Cherry Studio
Cherry Studio is a multi-provider desktop AI client. Use the "Custom (OpenAI-compatible)" provider type to connect to this service.
Official docs: https://docs.cherry-ai.com/docs/en-us/pre-basic/providers/zi-ding-yi-fu-wu-shang
1. Open model service settings
Click the gear icon (Settings) in the lower left, then go to Model Services.
2. Add a custom provider
Click the + Add button and configure a new provider:
| Field | Value |
|---|---|
| Name | Any name, e.g. My Proxy |
| Provider Type | OpenAI Compatible |
| API Address | https://codex.openai.com/v1 |
| API Key | Your codex_... or sk-... key |
3. Add models
Under the provider configuration, manually add a model ID such as gpt-5-codex-mini.
You can also click Fetch Model List to automatically pull the available models from the service.
4. Verify
Click the Verify button. After it passes, save the configuration.
Go back to the main view, select the newly added model, and start a conversation to confirm it works.
Notes
- The API Address takes the base URL including
/v1:https://codex.openai.com/v1 - Cherry Studio supports multiple simultaneous providers and lets you switch between them per session