{"object":"list","data":[{"id":"alibaba/happyhorse-1.0","object":"model","created":1782259200,"owned_by":"openai","canonical_slug":"alibaba/happyhorse-1.0-20260624","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"happyhorse","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.13"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"alibaba/happyhorse-1.1","object":"model","created":1782259200,"owned_by":"openai","canonical_slug":"alibaba/happyhorse-1.1-20260624","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。","context_length":0,"architecture":{"modality":"text+image-\u003evideo","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"happyhorse","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.13"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"alibaba/wan-2.6","object":"model","created":1774569600,"owned_by":"openai","canonical_slug":"alibaba/wan-2.6-20260327","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。","context_length":0,"architecture":{"modality":"text+image-\u003evideo","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"wan","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.1"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"alibaba/wan-2.7","object":"model","created":1776124800,"owned_by":"openai","canonical_slug":"alibaba/wan-2.7-20260414","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"wan","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.1"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"alibaba/wan-3.0","object":"model","created":1787529600,"owned_by":"openai","canonical_slug":"alibaba/wan-3.0-20260824","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"wan","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.054"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"alibaba/wan-3.0-prime","object":"model","created":1787529600,"owned_by":"openai","canonical_slug":"alibaba/wan-3.0-prime-20260824","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"wan","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.064"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"anthropic/claude-fable-5.2","object":"model","created":1794182400,"owned_by":"bedrock","canonical_slug":"claude-fable-5-2","name":"Anthropic: Claude Fable 5.2","description":"Claude Fable 5.2；adaptive thinking 恒开，原生不支持强制工具选择。","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000002","input_cache_write_5m":"0.00001","input_cache_write_1h":"0.000016","web_search":"0.01"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["claude-fable-5-2","claude-fable-5.2"]},{"id":"anthropic/claude-sonnet-4.6","object":"model","created":1771286400,"owned_by":"bedrock","canonical_slug":"claude-sonnet-4-6-20260217","name":"Anthropic: Claude Sonnet 4.6","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write_5m":"0.00000375","input_cache_write_1h":"0.000006","web_search":"0.015"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["claude-sonnet-4.6","claude-sonnet-4-6","claude-sonnet-4-6-20260217"]},{"id":"anthropic/claude-sonnet-5.5","object":"model","created":1790553600,"owned_by":"bedrock","canonical_slug":"claude-sonnet-5-5","name":"Anthropic: Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-tier model, offering a balance of speed and intelligence for coding, reasoning, and agentic workloads. It supports text, image, and file inputs with text output, with a 1M-token context window and up to 128K output tokens, at a lower per-token price than Claude Opus 5.5.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write_5m":"0.0000025","input_cache_write_1h":"0.000004","web_search":"0.015"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["claude-sonnet-5-5","claude-sonnet-5.5","claude-sonnet-latest","anthropic/claude-sonnet-latest"]},{"id":"bytedance/seedance-2.0","object":"model","created":1776124800,"owned_by":"openai","canonical_slug":"bytedance/seedance-2.0-20260414","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"seedance","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.07"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"bytedance/seedance-2.0-fast","object":"model","created":1776124800,"owned_by":"openai","canonical_slug":"bytedance/seedance-2.0-fast-20260414","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"seedance","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.06"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"bytedance/seedance-2.0-mini","object":"model","created":1781481600,"owned_by":"openai","canonical_slug":"doubao-seedance-2-0-mini-260615","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"seedance","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.04"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"bytedance/seedance-2.5","object":"model","created":1786060800,"owned_by":"openai","canonical_slug":"bytedance/seedance-2.5-20260807","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"seedance","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.11"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"],"reference_video_min_pixels":407696}},{"id":"deepseek/deepseek-v4-flash-0423","object":"model","created":1776902400,"owned_by":"deepseek","canonical_slug":"deepseek-v4-flash-20260423","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.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.00000019","completion":"0.00000051","input_cache_read":"0.000000028","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4-flash-0423","deepseek-v4-flash-20260423","deepseek-v4-flash-20260424"]},{"id":"deepseek/deepseek-v4-flash-0731","object":"model","created":1785456000,"owned_by":"deepseek","canonical_slug":"deepseek-v4-flash-20260731","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.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4-flash","deepseek-v4-flash-0731","deepseek-v4-flash-20260731"]},{"id":"deepseek/deepseek-v4-pro-0423","object":"model","created":1776902400,"owned_by":"deepseek","canonical_slug":"deepseek-v4-pro-20260423","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.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.00000174","completion":"0.00000348","input_cache_read":"0.000000145","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4-pro-0423","deepseek-v4-pro-20260423","deepseek-v4-pro-20260424"]},{"id":"deepseek/deepseek-v4-pro-0813","object":"model","created":1786579200,"owned_by":"deepseek","canonical_slug":"deepseek-v4-pro-20260813","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.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.00000132","completion":"0.00000396","input_cache_read":"0.000000044"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4-pro","deepseek-v4-pro-0813","deepseek-v4-pro-20260813","deepseek-pro-latest","deepseek/deepseek-pro-latest"]},{"id":"deepseek/deepseek-v4.1-flash","object":"model","created":1788998400,"owned_by":"deepseek","canonical_slug":"deepseek-v4.1-flash","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.","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4.1-flash","deepseek-flash","deepseek-flash-latest","deepseek/deepseek-flash-latest"]},{"id":"deepseek/deepseek-v4.1-flash-1017","object":"model","created":1792195200,"owned_by":"deepseek","canonical_slug":"deepseek-v4.1-flash-20261017","name":"DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 dated version of DeepSeek V4.1 Flash, served through Volcengine with the pinned upstream model ID deepseek-v4-1-flash-261017. It supports vision, reasoning, tool calls, JSON output and prompt caching, with a 1M-token context window and up to 384K output tokens. Available through Ofox via OpenAI and Anthropic protocols.","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["deepseek-v4.1-flash-1017","deepseek-v4.1-flash-20261017"]},{"id":"elevenlabs/eleven_v4","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"eleven_v4","name":"ElevenLabs Eleven v4","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_text_per_character":"0.00008"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","provider_options"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["eleven_v4"]},{"id":"elevenlabs/scribe_v2","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"scribe_v2","name":"ElevenLabs Scribe v2","context_length":0,"architecture":{"modality":"audio-\u003etext","input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_audio_per_second":"0.0000611111"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["file","language","response_format","provider_options"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/transcriptions"],"aliases":["scribe_v2"]},{"id":"google/gemini-2.5-flash","object":"model","created":1750118400,"owned_by":"google","canonical_slug":"gemini-2.5-flash-preview-05-20","name":"Google: Gemini 2.5 Flash","description":"Fast and cost-effective Gemini 2.5 with 1M context. Features toggleable reasoning capabilities and full multimodal support at significantly lower cost than Pro.","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","audio":"0.000001","input_cache_read":"0.00000003","input_cache_write":"0.000001","input_cached_image":"0.00000003","input_cached_audio":"0.0000001","input_cached_video":"0.00000003","web_search":"0.035"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-2.5-flash"]},{"id":"google/gemini-2.5-flash-image","object":"model","created":1759363200,"owned_by":"google","canonical_slug":"gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations. ","context_length":32000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","output_image":"0.00003"},"top_provider":{"context_length":32000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"],"aliases":["gemini-2.5-flash-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]}},{"id":"google/gemini-2.5-flash-lite","object":"model","created":1753142400,"owned_by":"google","canonical_slug":"gemini-2.5-flash-lite-preview-06-17","name":"Google: Gemini 2.5 Flash Lite","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, [thinking] (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.","context_length":1048576,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","audio":"0.0000003","input_cache_read":"0.00000001","input_cache_write":"0.000001","input_cached_image":"0.00000001","input_cached_audio":"0.00000003","input_cached_video":"0.00000001","web_search":"0.035"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-2.5-flash-lite"]},{"id":"google/gemini-2.5-flash-lite-preview-tts","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"gemini-2.5-flash-lite-preview-tts","name":"Gemini 2.5 Flash Lite Preview TTS","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.00001","output_audio":"0.00001"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","instructions"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["gemini-2.5-flash-lite-preview-tts"]},{"id":"google/gemini-2.5-flash-tts","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"gemini-2.5-flash-tts","name":"Gemini 2.5 Flash TTS","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.00001","output_audio":"0.00001"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","instructions"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["gemini-2.5-flash-tts"]},{"id":"google/gemini-2.5-pro","object":"model","created":1750118400,"owned_by":"google","canonical_slug":"gemini-2.5-pro-preview-05-06","name":"Google: Gemini 2.5 Pro","description":"Google's flagship Gemini model with 1M context, thinking/reasoning capabilities, and full multimodal support (text, image, video, audio). Excels at complex analysis and creative tasks.","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","audio":"0.00000125","input_cache_read":"0.000000125","input_cache_write":"0.0000045","input_cached_image":"0.000000125","input_cached_audio":"0.000000125","input_cached_video":"0.000000125","web_search":"0.035"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-2.5-pro"]},{"id":"google/gemini-2.5-pro-tts","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"gemini-2.5-pro-tts","name":"Gemini 2.5 Pro TTS","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.00002","output_audio":"0.00002"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","instructions"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["gemini-2.5-pro-tts"]},{"id":"google/gemini-3-flash-preview","object":"model","created":1765929600,"owned_by":"google","canonical_slug":"gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","audio":"0.000001","input_cache_read":"0.00000005","input_cache_write":"0.000001","input_cached_image":"0.00000005","input_cached_audio":"0.0000001","input_cached_video":"0.00000005","web_search":"0.014"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3-flash-preview"]},{"id":"google/gemini-3-pro-image","object":"model","created":1781740800,"owned_by":"google","canonical_slug":"gemini-3-pro-image","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.","context_length":66000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","output_image":"0.00012","web_search":"0.014"},"top_provider":{"context_length":66000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"],"aliases":["gemini-3-pro-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]}},{"id":"google/gemini-3.1-flash-image","object":"model","created":1781740800,"owned_by":"google","canonical_slug":"gemini-3.1-flash-image","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.","context_length":131000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000003","output_image":"0.00006","web_search":"0.014"},"top_provider":{"context_length":131000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"],"aliases":["gemini-3.1-flash-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]}},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1778112000,"owned_by":"google","canonical_slug":"gemini-3.1-flash-lite","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.","context_length":1000000,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","audio":"0.0000005","input_cache_read":"0.000000025","input_cache_write":"0.000001","input_cache_write_1h":"0.000001","input_cached_image":"0.000000025","input_cached_audio":"0.00000005","input_cached_video":"0.000000025","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.1-flash-lite"]},{"id":"google/gemini-3.1-flash-lite-image","object":"model","created":1782777600,"owned_by":"google","canonical_slug":"gemini-3.1-flash-lite-image","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.","context_length":66000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","output_image":"0.00003"},"top_provider":{"context_length":66000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"],"aliases":["gemini-3.1-flash-lite-image"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]}},{"id":"google/gemini-3.1-pro-preview","object":"model","created":1771459200,"owned_by":"google","canonical_slug":"gemini-3.1-pro-preview","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","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","audio":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.0000045","input_cached_image":"0.0000002","input_cached_audio":"0.0000002","input_cached_video":"0.0000002","web_search":"0.014"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.1-pro-preview"]},{"id":"google/gemini-3.5-flash","object":"model","created":1779235200,"owned_by":"google","canonical_slug":"gemini-3.5-flash","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.","context_length":1000000,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.000009","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cached_image":"0.00000015","input_cached_audio":"0.00000015","input_cached_video":"0.00000015","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.5-flash"]},{"id":"google/gemini-3.5-flash-lite","object":"model","created":1784592000,"owned_by":"google","canonical_slug":"gemini-3.5-flash-lite","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.","context_length":1000000,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000025","audio":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_image":"0.00000003","input_cached_audio":"0.00000003","input_cached_video":"0.00000003","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.5-flash-lite"]},{"id":"google/gemini-3.7-flash","object":"model","created":1786579200,"owned_by":"google","canonical_slug":"gemini-3.7-flash","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.","context_length":1000000,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_image":"0.00000015","input_cached_audio":"0.00000015","input_cached_video":"0.00000015","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.7-flash"]},{"id":"google/gemini-3.8-flash","object":"model","created":1788307200,"owned_by":"google","canonical_slug":"gemini-3.8-flash","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.","context_length":1000000,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","audio":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.000000083","input_cache_write_1h":"0.000001","input_cached_image":"0.00000015","input_cached_audio":"0.00000015","input_cached_video":"0.00000015","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-3.8-flash","gemini-flash-latest","google/gemini-flash-latest"]},{"id":"google/gemini-3.8-flash-lite-tts","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"gemini-3.8-flash-lite-tts","name":"Gemini 3.8 Flash-Lite TTS","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000006","output_audio":"0.000006"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","instructions"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["gemini-3.8-flash-lite-tts"]},{"id":"google/gemini-3.8-flash-tts","object":"model","created":1791446044,"owned_by":"openai","canonical_slug":"gemini-3.8-flash-tts","name":"Gemini 3.8 Flash TTS","context_length":0,"architecture":{"modality":"text-\u003eaudio","input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000009","output_audio":"0.000009"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","voice","response_format","speed","stream_format","language_code","instructions"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/speech"],"aliases":["gemini-3.8-flash-tts"]},{"id":"google/gemini-4-argon","object":"model","created":1791849600,"owned_by":"google","canonical_slug":"gemini-4-argon","name":"Google: Gemini 4 Argon","description":"Gemini 4 Argon is Google's flagship reasoning model for coding and agentic workflows. Supports text, image, audio, video and PDF input, tool calling and structured output. Input, thinking and output share a 1,048,576-token window. Thinking levels: low, medium (default), high. Implicit caching only. Standard streaming output up to 65,536 tokens; direct non-streaming REST up to 32,768. Long decode requires continuation support and is not enabled by this catalog entry.","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","audio":"0.000004","input_cache_read":"0.0000002","input_cached_image":"0.0000002","input_cached_audio":"0.0000002","input_cached_video":"0.0000002","web_search":"0.014"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-4-argon"]},{"id":"google/gemini-4-hydrogen","object":"model","created":1794441600,"owned_by":"google","canonical_slug":"gemini-4-hydrogen","name":"Google: Gemini 4 Hydrogen","description":"Gemini 4 Hydrogen is Google’s fast reasoning model for coding, agent workflows and multimodal analysis. It supports tool calling and structured output, with a shared 1,048,576-token input, reasoning and output window and up to 65,536 output tokens per foreground segment. Thinking levels are low, medium, high (default) and xhigh. It supports implicit context caching. This short-term GA release is subject to a minimum 45-day retirement notice.","context_length":1048576,"architecture":{"modality":"text+image+audio+file-\u003etext","input_modalities":["text","image","audio","file"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","audio":"0.0000015","input_cache_read":"0.000000075","input_cached_image":"0.000000075","input_cached_audio":"0.000000075","input_cached_video":"0.000000075","web_search":"0.014"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gemini-4-hydrogen"]},{"id":"google/gemini-nano-banana-2.1","object":"model","created":1791244800,"owned_by":"google","canonical_slug":"gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","description":"Nano Banana 2.1 is Google's GA image generation and editing model, the successor to Nano Banana 2 (Gemini 3.1 Flash Image). It supports up to 14 reference images per prompt and output at 1K, 2K, or 4K resolution, with aspect ratios from 1:8 to 8:1. It handles text-to-image generation, multi-turn editing, and can ground generations with Google Search.","context_length":131072,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.0000075","output_image":"0.00003","web_search":"0.014"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/images/edits","/v1/images/generations"],"aliases":["gemini-nano-banana-2.1"],"image_attributes":{"supported_params":["prompt","output_format","stream","user"]}},{"id":"microsoft/mai-image-2.5","object":"model","created":1780358400,"owned_by":"azure","canonical_slug":"mai-image-2.5-2026-06-02","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.","context_length":4100,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000047","image":"0.000008","output_image":"0.000047"},"top_provider":{"context_length":4100,"max_completion_tokens":1000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["mai-image-2.5","mai-image-2.5-2026-06-02","mai-image-2.5-20260602"]},{"id":"microsoft/mai-image-2.5-flash","object":"model","created":1780358400,"owned_by":"azure","canonical_slug":"mai-image-2.5-flash-2026-06-02","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.","context_length":4100,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000026","image":"0.00000175","output_image":"0.0000195"},"top_provider":{"context_length":4100,"max_completion_tokens":1000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["mai-image-2.5-flash","mai-image-2.5-flash-2026-06-02","mai-image-2.5-flash-20260602"]},{"id":"microsoft/mai-image-2.5-pro","object":"model","created":1781827200,"owned_by":"azure","canonical_slug":"mai-image-2.5-pro-2026-06-19","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.","context_length":4100,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"unknown","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.000106","image":"0.000008","output_image":"0.000106"},"top_provider":{"context_length":4100,"max_completion_tokens":1000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["mai-image-2.5-pro","mai-image-2.5-pro-2026-06-19","mai-image-2.5-pro-20260619"]},{"id":"minimax/hailuo-3","object":"model","created":1785456000,"owned_by":"openai","canonical_slug":"minimax/hailuo-3-20260731","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）。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"hailuo","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.08"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"minimax/hailuo-3-max","object":"model","created":1785456000,"owned_by":"openai","canonical_slug":"minimax/hailuo-3-max-20260731","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。","context_length":0,"architecture":{"modality":"text+image+video-\u003evideo","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"hailuo","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_video_per_second":"0.05"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","duration","resolution","aspect_ratio","size","generate_audio","seed","frame_images","input_references","callback_url","provider"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/videos"],"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"]}},{"id":"minimax/minimax-m2.5","object":"model","created":1770854400,"owned_by":"minimax","canonical_slug":"minimax-m2.5-2026-02-12","name":"MiniMax: MiniMax M2.5","description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"minimax","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"top_provider":{"context_length":200000,"max_completion_tokens":131000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["minimax-m2.5"]},{"id":"minimax/minimax-m2.7","object":"model","created":1773792000,"owned_by":"minimax","canonical_slug":"minimax-m2.7-2026-03-18","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%).","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"minimax","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"top_provider":{"context_length":200000,"max_completion_tokens":131000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["minimax-m2.7"]},{"id":"minimax/minimax-m3","object":"model","created":1780272000,"owned_by":"minimax","canonical_slug":"minimax-m3-2026-05-31","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.","context_length":1131000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"minimax","instruct_type":null},"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000012"},"top_provider":{"context_length":1131000,"max_completion_tokens":131000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["minimax-m3"]},{"id":"moonshotai/kimi-k2.6","object":"model","created":1776729600,"owned_by":"MoonshotAI","canonical_slug":"kimi-k2.6-20260421","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。","context_length":262144,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000016","web_search":"0.005"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["kimi-k2.6","kimi-k2.6-20260421"]},{"id":"moonshotai/kimi-k2.7-code","object":"model","created":1781222400,"owned_by":"MoonshotAI","canonical_slug":"kimi-k2.7-code-20260612","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)。","context_length":262144,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000019","web_search":"0.005"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["kimi-k2.7-code"]},{"id":"moonshotai/kimi-k2.7-code-highspeed","object":"model","created":1781222400,"owned_by":"MoonshotAI","canonical_slug":"kimi-k2.7-code-highspeed-20260612","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)。","context_length":262144,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"prompt":"0.0000019","completion":"0.000008","input_cache_read":"0.00000038","web_search":"0.005"},"top_provider":{"context_length":262144,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["kimi-k2.7-code-highspeed"]},{"id":"moonshotai/kimi-k3","object":"model","created":1784160000,"owned_by":"MoonshotAI","canonical_slug":"kimi-k3-20260716","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)。","context_length":1048576,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","web_search":"0.005"},"top_provider":{"context_length":1048576,"max_completion_tokens":1048576,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["kimi-k3"]},{"id":"moonshotai/kimi-k3.1-pro","object":"model","created":1792800000,"owned_by":"MoonshotAI","canonical_slug":"kimi-k3.1-pro-20261024","name":"MoonshotAI: Kimi K3.1 Pro","description":"Kimi K3.1 Pro is Moonshot AI’s flagship model for long-context coding, agent workflows and complex reasoning. Served through Volcengine Beijing with the pinned kimi-k3-1-pro-261024 version. Supports text and image input, tool calling, reasoning and prompt caching. Context: 1,048,576 tokens; output: up to 131,072 tokens. OpenAI and Anthropic compatible APIs. Images must be sent as base64 data URLs.","context_length":1048576,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000011","input_cache_read":"0.0000002","web_search":"0.005"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["kimi-k3.1-pro","kimi-k3-1-pro"]},{"id":"openai/gpt-4o","object":"model","created":1715558400,"owned_by":"azure","canonical_slug":"gpt-4o-2024-11-20","name":"GPT-4o","description":"OpenAI's flagship multimodal model supporting text and image inputs with text outputs. Maintains GPT-4 Turbo intelligence at 2x speed and 50% lower cost. Optimized for complex reasoning, coding, and visual understanding tasks.","context_length":128000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","web_search":"0.014"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["gpt-4o"]},{"id":"openai/gpt-4o-mini-transcribe","object":"model","created":1765756800,"owned_by":"azure","canonical_slug":"gpt-4o-mini-transcribe-20251215","name":"OpenAI: GPT 4o Mini Transcribe","description":"GPT-4o Mini Transcribe is OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o Mini audio capabilities. It's priced per token (input and output), making it suitable for high-volume transcription workflows that benefit from token-level billing transparency at a lower cost point.","context_length":128000,"architecture":{"modality":"audio-\u003etext","input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.000005","audio":"0.000003","web_search":"0.014"},"top_provider":{"context_length":128000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["file","language","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/transcriptions"],"aliases":["gpt-4o-mini-transcribe","gpt-4o-mini-transcribe-20251215"]},{"id":"openai/gpt-4o-transcribe-diarize","object":"model","created":1760486400,"owned_by":"azure","canonical_slug":"gpt-4o-transcribe-20250320","name":"OpenAI: GPT 4o Transcribe Diarize","description":"GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.","context_length":128000,"architecture":{"modality":"audio-\u003etext","input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.00001","audio":"0.000006","web_search":"0.014"},"top_provider":{"context_length":128000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["file","language","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/transcriptions"],"aliases":["gpt-4o-transcribe-diarize","gpt-4o-transcribe-20250320"]},{"id":"openai/gpt-5","object":"model","created":1754524800,"owned_by":"azure","canonical_slug":"gpt-5-2025-12-15","name":"GPT-5","description":"OpenAI's next-generation flagship model with 256K context window and advanced multimodal capabilities. Features enhanced reasoning, agentic workflows, and state-of-the-art performance across all benchmarks.","context_length":256000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.00000013","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":256000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5"]},{"id":"openai/gpt-5-mini","object":"model","created":1754524800,"owned_by":"azure","canonical_slug":"gpt-5-mini-2025-12-15","name":"GPT-5 Mini","description":"Cost-effective GPT-5 variant with 256K context. Balanced performance for everyday tasks while maintaining strong reasoning and vision capabilities at reduced cost.","context_length":256000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.000002","input_cache_read":"0.00000003","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":256000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5-mini"]},{"id":"openai/gpt-5-nano","object":"model","created":1754524800,"owned_by":"azure","canonical_slug":"gpt-5-nano-2025-12-15","name":"GPT-5 Nano","description":"Ultra-efficient GPT-5 variant optimized for maximum throughput at minimal cost. Features 128K context and low-latency design for high-volume automation tasks.","context_length":128000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000005","completion":"0.0000004","input_cache_read":"0.00000001","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5-nano"]},{"id":"openai/gpt-5.1","object":"model","created":1762992000,"owned_by":"azure","canonical_slug":"gpt-5.1-2026-01-08","name":"OpenAI: GPT-5.1","description":"OpenAI's enhanced GPT-5.1 model with improved reasoning and multimodal capabilities. Features 256K context with better instruction following and coding performance.","context_length":256000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.00000013","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.1"]},{"id":"openai/gpt-5.2","object":"model","created":1765411200,"owned_by":"azure","canonical_slug":"gpt-5.2-2026-01-10","name":"OpenAI: GPT-5.2","description":"OpenAI's latest GPT-5.2 model with 512K context window. Most advanced capabilities including enhanced reasoning, full multimodal support, and web search integration.","context_length":512000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.00000018","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":512000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.2"]},{"id":"openai/gpt-5.3-codex","object":"model","created":1771977600,"owned_by":"azure","canonical_slug":"gpt-5.3-codex-2026-02-06","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.","context_length":512000,"architecture":{"modality":"text+image+audio-\u003etext","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.00000018","web_search":"0.014"},"top_provider":{"context_length":512000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/responses"],"aliases":["gpt-5.3-codex"]},{"id":"openai/gpt-5.4","object":"model","created":1772668800,"owned_by":"azure","canonical_slug":"gpt-5.4-2026-03-05","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.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000025","completion":"0.000015","input_cache_read":"0.00000025","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.4"]},{"id":"openai/gpt-5.4-mini","object":"model","created":1773705600,"owned_by":"azure","canonical_slug":"gpt-5.4-mini-2026-03-17","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.","context_length":400000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000075","completion":"0.0000045","input_cache_read":"0.000000075","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.4-mini"]},{"id":"openai/gpt-5.4-nano","object":"model","created":1773705600,"owned_by":"azure","canonical_slug":"gpt-5.4-nano-2026-03-17","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.","context_length":400000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.00000125","input_cache_read":"0.00000002","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.4-nano"]},{"id":"openai/gpt-5.4-pro","object":"model","created":1772668800,"owned_by":"azure","canonical_slug":"gpt-5.4-pro-2026-03-05","name":"OpenAI: GPT-5.4 Pro","description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0.00018","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/responses"],"aliases":["gpt-5.4-pro"]},{"id":"openai/gpt-5.5","object":"model","created":1776988800,"owned_by":"azure","canonical_slug":"gpt-5.5-2026-04-25","name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","output_image":"0.000032","web_search":"0.014"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.5","gpt-5.5-2026-04-24"]},{"id":"openai/gpt-5.6-luna","object":"model","created":1783555200,"owned_by":"azure","canonical_slug":"gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","output_image":"0.000032","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.6-luna","gpt-5.6-luna-2026-07-09"]},{"id":"openai/gpt-5.6-sol","object":"model","created":1783555200,"owned_by":"azure","canonical_slug":"gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","output_image":"0.000032","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.6-sol","gpt-5.6-sol-2026-07-09"]},{"id":"openai/gpt-5.6-terra","object":"model","created":1783555200,"owned_by":"azure","canonical_slug":"gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","output_image":"0.000032","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-5.6-terra","gpt-5.6-terra-2026-07-09"]},{"id":"openai/gpt-6-astra","object":"model","created":1788480000,"owned_by":"openrouter","canonical_slug":"openai/gpt-6-astra-20260903","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.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-6-astra","gpt-6-astra-2026-09-03","gpt-astra-latest","openai/gpt-astra-latest"]},{"id":"openai/gpt-6-luna","object":"model","created":1790035200,"owned_by":"openrouter","canonical_slug":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","description":"GPT-6 Luna is the fastest and most cost-efficient model in OpenAI's GPT-6 family, built for high-volume, latency-sensitive workloads such as classification, extraction, and lightweight agents. It supports text and image inputs with text output, adjustable reasoning effort, a 1.05M-token context window, and up to 128K output tokens.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-6-luna","gpt-luna-latest","openai/gpt-luna-latest"]},{"id":"openai/gpt-6-sol","object":"model","created":1790035200,"owned_by":"openrouter","canonical_slug":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","description":"GPT-6 Sol is the balanced model in OpenAI's GPT-6 family, offering strong reasoning, coding, and agentic performance at a fraction of GPT-6 Astra's cost. It supports text and image inputs with text output, adjustable reasoning effort, a 1.05M-token context window, and up to 128K output tokens.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-6-sol"]},{"id":"openai/gpt-6.1-sol","object":"model","created":1790640000,"owned_by":"openrouter","canonical_slug":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","description":"GPT-6.1 Sol is OpenAI's balanced model for complex coding, computer use, and professional work. It offers near-Astra performance at lower cost, supports text and image inputs with text output, adjustable reasoning effort, a 1.05M-token context window, and up to 128K output tokens.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-6.1-sol","gpt-sol-latest","openai/gpt-sol-latest"]},{"id":"openai/gpt-6.1-terra","object":"model","created":1792972800,"owned_by":"openai","canonical_slug":"openai/gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","description":"GPT-6.1 Terra is a fast, efficient OpenAI model for visual reasoning, precise computer use, coding and natural writing. It supports text and image inputs, text output, adjustable reasoning, a 1,050,000-token context window and up to 128,000 output tokens. Tool calling uses the Responses API.","context_length":1050000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["gpt-6.1-terra"]},{"id":"openai/gpt-image-1.5","object":"model","created":1765843200,"owned_by":"azure","canonical_slug":"gpt-image-1.5-2025-12-16","name":"OpenAI: GPT Image 1.5","description":"GPT Image 1.5 is our latest image generation model, with better instruction following and adherence to prompts.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00001","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.000032"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","quality","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["gpt-image-1.5","gpt-image-1.5-2025-12-16","gpt-image-1.5-20251216"],"image_attributes":{"supported_params":["prompt","n","size","quality","output_format","stream","user"]}},{"id":"openai/gpt-image-2","object":"model","created":1776729600,"owned_by":"azure","canonical_slug":"gpt-image-2-2026-04-21","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.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","quality","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"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"]}},{"id":"openai/gpt-image-2.5-flare","object":"model","created":1788912000,"owned_by":"openai","canonical_slug":"gpt-image-2.5-flare","name":"OpenAI: GPT Image 2.5 Flare","description":"Fast, high-quality everyday image generation.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["gpt-image-2.5-flare"],"image_attributes":{"supported_params":["prompt","n","stream","user"]}},{"id":"openai/gpt-image-2.5-sunburst","object":"model","created":1788912000,"owned_by":"openai","canonical_slug":"gpt-image-2.5-sunburst","name":"OpenAI: GPT Image 2.5 Sunburst","description":"Our most capable model for image generation and editing.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["gpt-image-2.5-sunburst"],"image_attributes":{"supported_params":["prompt","n","stream","user"]}},{"id":"openai/gpt-image-2.6-flare","object":"model","created":1793750400,"owned_by":"openai","canonical_slug":"gpt-image-2.6-flare","name":"OpenAI: GPT Image 2.6 Flare","description":"Fast, high-quality everyday image generation.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["gpt-image-2.6-flare"],"image_attributes":{"supported_params":["prompt","n","stream","user"]}},{"id":"openai/gpt-image-2.6-sunburst","object":"model","created":1793750400,"owned_by":"openai","canonical_slug":"gpt-image-2.6-sunburst","name":"OpenAI: GPT Image 2.6 Sunburst","description":"Our most capable model for image generation and editing.","context_length":0,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.000005","completion":"0.00003","image":"0.000008","input_cache_read":"0.00000125","input_cached_image":"0.000002","output_image":"0.00003"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/edits","/v1/images/generations"],"aliases":["gpt-image-2.6-sunburst"],"image_attributes":{"supported_params":["prompt","n","stream","user"]}},{"id":"openai/gpt-transcribe","object":"model","created":1785196800,"owned_by":"azure","canonical_slug":"gpt-transcribe-20260728","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.","context_length":128000,"architecture":{"modality":"audio-\u003etext","input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_audio_per_second":"0.000075"},"top_provider":{"context_length":128000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["file","language","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/audio/transcriptions"],"aliases":["gpt-transcribe","gpt-transcribe-20260728"]},{"id":"openai/text-embedding-3-large","object":"model","created":1761782400,"owned_by":"azure","canonical_slug":"text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","context_length":8200,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0","web_search":"0.014"},"top_provider":{"context_length":8200,"max_completion_tokens":8200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/embeddings"],"aliases":["text-embedding-3-large"]},{"id":"openai/text-embedding-3-small","object":"model","created":1761782400,"owned_by":"azure","canonical_slug":"text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","context_length":8200,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"prompt":"0.00000002","completion":"0","web_search":"0.014"},"top_provider":{"context_length":8200,"max_completion_tokens":8200,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/embeddings"],"aliases":["text-embedding-3-small"]},{"id":"qwen/qwen-flash","object":"model","created":1753660800,"owned_by":"dashscope","canonical_slug":"qwen-flash","name":"Qwen Flash","description":"Alibaba Qwen Flash via Dashscope. Ultra-fast inference for latency-sensitive tasks. Lowest cost option in the Qwen family.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.000000022","completion":"0.00000022","input_cache_read":"0.0000000043","input_cache_write":"0.000000027","web_search":"0.01"},"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen-flash","bailian/qwen-flash"]},{"id":"qwen/qwen-image-3.0","object":"model","created":1785888000,"owned_by":"bailian","canonical_slug":"qwen-image-3.0","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。","context_length":100000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_image_per_num":"0.03"},"top_provider":{"context_length":100000,"max_completion_tokens":100000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/generations"],"aliases":["qwen-image-3.0","bailian/qwen-image-3.0"]},{"id":"qwen/qwen-image-3.0-pro","object":"model","created":1785888000,"owned_by":"bailian","canonical_slug":"qwen-image-3.0-pro","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。","context_length":100000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_image_per_num":"0.07"},"top_provider":{"context_length":100000,"max_completion_tokens":100000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/generations"],"aliases":["qwen-image-3.0-pro","bailian/qwen-image-3.0-pro"]},{"id":"qwen/qwen-plus","object":"model","created":1764547200,"owned_by":"dashscope","canonical_slug":"qwen-plus","name":"Qwen Plus","description":"Alibaba Qwen Plus via Dashscope. Balanced performance and cost for general tasks. Strong Chinese and English bilingual capabilities.","context_length":1000000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000012","completion":"0.00000029","input_cache_read":"0.000000023"},"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["qwen-plus","bailian/qwen-plus"]},{"id":"qwen/qwen3.5-flash","object":"model","created":1771804800,"owned_by":"dashscope","canonical_slug":"qwen3.5-flash-2026-02-23","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。","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.5-flash","bailian/qwen3.5-flash"]},{"id":"qwen/qwen3.6-flash","object":"model","created":1776297600,"owned_by":"dashscope","canonical_slug":"qwen3.6-flash-2026-04-16","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。","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000025","completion":"0.0000015","input_cache_read":"0.000000025","input_cache_write":"0.00000031","web_search":"0.01"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.6-flash","bailian/qwen3.6-flash"]},{"id":"qwen/qwen3.7-max","object":"model","created":1779321600,"owned_by":"dashscope","canonical_slug":"qwen3.7-max","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.","context_length":1064000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000171","completion":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"top_provider":{"context_length":1064000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.7-max","bailian/qwen3.7-max"]},{"id":"qwen/qwen3.7-plus","object":"model","created":1780272000,"owned_by":"dashscope","canonical_slug":"qwen3.7-plus","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.","context_length":1064000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.0000016","input_cache_read":"0.00000008","input_cache_write":"0.0000005","web_search":"0.01"},"top_provider":{"context_length":1064000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.7-plus","bailian/qwen3.7-plus"]},{"id":"qwen/qwen3.8-27b","object":"model","created":1787097600,"owned_by":"dashscope","canonical_slug":"qwen3.8-27b","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.","context_length":1131072,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.00000171","input_cache_read":"0.000000043","input_cache_write":"0.00000063","web_search":"0.01"},"top_provider":{"context_length":1131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.8-27b","bailian/qwen3.8-27b"]},{"id":"qwen/qwen3.8-flash","object":"model","created":1787616000,"owned_by":"dashscope","canonical_slug":"qwen3.8-flash","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.","context_length":1131072,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000011","completion":"0.00000039","input_cache_read":"0.000000011","input_cache_write":"0.00000014","web_search":"0.01"},"top_provider":{"context_length":1131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.8-flash","bailian/qwen3.8-flash"]},{"id":"qwen/qwen3.8-max","object":"model","created":1785715200,"owned_by":"dashscope","canonical_slug":"qwen3.8-max","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.","context_length":1131072,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000171","completion":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"top_provider":{"context_length":1131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.8-max","bailian/qwen3.8-max"]},{"id":"qwen/qwen3.8-max-0902","object":"model","created":1788307200,"owned_by":"dashscope","canonical_slug":"qwen3.8-max-0902","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.","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.00000171","completion":"0.00000514","input_cache_read":"0.00000017","input_cache_write":"0.00000214","web_search":"0.01"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["qwen3.8-max-0902","qwen3.8-max-2026-09-02","bailian/qwen3.8-max-0902"]},{"id":"qwen/text-embedding-v4","object":"model","created":1735689600,"owned_by":"dashscope","canonical_slug":"text-embedding-v4","name":"Qwen Text Embedding V4","description":"Alibaba Text Embedding V4 via Dashscope. Latest embedding model with improved accuracy, 1024 dimensions, and 8K context support.","context_length":8192,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"qwen","instruct_type":null},"pricing":{"prompt":"0.000000072","completion":"0"},"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/embeddings"],"aliases":["text-embedding-v4","bailian/text-embedding-v4"]},{"id":"typesafe/jev-latest","object":"model","created":1790121600,"owned_by":"typesafe","canonical_slug":"jev-latest","name":"TypeSafe: Jev","description":"TypeSafe Jev evaluates text or structured state using predicate, choice and score questions. Available through /v1/decisions, /openai/v1/decisions and /typesafe/v1/systemone.","context_length":64000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"jev","instruct_type":null},"pricing":{"prompt":"0.000000042","completion":"0"},"top_provider":{"context_length":64000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/decisions"],"aliases":["jev-latest"]},{"id":"volcengine/doubao-seed-2.0-code","object":"model","created":1771027200,"owned_by":"volcengine","canonical_slug":"doubao-seed-2-0-code-preview-260215","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.00000067","completion":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-2.0-code","doubao-seed-2-0-code-preview-260215"]},{"id":"volcengine/doubao-seed-2.0-pro","object":"model","created":1771027200,"owned_by":"volcengine","canonical_slug":"doubao-seed-2-0-pro-260215","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.00000067","completion":"0.00000336","input_cache_read":"0.00000014","input_cache_write":"0.0000000024"},"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-2.0-pro","doubao-seed-2-0-pro-260215"]},{"id":"volcengine/doubao-seed-2.1-pro","object":"model","created":1782172800,"owned_by":"volcengine","canonical_slug":"doubao-seed-2-1-pro-260628","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.000000884","completion":"0.00000442","input_cache_read":"0.000000177","input_cache_write":"0.0000000025","web_search":"0.0012"},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-2.1-pro"]},{"id":"volcengine/doubao-seed-2.1-turbo","object":"model","created":1782172800,"owned_by":"volcengine","canonical_slug":"doubao-seed-2-1-turbo-260628","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.000000442","completion":"0.000002212","input_cache_read":"0.000000085","input_cache_write":"0.0000000024","web_search":"0.0012"},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-2.1-turbo"]},{"id":"volcengine/doubao-seed-character","object":"model","created":1782172800,"owned_by":"volcengine","canonical_slug":"doubao-seed-character-260628","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.000000177","completion":"0.000000884","input_cache_read":"0.000000024","input_cache_write":"0.0000000025","web_search":"0.0012"},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-character"]},{"id":"volcengine/doubao-seed-evolving","object":"model","created":1782172800,"owned_by":"volcengine","canonical_slug":"doubao-seed-evolving-latest-version","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。","context_length":256000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0.000000884","completion":"0.00000442","input_cache_read":"0.000000177","input_cache_write":"0.0000000025","web_search":"0.0012"},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["doubao-seed-evolving"]},{"id":"volcengine/doubao-seedream-5.0-flash","object":"model","created":1789430400,"owned_by":"volcengine","canonical_slug":"doubao-seedream-5-0-flash-260915","name":"Doubao Seedream 5.0 Flash","description":"Seedream 5.0 Flash 是字节跳动的快速图像生成模型，支持文生图和参考图编辑。支持 1K、1.5K、2K 分辨率及 PNG、JPEG 输出，提示词优化仅支持 standard 模式。","context_length":100000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_image_per_num":"0.02"},"top_provider":{"context_length":100000,"max_completion_tokens":100000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","image","size","watermark","output_format","response_format","optimize_prompt_options"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/generations"],"aliases":["doubao-seedream-5.0-flash","doubao-seedream-5-0-flash","doubao-seedream-5-0-flash-260915"],"image_attributes":{"supported_params":["prompt","image","size","watermark","output_format","response_format","optimize_prompt_options"],"sizes":["1K","1.5K","2K"],"output_formats":["png","jpeg"],"optimize_prompt_modes":["standard"],"family":"seedream"}},{"id":"volcengine/doubao-seedream-5.0-pro","object":"model","created":1783468800,"owned_by":"volcengine","canonical_slug":"doubao-seedream-5-0-pro-260628","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。","context_length":100000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_image_per_num":"0.05"},"top_provider":{"context_length":100000,"max_completion_tokens":100000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","n","size","output_format","stream","user"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/generations"],"aliases":["doubao-seedream-5.0-pro","doubao-seedream-5-0-pro-260628"]},{"id":"volcengine/doubao-seedream-5.5","object":"model","created":1794182400,"owned_by":"volcengine","canonical_slug":"doubao-seedream-5-5-261028","name":"Doubao Seedream 5.5","description":"Seedream 5.5 是字节跳动的图像创作模型，支持文生图、最多 10 张参考图编辑和多轮精准编辑，可生成透明背景 PNG 图片。支持 1K、1.5K、2K 分辨率及 PNG、JPEG 输出。","context_length":100000,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"doubao","instruct_type":null},"pricing":{"prompt":"0","completion":"0","output_image_per_num":"0.05"},"top_provider":{"context_length":100000,"max_completion_tokens":100000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["prompt","image","size","background","watermark","output_format","response_format","optimize_prompt_options"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/images/generations"],"aliases":["doubao-seedream-5.5","doubao-seedream-5-5","doubao-seedream-5-5-261028"],"image_attributes":{"supported_params":["prompt","image","size","background","watermark","output_format","response_format","optimize_prompt_options"],"sizes":["1K","1.5K","2K"],"backgrounds":["auto","transparent","opaque"],"output_formats":["png","jpeg"],"optimize_prompt_modes":["standard"],"family":"seedream"}},{"id":"x-ai/grok-4.1-fast","object":"model","created":1763510400,"owned_by":"xai","canonical_slug":"grok-4-1-fast-non-reasoning","name":"xAI: Grok 4.1 Fast","description":"xAI Grok 4.1 Fast - latest version with improved tool calling and 2M context. Best agentic performance from xAI without explicit reasoning.","context_length":2000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"prompt":"0.0000002","completion":"0.0000005","input_cache_read":"0.00000005","web_search":"0.014"},"top_provider":{"context_length":2000000,"max_completion_tokens":30000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"]},{"id":"x-ai/grok-4.3","object":"model","created":1777507200,"owned_by":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","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...","context_length":1000000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.014"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["grok-4.3","grok-4.3-20260430"]},{"id":"x-ai/grok-4.5","object":"model","created":1783468800,"owned_by":"xai","canonical_slug":"grok-4.5","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.","context_length":500000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000003"},"top_provider":{"context_length":500000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["grok-4.5"]},{"id":"x-ai/grok-4.6","object":"model","created":1786492800,"owned_by":"xai","canonical_slug":"grok-4.6","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.","context_length":500000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005"},"top_provider":{"context_length":500000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["grok-4.6"]},{"id":"x-ai/grok-4.7","object":"model","created":1789948800,"owned_by":"xai","canonical_slug":"grok-4.7","name":"xAI: Grok 4.7","description":"Grok 4.7 is xAI's latest reasoning model, succeeding Grok 4.6 for coding, agentic tool use, and general chat. It supports a 500K-token context window with always-on reasoning, function calling, structured outputs, and prompt caching; requests of 200K prompt tokens or more are billed at the long-context rate.","context_length":500000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005"},"top_provider":{"context_length":500000,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["grok-4.7"]},{"id":"z-ai/glm-4.7","object":"model","created":1766448000,"owned_by":"zhipu","canonical_slug":"glm-4.7","name":"Z.ai: GLM 4.7","description":"Zhipu GLM-4.7 - latest flagship model with advanced reasoning, 128K context, and web search capabilities. Best-in-class Chinese language understanding.","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000004","completion":"0.0000022","input_cache_read":"0.00000011","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-4.7"]},{"id":"z-ai/glm-4.7-flashx","object":"model","created":1768780800,"owned_by":"zhipu","canonical_slug":"glm-4.7-flashx","name":"Z.ai: GLM-4.7 FlashX","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.000000072","completion":"0.0000004","input_cache_read":"0.00000001","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-4.7-flashx"]},{"id":"z-ai/glm-5","object":"model","created":1770768000,"owned_by":"zhipu","canonical_slug":"glm-5","name":"Z.ai: GLM-5","description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-5"]},{"id":"z-ai/glm-5-turbo","object":"model","created":1773619200,"owned_by":"zhipu","canonical_slug":"glm-5-turbo","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.","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-5-turbo"]},{"id":"z-ai/glm-5.1","object":"model","created":1774569600,"owned_by":"zhipu","canonical_slug":"glm-5.1","name":"Z.ai: GLM 5.1","context_length":200000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-5.1"]},{"id":"z-ai/glm-5.2","object":"model","created":1781568000,"owned_by":"zhipu","canonical_slug":"glm-5.2","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).","context_length":1048576,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["glm-5.2"]},{"id":"z-ai/glm-5.3","object":"model","created":1787097600,"owned_by":"zhipu","canonical_slug":"glm-5.3","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).","context_length":1048576,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","web_search":"0.01"},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["glm-5.3"]},{"id":"z-ai/glm-5.3-flash","object":"model","created":1787702400,"owned_by":"zhipu","canonical_slug":"glm-5.3-flash","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).","context_length":1048576,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","web_search":"0.01"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions","/v1/responses"],"aliases":["glm-5.3-flash"]},{"id":"z-ai/glm-5.3-flashx","object":"model","created":1787702400,"owned_by":"zhipu","canonical_slug":"glm-5.3-flashx","name":"Z.ai: GLM-5.3-FlashX","description":"GLM-5.3-FlashX 是 z.ai 国际站（api.z.ai）面向高效编码与长程 Agent 任务的轻量高速模型，推理速度可达 200 tokens/s，提供更快、更流畅的模型体验。支持原生多模态输入（图片、视频）、1M 上下文、常驻 thinking（不可关闭，支持 low、high、max 三档 reasoning effort）、prompt caching、tool calling 与 web search，并通过 OpenAI-compatible 和 Anthropic 双协议接入（不支持 Responses 端点）。","context_length":1048576,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.00000037","completion":"0.00000125","input_cache_read":"0.000000075","web_search":"0.01"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-5.3-flashx"]},{"id":"z-ai/glm-5v-turbo","object":"model","created":1775001600,"owned_by":"zhipu","canonical_slug":"glm-5v-turbo","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. ","context_length":200000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024","web_search":"0.01"},"top_provider":{"context_length":200000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice","response_format","reasoning"],"default_parameters":null,"expiration_date":null,"is_deprecated":false,"supported_endpoints":["/v1/chat/completions"],"aliases":["glm-5v-turbo"]}]}
