支持模型

本页列出开源版 OpenMAIC 随代码内置的 provider registry。内置 provider 可以通过设置、环境变量或 server-providers.yml 配置；自定义 OpenAI 兼容 provider 请在设置中添加。具体可用性还取决于 provider 账号、所在区域和服务端配置；托管实例也可能通过白名单隐藏部分内置模型。

LLM 模型

DEFAULT_MODEL 或 YAML 中的模型写法是 provider:model-id，例如 openai:gpt-5.6、qwen:qwen3.7-plus、ollama:llama3.3。

提供方	Provider ID	内置模型
OpenAI	`openai`	GPT-5.6 Sol (`gpt-5.6`) GPT-5.6 Terra (`gpt-5.6-terra`) GPT-5.6 Luna (`gpt-5.6-luna`) GPT-5.5 (`gpt-5.5`) GPT-5.4 Pro (`gpt-5.4-pro`) GPT-5.4 (`gpt-5.4`) GPT-5.4 Mini (`gpt-5.4-mini`) GPT-5.4 Nano (`gpt-5.4-nano`)
Azure OpenAI	`azure`	无预设模型 ID；填写 Azure OpenAI deployment name。
Atlas Cloud	`atlascloud`	Qwen3.5 Flash (`qwen/qwen3.5-flash`) DeepSeek V4 Pro (`deepseek-ai/deepseek-v4-pro`)
Amazon Bedrock	`bedrock`	Claude Sonnet 5 (`us.anthropic.claude-sonnet-5`) Claude Opus 4.8 (`us.anthropic.claude-opus-4-8`) Claude Opus 4.7 (`us.anthropic.claude-opus-4-7`) Claude Sonnet 4.6 (`us.anthropic.claude-sonnet-4-6`) Amazon Nova Pro (`us.amazon.nova-pro-v1:0`) Amazon Nova Lite (`us.amazon.nova-lite-v1:0`) Amazon Nova Micro (`us.amazon.nova-micro-v1:0`) Llama 3.3 70B Instruct (`us.meta.llama3-3-70b-instruct-v1:0`)
Claude	`anthropic`	Claude Opus 5 (`claude-opus-5`) Claude Sonnet 5 (`claude-sonnet-5`) Claude Fable 5 (`claude-fable-5`) Claude Opus 4.8 (`claude-opus-4-8`) Claude Opus 4.7 (`claude-opus-4-7`) Claude Opus 4.6 (`claude-opus-4-6`) Claude Sonnet 4.6 (`claude-sonnet-4-6`) Claude Sonnet 4.5 (`claude-sonnet-4-5`) Claude Haiku 4.5 (`claude-haiku-4-5`)
Gemini	`google`	Gemini 3.6 Flash (`gemini-3.6-flash`) Gemini 3.5 Flash-Lite (`gemini-3.5-flash-lite`) Gemini 3.5 Flash (`gemini-3.5-flash`) Gemini 3.1 Pro Preview (`gemini-3.1-pro-preview`) Gemini 3 Flash Preview (`gemini-3-flash-preview`) Gemini 2.5 Flash (`gemini-2.5-flash`) Gemini 2.5 Flash Lite (`gemini-2.5-flash-lite`) Gemini 2.5 Pro (`gemini-2.5-pro`)
GLM	`glm`	GLM-5.2 (`glm-5.2`) GLM-5.1 (`glm-5.1`) GLM-5V-Turbo (`glm-5v-turbo`) GLM-5 (`glm-5`) GLM-4.7 (`glm-4.7`) GLM-4.7-FlashX (`glm-4.7-flashx`) GLM-4.7-Flash (`glm-4.7-flash`) GLM-4.6 (`glm-4.6`) GLM-4.6V (`glm-4.6v`) GLM-4.6V-Flash (`glm-4.6v-flash`)
Qwen	`qwen`	Qwen3.7 Plus (`qwen3.7-plus`) Qwen3.7 Max (`qwen3.7-max`) Qwen3.6 Max Preview (`qwen3.6-max-preview`) Qwen3.6 Plus (`qwen3.6-plus`) Qwen3.6 Plus 2026-04-02 (`qwen3.6-plus-2026-04-02`) Qwen3.6 Flash (`qwen3.6-flash`) Qwen3.6 Flash 2026-04-16 (`qwen3.6-flash-2026-04-16`) Qwen3.6 35B A3B (`qwen3.6-35b-a3b`) Qwen3.5 Flash (`qwen3.5-flash`) Qwen3.5 Plus (`qwen3.5-plus`) Qwen3 Max (`qwen3-max`) Qwen3 VL Plus (`qwen3-vl-plus`)
DeepSeek	`deepseek`	DeepSeek V4 Pro (`deepseek-v4-pro`) DeepSeek V4 Flash (`deepseek-v4-flash`)
Kimi	`kimi`	Kimi K3 (`kimi-k3`) Kimi K2.7 Code (`kimi-k2.7-code`) Kimi K2.7 Code HighSpeed (`kimi-k2.7-code-highspeed`) Kimi K2.6 (`kimi-k2.6`) Kimi K2.5 (`kimi-k2.5`) Kimi K2 Thinking (`kimi-k2-thinking`)
MiniMax	`minimax`	MiniMax M3 (`MiniMax-M3`) MiniMax M2.7 (`MiniMax-M2.7`)
SiliconFlow	`siliconflow`	DeepSeek-V3.2 (`deepseek-ai/DeepSeek-V3.2`) DeepSeek-R1 (`deepseek-ai/DeepSeek-R1`) DeepSeek-R1-Distill-Qwen-7B (`deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`) Qwen3-VL-32B-Instruct (`Qwen/Qwen3-VL-32B-Instruct`) Kimi-K2.5 (`Pro/moonshotai/Kimi-K2.5`) GLM-4.1V-9B-Thinking (`THUDM/GLM-4.1V-9B-Thinking`) GLM-Z1-Rumination-32B (`THUDM/GLM-Z1-Rumination-32B-0414`)
Doubao	`doubao`	Doubao Seed 2.1 Pro (`doubao-seed-2-1-pro-260628`) Doubao Seed 2.1 Turbo (`doubao-seed-2-1-turbo-260628`) Doubao Seed Evolving (`doubao-seed-evolving`) Doubao Seed Character (`doubao-seed-character-260628`) Doubao Seed 2.0 Pro (`doubao-seed-2-0-pro-260215`) Doubao Seed 2.0 Lite (`doubao-seed-2-0-lite-260215`) Doubao Seed 2.0 Mini (`doubao-seed-2-0-mini-260215`) Doubao Seed 1.8 (`doubao-seed-1-8-251228`)
Claude	`claude`
OpenRouter	`openrouter`	DeepSeek V4 Pro (`deepseek/deepseek-v4-pro`) DeepSeek V4 Flash (`deepseek/deepseek-v4-flash`)
Grok	`grok`	Grok 4.6 (`grok-4.6`) Grok 4.5 (`grok-4.5`) Grok 4.3 (`grok-4.3`) Grok Build 0.1 (`grok-build-0.1`) Grok 4.20 Reasoning (`grok-4.20-reasoning`) Grok 4.20 (`grok-4.20`) Grok 4.20 Multi-Agent (`grok-4.20-multi-agent`) Grok 4.1 Fast Reasoning (`grok-4-1-fast-reasoning`) Grok 4.1 Fast (`grok-4-1-fast-non-reasoning`) Grok Code Fast (`grok-code-fast-1`)
Tencent Hunyuan	`tencent-hunyuan`	Tencent Hy3 Preview (`hy3-preview`)
Xiaomi MiMo	`xiaomi`	MiMo V2.6 Pro (`mimo-v2.6-pro`) MiMo V2.6 Flash (`mimo-v2.6-flash`) MiMo V2.5 Pro (`mimo-v2.5-pro`) MiMo V2 Pro (`mimo-v2-pro`) MiMo V2.5 (`mimo-v2.5`) MiMo V2 Omni (`mimo-v2-omni`) MiMo V2 Flash (`mimo-v2-flash`)
Ollama	`ollama`	Llama 3.3 70B (`llama3.3`) Gemma 3 12B (`gemma3`) DeepSeek R1 (`deepseek-r1`)
Lemonade	`lemonade`	Gemma 4 26B A4B IT GGUF (`Gemma-4-26B-A4B-it-GGUF`)

图像生成模型

提供方	Provider ID	内置模型
Seedream	`seedream`	Seedream 5.0 Lite (`doubao-seedream-5-0-260128`) Seedream 5.0 Lite Alias (`doubao-seedream-5-0-lite-260128`) Seedream 4.5 (`doubao-seedream-4-5-251128`) Seedream 4.0 (`doubao-seedream-4-0-250828`) Seedream 3.0 (`doubao-seedream-3-0-t2i-250415`)
OpenAI Image	`openai-image`	GPT Image 2 (`gpt-image-2`) GPT Image 2 2026-04-21 (`gpt-image-2-2026-04-21`) GPT Image 1.5 (`gpt-image-1.5`) GPT Image 1 (`gpt-image-1`) GPT Image 1 Mini (`gpt-image-1-mini`) ChatGPT Image Latest (`chatgpt-image-latest`)
Qwen Image	`qwen-image`	Qwen Image 2.0 Pro (`qwen-image-2.0-pro`) Qwen Image 2.0 Pro 2026-03-03 (`qwen-image-2.0-pro-2026-03-03`) Qwen Image 2.0 (`qwen-image-2.0`) Qwen Image 2.0 2026-03-03 (`qwen-image-2.0-2026-03-03`) Qwen Image Max (`qwen-image-max`) Qwen Image Max 2025-12-30 (`qwen-image-max-2025-12-30`) Qwen Image Plus (`qwen-image-plus`) Qwen Image Plus 2026-01-09 (`qwen-image-plus-2026-01-09`) Qwen Image (`qwen-image`) Z-Image Turbo (`z-image-turbo`)
Nano Banana (Gemini)	`nano-banana`	Gemini 3.1 Flash Image (Nano Banana 2) (`gemini-3.1-flash-image-preview`) Gemini 3 Pro Image (Nano Banana Pro) (`gemini-3-pro-image-preview`) Gemini 2.5 Flash Image (Nano Banana) (`gemini-2.5-flash-image`)
MiniMax Image	`minimax-image`	Image 01 (`image-01`) Image 01 Live (`image-01-live`)
Grok Image	`grok-image`	Grok Imagine Image (`grok-imagine-image`) Grok Imagine Image Pro (`grok-imagine-image-pro`)
ComfyUI Image	`comfyui-image`	无预设模型 ID；运行时从 `public/` 中发现并选择 ComfyUI workflow。
Lemonade Image	`lemonade`	Qwen Image GGUF (`Qwen-Image-GGUF`) Stable Diffusion (sd-cpp) (`sd-cpp`)

视频生成模型

提供方	Provider ID	内置模型
Seedance	`seedance`	Seedance 2.0 (`doubao-seedance-2-0-260128`) Seedance 2.0 Fast (`doubao-seedance-2-0-fast-260128`) Seedance 2.0 Mini (`doubao-seedance-2-0-mini-260615`) Seedance 1.5 Pro (`doubao-seedance-1-5-pro-251215`) Seedance 1.0 Pro (`doubao-seedance-1-0-pro-250528`) Seedance 1.0 Pro Fast (`doubao-seedance-1-0-pro-fast-251015`) Seedance 1.0 Lite T2V (`doubao-seedance-1-0-lite-t2v-250428`)
Kling	`kling`	Kling V2.6 (`kling-v2-6`) Kling V1.6 (`kling-v1-6`)
Veo	`veo`	Veo 3.1 Fast (`veo-3.1-fast-generate-001`) Veo 3.1 (`veo-3.1-generate-001`) Veo 3.0 Fast (`veo-3.0-fast-generate-001`) Veo 3.0 (`veo-3.0-generate-001`) Veo 2.0 (`veo-2.0-generate-001`)
MiniMax Video	`minimax-video`	Hailuo 2.3 (`MiniMax-Hailuo-2.3`) Hailuo 02 (`MiniMax-Hailuo-02`) T2V-01 Director (`T2V-01-Director`) T2V-01 (`T2V-01`)
Grok Video	`grok-video`	Grok Imagine Video (`grok-imagine-video`)
HappyHorse	`happyhorse`	HappyHorse 1.0 T2V (`happyhorse-1.0-t2v`)

TTS 模型与后端

此表列出模型选择器和自托管后端，不展开每个 provider 的完整音色列表。

提供方	Provider ID	模型或后端
OpenAI TTS	`openai-tts`	GPT-4o Mini TTS (`gpt-4o-mini-tts`) TTS-1 (`tts-1`) TTS-1 HD (`tts-1-hd`)
Azure TTS	`azure-tts`	无模型选择器，使用已配置的 Azure Neural Voices。
GLM TTS	`glm-tts`	GLM TTS (`glm-tts`)
Qwen TTS	`qwen-tts`	Qwen3 TTS Flash (`qwen3-tts-flash`) Qwen3 TTS Instruct Flash (`qwen3-tts-instruct-flash`) Qwen TTS (`qwen-tts`)
MiniMax TTS	`minimax-tts`	Speech 2.8 HD (`speech-2.8-hd`) Speech 2.8 Turbo (`speech-2.8-turbo`) Speech 2.6 HD (`speech-2.6-hd`) Speech 2.6 Turbo (`speech-2.6-turbo`) Speech 02 HD (`speech-02-hd`) Speech 02 Turbo (`speech-02-turbo`)
VoxCPM2	`voxcpm-tts`	VoxCPM2 (`voxcpm2`) 后端：vLLM-Omni、Python API、Nano-vLLM
Lemonade TTS	`lemonade-tts`	Kokoro v1 (`kokoro-v1`)
豆包 TTS 2.0	`doubao-tts`	无模型选择器，使用豆包 TTS 2.0 音色 ID。
ElevenLabs TTS	`elevenlabs-tts`	Multilingual v2 (`eleven_multilingual_v2`) Flash v2.5 (`eleven_flash_v2_5`) Flash v2 (`eleven_flash_v2`)
浏览器原生 TTS	`browser-native-tts`	无模型选择器，使用浏览器和操作系统提供的音色列表。

ASR 模型

提供方	Provider ID	内置模型
OpenAI Whisper	`openai-whisper`	GPT-4o Mini Transcribe (`gpt-4o-mini-transcribe`) GPT-4o Transcribe (`gpt-4o-transcribe`) Whisper-1 (`whisper-1`)
Qwen ASR	`qwen-asr`	Qwen3 ASR Flash (`qwen3-asr-flash`)
Azure STT	`azure-asr`	无模型选择器，使用 Azure Speech to Text。
FunASR	`funasr-asr`	SenseVoiceSmall (`sensevoice`) Paraformer (`paraformer`) Fun-ASR-Nano (`fun-asr-nano`)
Lemonade ASR	`lemonade-asr`	Whisper Base (`Whisper-Base`) Whisper Large v3 (`Whisper-Large-v3`) Whisper Large v3 Turbo (`Whisper-Large-v3-Turbo`) Whisper Medium (`Whisper-Medium`) Whisper Small (`Whisper-Small`) Whisper Tiny (`Whisper-Tiny`)
浏览器原生 ASR	`browser-native`	无模型选择器，使用浏览器 Web Speech API。

文档解析提供方

提供方	Provider ID	能力
unpdf	`unpdf`	文本、图片、元数据
MinerU	`mineru`	文本、图片、表格、公式、版面分析
MinerU Cloud	`mineru-cloud`	文本、图片、表格、公式、版面分析
AliDocMind	`alidocmind`	文本、图片、表格、公式、版面分析、OCR

Web Search 提供方

Web Search provider 没有模型选择器。SearXNG 仅支持服务端托管配置；其他 provider 可按各自要求配置 API key 或 Base URL。

提供方	Provider ID
Tavily	`tavily`
Bocha	`bocha`
Brave Search	`brave`
Baidu	`baidu`
MiniMax	`minimax`
Doubao	`doubao`
SearXNG	`searxng`