Dify supports the below model providers out-of-box:
ProviderLLMText EmbeddingRerankSpeech to textTTS
OpenAI✔(🛠)(👓)✔✔✔
Anthropic✔(🛠)
Azure OpenAI✔(🛠)(👓)✔✔✔
Gemini✔
Google Cloud✔(👓)✔
Nvidia API Catalog✔✔✔
Nvidia NIM✔
Nvidia Triton Inference Server✔
AWS Bedrock✔✔
OpenRouter✔
Cohere✔✔✔
together.ai✔
Ollama✔✔
Mistral AI✔
groqcloud✔
Replicate✔✔
Hugging Face✔✔
Xorbits inference✔✔✔✔✔
Zhipu AI✔(🛠)(👓)✔
Baichuan✔✔
Spark✔
Minimax✔(🛠)✔
Tongyi✔✔✔
Wenxin✔✔
Moonshot AI✔(🛠)
Tencent Cloud✔
Stepfun✔(🛠)(👓)
VolcanoEngine✔✔
01.AI✔
360 Zhinao✔
Azure AI Studio✔✔
deepseek✔(🛠)
Tencent Hunyuan✔
SILICONFLOW✔✔
Jina AI✔✔
ChatGLM✔
Xinference✔(🛠)(👓)✔✔
OpenLLM✔✔
LocalAI✔✔✔✔
OpenAI API-Compatible✔✔✔
PerfXCloud✔✔
Lepton AI✔
novita.ai✔
Amazon Sagemaker✔✔✔
Text Embedding Inference✔✔
GPUStack✔(🛠)(👓)✔✔
GPUStack✔(🔧)(👓)✔✔✔✔
where (🛠)  denotes “function calling” and (👓) denotes “support for vision”.
This table is continuously updated. We also keep track of model providers requested by community members here. If you’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