Discover. Extend. Build

Official DeepSeek models with reasoning, tool calling, and native vision in deepseek-flash.

Tongyi

Model providers compatible with OpenAI's API standard, such as LM Studio or llama.cpp Service.

Call Volcengine Ark endpoints (Endpoint ID) from Dify. Supports LLM, text embedding, and speech-to-text.

Current OpenAI language, embedding, moderation, and audio models.

Ollama

Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall and hunyuan-lite.

SiliconFlow provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.

Google's Gemini model.

Anthropic's powerful models.

Azure OpenAI Service Model

Xorbits Inference

OpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options.

Minimax AI models for LLM, text embedding, and text-to-speech

ZHIPU AI

Embedding and Rerank Model Supported

A blazing fast inference solution for text embeddings models.

The models of Amazon Bedrock

Models provided by ModelScope

Models provided by Moonshot, such as kimi-k3.1-pro, kimi-k3.1-pro-highspeed, kimi-k3, kimi-k2.7-code, kimi-k2.6, kimi-k2.5, kimi-k2, moonshot-v1-8k, moonshot-v1-32k, and moonshot-v1-128k.

xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe.

vllm provider for extra_body support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5

Vertex AI in Google Cloud Platform.

Cohere

Baidu's ERNIE Model

Deploy local models using LM Studio

Hugging Face Model

One Gateway, Infinite Models；one-stop request: OpenAI, Claude, Gemini, DeepSeek, Qwen, and over 500 AI models.

GroqCloud provides access to the Groq Cloud API, which hosts models like LLama2 and Mixtral.

Volcengine Ark base and multimodal model invocation.

Azure AI Studio

GPUStack is an open-source GPU cluster manager for running AI models.

LocalAI

ChatGLM

Huawei Cloud MaaS provides access to various models (LLMs), configurable via model name, API key, and other parameters.

Models provided by Fish Audio, currently support TTS and ASR.

Models provided by Xiaomi MiMo, such as mimo-v2.6-pro, mimo-v2.6-flash, mimo-v2.6-pro-ultraspeed. Supports Token Plan subscription.

Models provided by MistralAI, including Magistral models with prompt_mode support, Mistral Large/Medium/Small, Pixtral vision models, Codestral for coding, specialized embedding models, and content moderation services.

NVIDIA NIM, a set of easy-to-use inference microservices.

OpenLLM