Dify supports the below model providers out-of-box:

ProviderLLMText EmbeddingRerankSpeech to textTTS
OpenAIโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)โœ”๏ธโœ”๏ธโœ”๏ธ
Anthropicโœ”๏ธ(๐Ÿ› ๏ธ)
Azure OpenAIโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)โœ”๏ธโœ”๏ธโœ”๏ธ
Geminiโœ”๏ธ
Google Cloudโœ”๏ธ(๐Ÿ‘“)โœ”๏ธ
Nvidia API Catalogโœ”๏ธโœ”๏ธโœ”๏ธ
Nvidia NIMโœ”๏ธ
Nvidia Triton Inference Serverโœ”๏ธ
AWS Bedrockโœ”๏ธโœ”๏ธ
OpenRouterโœ”๏ธ
Cohereโœ”๏ธโœ”๏ธโœ”๏ธ
together.aiโœ”๏ธ
Ollamaโœ”๏ธโœ”๏ธ
Mistral AIโœ”๏ธ
groqcloudโœ”๏ธ
Replicateโœ”๏ธโœ”๏ธ
Hugging Faceโœ”๏ธโœ”๏ธ
Xorbits inferenceโœ”๏ธโœ”๏ธโœ”๏ธโœ”๏ธโœ”๏ธ
Zhipu AIโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)โœ”๏ธ
Baichuanโœ”๏ธโœ”๏ธ
Sparkโœ”๏ธ
Minimaxโœ”๏ธ(๐Ÿ› ๏ธ)โœ”๏ธ
Tongyiโœ”๏ธโœ”๏ธโœ”๏ธ
Wenxinโœ”๏ธโœ”๏ธ
Moonshot AIโœ”๏ธ(๐Ÿ› ๏ธ)
Tencent Cloudโœ”๏ธ
Stepfunโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)
VolcanoEngineโœ”๏ธโœ”๏ธ
01.AIโœ”๏ธ
360 Zhinaoโœ”๏ธ
Azure AI Studioโœ”๏ธโœ”๏ธ
deepseekโœ”๏ธ(๐Ÿ› ๏ธ)
Tencent Hunyuanโœ”๏ธ
SILICONFLOWโœ”๏ธโœ”๏ธ
Jina AIโœ”๏ธโœ”๏ธ
ChatGLMโœ”๏ธ
Xinferenceโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)โœ”๏ธโœ”๏ธ
OpenLLMโœ”๏ธโœ”๏ธ
LocalAIโœ”๏ธโœ”๏ธโœ”๏ธโœ”๏ธ
OpenAI API-Compatibleโœ”๏ธโœ”๏ธโœ”๏ธ
PerfXCloudโœ”๏ธโœ”๏ธ
Lepton AIโœ”๏ธ
novita.aiโœ”๏ธ
Amazon Sagemakerโœ”๏ธโœ”๏ธโœ”๏ธ
Text Embedding Inferenceโœ”๏ธโœ”๏ธ
GPUStackโœ”๏ธ(๐Ÿ› ๏ธ)(๐Ÿ‘“)โœ”๏ธโœ”๏ธ
GPUStackโœ”๏ธ(๐Ÿ”ง๏ธ)(๐Ÿ‘“)โœ”๏ธโœ”๏ธโœ”๏ธโœ”๏ธ

where (๐Ÿ› ๏ธ) ๏ธŽ denotes โ€œfunction callingโ€ and (๐Ÿ‘“) denotes โ€œsupport for visionโ€.


This table is continuously updated. We also keep track of model providers requested by community members here. If youโ€™d like to see a model provider not listed above, please consider contributing by making a PR. To learn more, check out our contribution.md Guide.


Edit this page | Report an issue