Download Cherry Studio
Download Cherry StudioConfigure AIHubMix
-
Open Settings → Model Provider, select AiHubMix, and turn on the switch in the top-right corner.
-
Keep API Host at
https://aihubmix.com/v1.
-
Enter the key from this site in API Key and click Model Check.
If the check fails, disable your VPN and try again. -
Click Sync models to add models from the returned list, or click + to add a model ID manually.
-
Open Settings → Default Model and choose the models used for the assistant, quick tasks, and translation.
Start chatting
Return to the home page and select the added model in the model selector at the top.FAQ
The model cannot recognize images
Open the model’s edit page under Settings → Model Provider and enable Vision under Input Modalities.Calling Claude models returns AI_APICallError
Check whether the request URL in the error message is https://aihubmix.com/anthropic/v1/messages. If it is, change the Anthropic endpoint URL to https://aihubmix.com in the provider settings.
Enable Claude prompt caching
Open API Settings on the AiHubMix provider page and configure the options as needed:- Cache Token Threshold: only messages above this token count are cached; set to 0 to disable caching
- Cache System Message: whether to cache the system prompt
- Cache Last N Messages: cache the last N conversation messages, excluding system messages
- Cache Duration: 5 minutes or 1 hour; one-hour cache writes cost more
cache_control for Claude models. For details, see Claude Prompt Caching.
Last updated: 2026-11-04