https://api.laozhang.ai, enter your LaoZhang API key, then fetch the model list or add model IDs by hand. You can then chat with GPT-6, Gemini, DeepSeek, and other models.
Add LaoZhang API
1
Create the provider
Open Cherry Studio, click Settings (the gear icon at the bottom left), go to Model Provider, and click Add at the bottom of the list. Name it “LaoZhang API” and choose OpenAI as the provider type.
2
Enter the key and address
- API Key: your LaoZhang API key
- API Address:
https://api.laozhang.ai
https://api.laozhang.ai/v1/chat/completions. An address ending in / stops Cherry Studio from adding /v1, and one ending in # is used exactly as typed; you normally need neither.3
Check the connection
Click Check next to the API key and pick a model to test. When it passes, turn on the switch at the top right of the provider.
4
Add models
Click Manage to pick from the model list, or Add to enter a model ID such as
gpt-6-sol. Model IDs must match the model catalog exactly.Choose a model
For chats with MCP tools turned on, prefer
gemini-3.8-flash, deepseek-v4-pro, or gpt-5.6-sol; the FAQ below explains why.
FAQ
GPT-6 returns “Unsupported parameter: ‘max_tokens’”
GPT-6 models don’t acceptmax_tokens. Turn off the max-tokens setting in the assistant or chat settings, or use another model.
With MCP tools on, GPT-6 returns “Function tools with reasoning_effort are not supported”
GPT-6 models can only call tools in Chat Completions with reasoning effort set tonone. Use gpt-5.6-sol, gemini-3.8-flash, or deepseek-v4-pro in those chats.
The connection check fails or returns 404
Make sure the API address ishttps://api.laozhang.ai and the preview shows only one /v1. For a 401, copy the key again and confirm the token is enabled in Tokens. For more, see Invalid API key or 404.