模型Preview版本，当前开放纯文本模型能力供体验。相较于此前发布的Qwen3-Max和Qwen3.6-Plus，本模型在vibe coding能力上进一步提升、coding agent执行更加高效、前端编程开发能力显著提升；长尾知识能力进一步升级。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.000002","output":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000002","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-04-20T00:00:00Z","is_deprecated":false,"aliases":["qwen3.6-max-preview","bailian/qwen3.6-max-preview"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000215","output":"0.00001286","input_cache_read":"0.0000002","input_cache_write":"0.00000117","web_search":"0.01"},"is_override":true}},{"id":"anthropic/claude-opus-4.7","canonical_slug":"claude-opus-4-7","display_name":"Anthropic: Claude Opus 4.7","description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.000005","output":"0.000025","input_cache_read":"0.0000005","input_cache_write_5m":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["aws_bedrock","anthropic"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-16T00:00:00Z","is_deprecated":false,"aliases":["claude-opus-4.7","claude-opus-4-7","claude-opus-4-7-20260416"],"provider_price":{"provider_type":"anthropic","pricing":{"input":"0.000005","output":"0.000025","input_cache_read":"0.0000005","input_cache_write_5m":"0.00000625","input_cache_write_1h":"0.00001","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.6-flash","canonical_slug":"qwen3.6-flash-2026-04-16","display_name":"Qwen: Qwen3.6 Flash","description":"Qwen3.6原生视觉语言系列Flash模型，模型效果相较3.5-Flash显著提升。本模型重点提升agentic coding能力（在多项代码智能体基准上大幅超越前代）、数学推理和代码推理能力；视觉方面在空间智能能力上显著增强，物体定位与目标检测提升尤为突出。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1000000,"max_output_tokens":64000,"pricing":{"input":"0.00000025","output":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.00000031","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-16T00:00:00Z","is_deprecated":false,"aliases":["qwen3.6-flash","bailian/qwen3.6-flash"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000025","output":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.00000031","web_search":"0.01"},"is_override":false}},{"id":"bytedance/seedance-2.0","canonical_slug":"bytedance/seedance-2.0-20260414","display_name":"Seedance 2.0","description":"字节豆包新一代多模态创作视频模型，支持文本、图片、视频、音频四种模态混合输入（最多 9 图 + 3 视频 + 3 音频）。4-15 秒可控时长、480p/720p/1080p 三档分辨率、6 种宽高比 + 自适应，默认输出带同步音频，支持多语言提示词。擅长多人竞技运动、多镜头叙事等复杂场景。","icon":"Jimeng","owned_by":"openai","model_protocol":"openai","series":"seedance","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.07","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.07"},{"resolution":"720p","input_type":"t2v","price":"0.16"},{"resolution":"1080p","input_type":"t2v","price":"0.34"},{"resolution":"4k","input_type":"t2v","price":"1.37"},{"resolution":"480p","input_type":"v2v","price":"0.09"},{"resolution":"720p","input_type":"v2v","price":"0.2"},{"resolution":"1080p","input_type":"v2v","price":"0.45"},{"resolution":"4k","input_type":"v2v","price":"1.7"},{"price":"1.7"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["byteplus","volcengine"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-04-14T00:00:00Z","is_deprecated":false,"aliases":["seedance-2.0","seedance-2.0-20260414"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p","1080p","4k"],"default_resolution":"1080p","min_duration_seconds":4,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1","adaptive"]},"provider_price":{"provider_type":"byteplus","pricing":{"input":"0","output":"0","output_video_per_second":"0.063","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.063"},{"resolution":"720p","input_type":"t2v","price":"0.15"},{"resolution":"1080p","input_type":"t2v","price":"0.31"},{"resolution":"4k","input_type":"t2v","price":"1.24"},{"resolution":"480p","input_type":"v2v","price":"0.081"},{"resolution":"720p","input_type":"v2v","price":"0.18"},{"resolution":"1080p","input_type":"v2v","price":"0.41"},{"resolution":"4k","input_type":"v2v","price":"1.53"},{"price":"1.53"}]}},"is_override":true}},{"id":"bytedance/seedance-2.0-fast","canonical_slug":"bytedance/seedance-2.0-fast-20260414","display_name":"Seedance 2.0 Fast","description":"Seedance 2.0 极速版，在标准版多模态视频生成能力基础上优化推理速度，适合对生成时延敏感的批量创作场景。支持文生视频、图生视频、多模态参考输入，480p/720p/1080p 分辨率，默认带同步音频。","icon":"Jimeng","owned_by":"openai","model_protocol":"openai","series":"seedance","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.06","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.06"},{"resolution":"720p","input_type":"t2v","price":"0.13"},{"resolution":"480p","input_type":"v2v","price":"0.07"},{"resolution":"720p","input_type":"v2v","price":"0.15"},{"price":"0.15"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["byteplus","volcengine"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-04-14T00:00:00Z","is_deprecated":false,"aliases":["seedance-2.0-fast","seedance-2.0-fast-20260414"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["480p","720p"],"default_resolution":"720p","min_duration_seconds":4,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1","adaptive"]},"provider_price":{"provider_type":"volcengine","pricing":{"input":"0","output":"0","output_video_per_second":"0.042","video_pricing":{"unit":"per_second","tiers":[{"resolution":"480p","input_type":"t2v","price":"0.042"},{"resolution":"720p","input_type":"t2v","price":"0.091"},{"resolution":"480p","input_type":"v2v","price":"0.05"},{"resolution":"720p","input_type":"v2v","price":"0.11"},{"price":"0.11"}]}},"is_override":true}},{"id":"alibaba/wan-2.7","canonical_slug":"alibaba/wan-2.7-20260414","display_name":"Wan 2.7","description":"阿里通义万相 2.7 视频生成模型，在 2.6 基础上增强图生视频能力，支持首帧生视频、首尾帧生视频、视频续写三大任务，画面连贯性与指令遵循优先于 2.6 及更早版本。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"wan","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.1","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.086"},{"resolution":"1080p","price":"0.15"},{"price":"0.15"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["alicloud","aliyun"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-04-14T00:00:00Z","is_deprecated":false,"aliases":["wan-2.7","wan-2.7-20260414"],"video_attributes":{"modes":["t2v","i2v","v2v"],"resolutions":["720p","1080p"],"default_resolution":"1080p","min_duration_seconds":2,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1"]},"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_video_per_second":"0.1","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.086"},{"resolution":"1080p","price":"0.15"},{"price":"0.15"}]}},"is_override":false}},{"id":"qwen/qwen3.6-plus","canonical_slug":"qwen3.6-plus-2026-04-02","display_name":"Qwen: Qwen3.6 Plus","description":"Qwen3.6原生视觉语言系列Plus模型，展现出与当前顶尖前沿模型相媲美的卓越性能，模型效果相较3.5系列显著提升。模型在Agentic coding、前端编程、Vibe coding等代码能力、多模态万物识别、OCR、物体定位等能力上显著增强。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1000000,"max_output_tokens":64000,"pricing":{"input":"0.0000005","output":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.000000625","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-04-02T00:00:00Z","is_deprecated":false,"aliases":["bailian/qwen3-6-plus","bailian/qwen3.6-plus"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000005","output":"0.000003","input_cache_read":"0.00000005","input_cache_write":"0.000000625","web_search":"0.01"},"is_override":false}},{"id":"z-ai/glm-5v-turbo","canonical_slug":"glm-5v-turbo","display_name":"GLM-5V-Turbo","description":"GLM-5V-Turbo is Z.AI’s first multimodal coding foundation model, built for vision-based coding tasks. It can natively process multimodal inputs such as images, video, and text, while also excelling at long-horizon planning, complex coding, and action execution. ","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":200000,"max_output_tokens":128000,"pricing":{"input":"0.0000012","output":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":true},"supported_provider_types":["zai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-04-01T00:00:00Z","is_deprecated":false,"aliases":["glm-5v-turbo"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.0000012","output":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"is_override":false}},{"id":"x-ai/grok-4.20","canonical_slug":"grok-4-20-non-reasoning","display_name":"xAI: Grok 4.20","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 precise and truthful responses.","icon":"Grok","owned_by":"xai","model_protocol":"openai","series":"grok","mode":"chat","context_window":2000000,"max_output_tokens":128000,"pricing":{"input":"0.000004","output":"0.000012","input_cache_read":"0.0000004","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":false,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-31T00:00:00Z","is_deprecated":false,"provider_price":null},{"id":"alibaba/wan-2.6","canonical_slug":"alibaba/wan-2.6-20260327","display_name":"Wan 2.6","description":"阿里通义万相 2.6 视频生成模型，面向专业影视级制作全面升级。首创角色扮演能力，可用人物或任意物体作为主角生成单人表演或多人协作，具备多镜头叙事、智能调度、多人对话稳定、时长更长、指令遵循更强、音画同步等特性。","icon":"Qwen","owned_by":"openai","model_protocol":"openai","series":"wan","mode":"video_generation","context_window":0,"max_output_tokens":0,"pricing":{"input":"0","output":"0","output_video_per_second":"0.1","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.086"},{"resolution":"1080p","price":"0.15"},{"price":"0.15"}]}},"capabilities":{"vision":false,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/videos"]},"released_at":"2026-03-27T00:00:00Z","is_deprecated":false,"aliases":["wan-2.6","wan-2.6-20260327"],"video_attributes":{"modes":["t2v","i2v"],"resolutions":["720p","1080p"],"default_resolution":"1080p","min_duration_seconds":2,"max_duration_seconds":15,"supports_audio":true,"aspect_ratios":["16:9","9:16","1:1"]},"provider_price":{"provider_type":"aliyun","pricing":{"input":"0","output":"0","output_video_per_second":"0.1","video_pricing":{"unit":"per_second","tiers":[{"resolution":"720p","price":"0.086"},{"resolution":"1080p","price":"0.15"},{"price":"0.15"}]}},"is_override":false}},{"id":"z-ai/glm-5.1","canonical_slug":"glm-5.1","display_name":"Z.ai: GLM 5.1","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":200000,"max_output_tokens":128000,"pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["zai","aliyun","alicloud"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-03-27T00:00:00Z","is_deprecated":false,"aliases":["glm-5.1"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.0000014","output":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"is_override":false}},{"id":"minimax/minimax-m2.7","canonical_slug":"minimax-m2.7-2026-03-18","display_name":"MiniMax: MiniMax M2.7","description":"M2.7 delivers outstanding performance in real-world software engineering, including end-to-end complete project delivery, log analysis and bug triaging, code security, machine learning, and more. On the benchmark SWE-Pro, M2.7 scores 56.22%, nearly matching the level of Opus. This capability also extends to end-to-end complete project delivery scenarios (VIBE-Pro 55.6%) and deep understanding of complex engineering systems on Terminal Bench 2 (57.0%).","icon":"Minimax","owned_by":"minimax","model_protocol":"openai","series":"minimax","mode":"chat","context_window":200000,"max_output_tokens":131000,"pricing":{"input":"0.0000003","output":"0.0000012","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["minimax"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-18T00:00:00Z","is_deprecated":false,"aliases":["minimax-m2.7"],"provider_price":{"provider_type":"minimax","pricing":{"input":"0.0000003","output":"0.0000012","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"is_override":false}},{"id":"minimax/minimax-m2.7-highspeed","canonical_slug":"minimax-m2.7-highspeed-2026-03-18","display_name":"MiniMax: MiniMax M2.7 Highspeed","description":"M2.7 highspeed: Same performance, faster, more agile","icon":"Minimax","owned_by":"minimax","model_protocol":"openai","series":"minimax","mode":"chat","context_window":200000,"max_output_tokens":131000,"pricing":{"input":"0.0000006","output":"0.0000024","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["minimax"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-18T00:00:00Z","is_deprecated":false,"aliases":["minimax-m2.7-highspeed"],"provider_price":{"provider_type":"minimax","pricing":{"input":"0.0000006","output":"0.0000024","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"is_override":false}},{"id":"openai/gpt-5.4-mini","canonical_slug":"gpt-5.4-mini-2026-03-17","display_name":"OpenAI: GPT-5.4 Mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":400000,"max_output_tokens":128000,"pricing":{"input":"0.00000075","output":"0.0000045","input_cache_read":"0.000000075","output_image":"0.000032","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-17T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.4-mini"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.00000075","output":"0.0000045","input_cache_read":"0.000000075","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"openai/gpt-5.4-nano","canonical_slug":"gpt-5.4-nano-2026-03-17","display_name":"OpenAI: GPT-5.4 Nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":400000,"max_output_tokens":128000,"pricing":{"input":"0.0000002","output":"0.00000125","input_cache_read":"0.00000002","output_image":"0.000032","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-17T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.4-nano"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.0000002","output":"0.00000125","input_cache_read":"0.00000002","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"z-ai/glm-5-turbo","canonical_slug":"glm-5-turbo","display_name":"Z.ai: GLM-5-Turbo","description":"GLM-5-Turbo is a foundation model deeply optimized for the OpenClaw scenario. It has been specifically optimized for the core requirements of OpenClaw tasks since the training phase, enhancing key capabilities such as tool invocation, command following, timed and persistent tasks, and long-chain execution.","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":200000,"max_output_tokens":128000,"pricing":{"input":"0.0000012","output":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["zai"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-03-16T00:00:00Z","is_deprecated":false,"aliases":["glm-5-turbo"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.0000012","output":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"is_override":false}},{"id":"google/gemini-embedding-2-preview","canonical_slug":"gemini-embedding-2-preview","display_name":"Google: Gemini Embedding 2 Preview","description":"Gemini Embeddings is a multimodal embedding technique that converts text, audio, video, and image data into numerical vectors that can be processed by machine learning algorithms, especially large models. These vector representations are designed to capture the semantic meaning and context of the data they represent.","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"embedding","context_window":8192,"max_output_tokens":8192,"pricing":{"input":"0.0000002","output":"0","image":"0.00000045","audio":"0.0000065","video":"0.000012"},"capabilities":{"vision":true,"function_calling":false,"reasoning":false,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":false},"supported_provider_types":["google_vertex"],"supported_protocols":["gemini"],"released_at":"2026-03-10T00:00:00Z","is_deprecated":false,"aliases":["gemini-embedding-2-preview"],"provider_price":null},{"id":"openai/gpt-5.4","canonical_slug":"gpt-5.4-2026-03-05","display_name":"OpenAI: GPT-5.4","description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.0000025","output":"0.000015","input_cache_read":"0.00000025","output_image":"0.000032","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["openai","azure_foundry"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-05T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.4"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.0000025","output":"0.000015","input_cache_read":"0.00000025","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"openai/gpt-5.4-pro","canonical_slug":"gpt-5.4-pro-2026-03-05","display_name":"OpenAI: GPT-5.4 Pro","description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":1050000,"max_output_tokens":128000,"pricing":{"input":"0.00003","output":"0.00018","output_image":"0.000032","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":false,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-03-05T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.4-pro"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.00003","output":"0.00018","output_image":"0.000032","web_search":"0.035"},"is_override":true}},{"id":"openai/gpt-5.3-codex","canonical_slug":"gpt-5.3-codex-2026-02-06","display_name":"OpenAI: GPT-5.3 Codex","description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills.","icon":"OpenAI","owned_by":"azure","model_protocol":"openai","series":"gpt","mode":"chat","context_window":512000,"max_output_tokens":128000,"pricing":{"input":"0.00000175","output":"0.000014","input_cache_read":"0.00000018","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":false},"supported_provider_types":["azure_foundry","openai"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-25T00:00:00Z","is_deprecated":false,"aliases":["gpt-5.3-codex"],"provider_price":{"provider_type":"azure_foundry","pricing":{"input":"0.00000175","output":"0.000014","input_cache_read":"0.00000018","web_search":"0.035"},"is_override":true}},{"id":"qwen/qwen3.5-122b-a10b","canonical_slug":"qwen3.5-122b-a10b","display_name":"Qwen: Qwen3.5 122B A10B","description":"Qwen3.5系列122B-A10B原生视觉语言模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。该模型的综合表现仅次于Qwen3.5-397B-A17B，文本能力显著优于Qwen3-235B-2507，视觉能力优于Qwen3-VL-235B。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.00000029","output":"0.00000229","input_cache_read":"0.00000029","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-23T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-122b-a10b","bailian/qwen3.5-122b-a10b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000029","output":"0.00000229","input_cache_read":"0.00000029","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.5-27b","canonical_slug":"qwen3.5-27b","display_name":"Qwen: Qwen3.5 27B","description":"Qwen3.5系列27B原生视觉语言Dense模型，融合了线性注意力机制；响应速度快，兼具推理速度和性能。该模型的综合能力接近于Qwen3.5-122B-A10B。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.00000029","output":"0.00000205","input_cache_read":"0.00000029","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-23T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-27b","bailian/qwen3.5-27b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000029","output":"0.00000205","input_cache_read":"0.00000029","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.5-35b-a3b","canonical_slug":"qwen3.5-35b-a3b","display_name":"Qwen: Qwen3.5 35B A3B","description":"Qwen3.5系列35B-A3B原生视觉语言模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。该模型的综合表现接近于Qwen3.5-27B。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.00000029","output":"0.00000183","input_cache_read":"0.00000029","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-23T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-35b-a3b","bailian/qwen3.5-35b-a3b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000029","output":"0.00000183","input_cache_read":"0.00000029","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.5-397b-a17b","canonical_slug":"qwen3.5-397b-a17b","display_name":"Qwen: Qwen3.5 397B A17B","description":"Qwen3.5系列397B-A17B原生视觉语言模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。在语言理解、逻辑推理、代码生成、智能体任务、图像理解、视频理解、图形用户界面（GUI）等多种任务中，均展现出与当前顶尖前沿模型相媲美的卓越性能。具备强大的代码生成与智能体能力，对于各类智能体场景具有良好的泛化性。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.00000055","output":"0.0000035","input_cache_read":"0.00000055","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-23T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-397b-a17b","bailian/qwen3.5-397b-a17b"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.00000055","output":"0.0000035","input_cache_read":"0.00000055","web_search":"0.01"},"is_override":false}},{"id":"qwen/qwen3.5-flash","canonical_slug":"qwen3.5-flash-2026-02-23","display_name":"Qwen: Qwen3.5 Flash","description":"Qwen3.5原生视觉语言系列Flash模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。模型效果在纯文本与多模态方面相较3系列均实现飞跃式进步；响应速度快，兼具推理速度和性能。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1000000,"max_output_tokens":64000,"pricing":{"input":"0.0000001","output":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["aliyun","alicloud"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-23T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-flash","bailian/qwen3.5-flash"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000001","output":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"is_override":false}},{"id":"google/gemini-3.1-pro-preview","canonical_slug":"gemini-3.1-pro-preview","display_name":"Google: Gemini 3.1 Pro Preview","description":"Gemini 3.1 Pro is the next generation in the Gemini series of models, a suite of highly-capable, natively multimodal, reasoning models. Gemini 3 Pro is now Google’s most advanced model for complex tasks, and can comprehend vast datasets, challenging problems from different information sources, including text, audio, images, video, and entire code repositories","icon":"Gemini","owned_by":"google","model_protocol":"gemini","series":"gemini","mode":"chat","context_window":1048576,"max_output_tokens":65536,"pricing":{"input":"0.000002","output":"0.000012","audio":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.0000045","input_cached_audio":"0.0000002","web_search":"0.014"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":true,"video_input":true,"pdf_input":true},"supported_provider_types":["google_vertex"],"supported_protocols":["openai","gemini"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-19T00:00:00Z","is_deprecated":false,"aliases":["gemini-3.1-pro-preview"],"provider_price":null},{"id":"qwen/qwen3-coder-next","canonical_slug":"qwen3-coder-next-2026-02-19","display_name":"Qwen3 Coder Next","description":"Qwen3系列新一代代码生成模型，效果接近Qwen3-Coder-Plus兼具更优性能。模型重点优化仓库级别理解、支持多轮工具交互、提升对于agentic coding类工具的适配能力。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":256000,"max_output_tokens":64000,"pricing":{"input":"0.0000002","output":"0.0000015"},"capabilities":{"vision":false,"function_calling":false,"reasoning":true,"prompt_caching":false,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["alicloud","aliyun"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-19T00:00:00Z","is_deprecated":false,"aliases":["qwen3-coder-next","bailian/qwen3-coder-next"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000002","output":"0.0000015"},"is_override":false}},{"id":"anthropic/claude-sonnet-4.6","canonical_slug":"claude-sonnet-4-6-20260217","display_name":"Anthropic: Claude Sonnet 4.6","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","icon":"Claude","owned_by":"bedrock","model_protocol":"anthropic","series":"claude","mode":"chat","context_window":1000000,"max_output_tokens":128000,"pricing":{"input":"0.000003","output":"0.000015","input_cache_read":"0.0000003","input_cache_write_5m":"0.00000375","input_cache_write_1h":"0.000006","web_search":"0.015"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":true},"supported_provider_types":["aws_bedrock"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-17T00:00:00Z","is_deprecated":false,"aliases":["claude-sonnet-4.6","claude-sonnet-4-6","claude-sonnet-4-6-20260217"],"provider_price":null},{"id":"qwen/qwen3.5-plus","canonical_slug":"qwen3.5-plus-2026-02-15","display_name":"Qwen3.5 Plus","description":"Qwen3.5原生视觉语言系列Plus模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。在多项任务评测中，3.5系列均展现出与当前顶尖前沿模型相媲美的卓越性能，模型效果在纯文本与多模态方面相较3系列均实现飞跃式进步。","icon":"Qwen","owned_by":"dashscope","model_protocol":"openai","series":"qwen","mode":"chat","context_window":1000000,"max_output_tokens":64000,"pricing":{"input":"0.0000004","output":"0.0000024","input_cache_read":"0.00000004","input_cache_write":"0.0000004","web_search":"0.01"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["alicloud","aliyun"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-16T00:00:00Z","is_deprecated":false,"aliases":["qwen3.5-plus","bailian/qwen3.5-plus"],"provider_price":{"provider_type":"aliyun","pricing":{"input":"0.0000004","output":"0.0000024","input_cache_read":"0.00000004","input_cache_write":"0.0000004","web_search":"0.01"},"is_override":false}},{"id":"volcengine/doubao-seed-2.0-code","canonical_slug":"doubao-seed-2-0-code-preview-260215","display_name":"Doubao Seed 2.0 Code","description":"Doubao-Seed-2.0-Code 面向企业级编程需求优化，在 Seed 2.0 优秀的 Agent、VLM 能力基础上，特别增强了代码能力，不仅前端能力表现出众，也对企业常见的多语言编码需求做了特别优化，适合接入各种 AI 编程工具使用。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":128000,"pricing":{"input":"0.00000067","output":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-14T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.0-code","doubao-seed-2-0-code-preview-260215"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.00000067","output":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"is_override":false}},{"id":"volcengine/doubao-seed-2.0-lite","canonical_slug":"doubao-seed-2-0-lite-260215","display_name":"Doubao Seed 2.0 Lite","description":"Doubao-Seed-2.0-lite 是面向高频企业场景兼顾性能与成本的均衡型模型，综合能力超越上一代Doubao-Seed-1.8。胜任非结构化信息处理、内容创作、搜索推荐、数据分析等生产型工作，支持长上下文、多源信息融合、多步指令执行与高保真结构化输出。在保障稳定效果的同时显著优化成本。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":32000,"pricing":{"input":"0.00000013","output":"0.00000076","input_cache_read":"0.00000003","input_cache_write":"0.0000000024"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-14T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.0-lite","doubao-seed-2-0-lite-260215"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.00000013","output":"0.00000076","input_cache_read":"0.00000003","input_cache_write":"0.0000000024"},"is_override":false}},{"id":"volcengine/doubao-seed-2.0-mini","canonical_slug":"doubao-seed-2-0-mini-260215","display_name":"Doubao Seed 2.0 Mini","description":"Doubao-Seed-2.0-mini 面向低时延、高并发与成本敏感场景，强调快速响应与灵活推理部署。模型效果与Doubao-Seed-1.6相当。支持256k上下文、4档思考长度和多模态理解，适合成本和速度优先的轻量级任务。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":32000,"pricing":{"input":"0.00000006","output":"0.00000056","input_cache_read":"0.00000002","input_cache_write":"0.0000000024"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-14T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.0-mini","doubao-seed-2-0-mini-260215"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.00000006","output":"0.00000056","input_cache_read":"0.00000002","input_cache_write":"0.0000000024"},"is_override":false}},{"id":"volcengine/doubao-seed-2.0-pro","canonical_slug":"doubao-seed-2-0-pro-260215","display_name":"Doubao Seed 2.0 Pro","description":"Doubao-Seed-2.0-pro是旗舰级全能通用模型，面向 Agent 时代的复杂推理与长链路任务执行场景。强调多模态理解、长上下文推理、结构化生成与工具增强执行。复杂指令与多约束执行能力突出，可稳定应对多步复杂规划、复杂图文推理、视频内容理解与高难度分析等场景。","icon":"Doubao","owned_by":"volcengine","model_protocol":"openai","series":"doubao","mode":"chat","context_window":256000,"max_output_tokens":128000,"pricing":{"input":"0.00000067","output":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"capabilities":{"vision":true,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":false,"web_fetch":false,"audio_input":false,"video_input":true,"pdf_input":false},"supported_provider_types":["volcengine"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-14T00:00:00Z","is_deprecated":false,"aliases":["doubao-seed-2.0-pro","doubao-seed-2-0-pro-260215"],"provider_price":{"provider_type":"volcengine","pricing":{"input":"0.00000067","output":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"is_override":false}},{"id":"minimax/minimax-m2.5","canonical_slug":"minimax-m2.5-2026-02-12","display_name":"MiniMax: MiniMax M2.5","description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","icon":"Minimax","owned_by":"minimax","model_protocol":"openai","series":"minimax","mode":"chat","context_window":200000,"max_output_tokens":131000,"pricing":{"input":"0.0000003","output":"0.0000012","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["aliyun"],"supported_protocols":["openai","anthropic"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-12T00:00:00Z","is_deprecated":false,"aliases":["minimax-m2.5"],"provider_price":null},{"id":"minimax/minimax-m2.5-lightning","canonical_slug":"minimax-m2.5-lightning-2026-02-12","display_name":"MiniMax: MiniMax M2.5 Lightning","description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","icon":"Minimax","owned_by":"minimax","model_protocol":"openai","series":"minimax","mode":"chat","context_window":200000,"max_output_tokens":131000,"pricing":{"input":"0.0000003","output":"0.0000024","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["minimax"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions","/v1/responses"]},"released_at":"2026-02-12T00:00:00Z","is_deprecated":false,"aliases":["minimax-m2.5-lightning"],"provider_price":{"provider_type":"minimax","pricing":{"input":"0.0000003","output":"0.0000024","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"is_override":false}},{"id":"z-ai/glm-5","canonical_slug":"glm-5","display_name":"Z.ai: GLM-5","description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","icon":"Zhipu","owned_by":"zhipu","model_protocol":"openai","series":"glm","mode":"chat","context_window":200000,"max_output_tokens":128000,"pricing":{"input":"0.000001","output":"0.0000032","input_cache_read":"0.0000002","web_search":"0.01"},"capabilities":{"vision":false,"function_calling":true,"reasoning":true,"prompt_caching":true,"web_search":true,"web_fetch":false,"audio_input":false,"video_input":false,"pdf_input":false},"supported_provider_types":["zai","aliyun"],"supported_protocols":["anthropic","openai"],"supported_protocol_endpoints":{"openai":["/v1/chat/completions"]},"released_at":"2026-02-11T00:00:00Z","is_deprecated":false,"aliases":["glm-5"],"provider_price":{"provider_type":"zai","pricing":{"input":"0.000001","output":"0.0000032","input_cache_read":"0.0000002","web_search":"0.01"},"is_override":false}}],"total":148,"provider_types":["google_vertex","zai","byteplus","aliyun","alicloud","aws_bedrock","volcengine","grok","minimax","moonshot","anthropic","deepseek","azure_foundry","openai","novita"]}