Model Service

Cherry Studio has built-in connection templates for 60+ providers (model service providers), covering most mainstream models and local inference frameworks at home and abroad. This section provides an independent configuration guide for each provider.

Provider Types

Cherry Studio divides providers into the following categories by protocol, with slightly different behavior:

Type	Compatible Protocol	Typical Examples
OpenAI compatible	/v1/chat/completions	OpenAI, DeepSeek, SiliconFlow, OpenRouter, most third-party gateways
Anthropic compatible	/v1/messages	Anthropic, CherryIN, some gateways.Cherry Agent requires this type
Gemini	Google AI Studio / Vertex	Google Gemini, Vertex AI
Bedrock	AWS Bedrock SDK	AWS Bedrock
Azure OpenAI	Azure OpenAI Service	Azure OpenAI
Local inference	Local HTTP service	Ollama, LM Studio, GPUStack, OpenVINO Model Server
Special gateways	Vendor proprietary protocols	NewAPI, OneAPI, AiHubMix, DMXAPI, etc.

General steps to add a Provider

1. After opening Settings → Model Services
2. Find the target Provider in the built-in Provider list and click to enter the details page
3. Fill in API key(required), modify as needed API Address(the default is the Provider's official address)
4. Click Get model list, and add your commonly used chat/embedding/vision models as needed
5. (optional) click Test, and use any chat model to verify whether the connection is successful

Provider Configuration Details

General/Gateway category

• CherryAI (Free)
• CherryIN — Dual endpoints (OpenAI + Anthropic), recommended for Cherry Agent
• NewAPI / OneAPI — Self-hosted/third-party gateway

Overseas vendors

• OpenAI
• Google Gemini
• Vertex AI
• Mistral
• Perplexity
• GitHub Copilot
• MiniMax Coding Plan

Domestic vendors

• Alibaba Cloud Bailian
• Zhipu AI
• SiliconFlow
• Volcano Engine (Doubao)
• PPIO
• ModelScope (ModelScope)

Local inference

• Ollama

Custom providers

• Custom providers — Any OpenAI / Anthropic / Gemini compatible endpoint

What if you can't find the Provider you use?

Cherry Studio has built-in 60+ provider templates, but far more than the number included in this section's documentation If you're using Anthropic (Claude), Azure OpenAI, official DeepSeek, Grok, Groq, LM Studio, OpenRouter, Mistral, Perplexity, Together, etc.,they are all in the Provider list, just add the API key directly. This section will gradually add dedicated pages for these providers.

API keys and API addresses

See model service settings(including multi-Key polling,# advanced usage such as fixed paths at the end).

---

Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.