# Cherry Studio setup

## Compatibility and prerequisites

This guide prepares Cherry Studio integration with U9 AI. You need an active U9 key, sufficient credit and an available model matching the endpoint. Official documentation was checked on 2026-10-24; this is not an end-to-end test of every client version or upstream model.

## Setup steps

1. Open Settings → Model Provider and add a custom provider named U9 AI.
2. Choose the OpenAI-compatible type and enter API Key and API Host.
3. Sync models or manually add the exact U9 model ID. Enable only confirmed capabilities.
4. Run the model check, then select the U9 model in a new chat.

## Configuration values

| Setting | Value |
| --- | --- |
| API Host | https://u9ai.ai |
| API Key | YOUR_U9AI_API_KEY · U9 API key |
| Model | YOUR_CHAT_MODEL_ID · Available model ID |
| Expected chat endpoint | https://u9ai.ai/v1/chat/completions |

## Important differences

Check that the final path is /v1/chat/completions without duplicate /v1. This configures chat. Cherry Agent has separate protocol requirements; chat success is not agent validation.

## Acceptance and handoff

First follow [quickstart](/en/docs/quickstart) to check GET /v1/models without generating content. Then test a short non-streaming request, streaming and any required tool-call round trip separately. Generation tests may incur charges. Record the request ID and verify [cost analysis](/en/docs/billing). For failures, include client version, model ID, endpoint, status and sanitized errors in a [ticket](/en/support). Do not blindly resubmit timed-out jobs.

Give this Markdown file to your developer or agent. Ask it to preserve current settings, substitute only available model IDs and report untested capabilities. Never put real keys in shared Markdown.

## Official reference

[Cherry Studio](https://www.cherryai.com/docs/en/pre-basic/providers/)

For the API Host field that automatically appends /v1/chat/completions, use the root origin https://u9ai.ai. If your version asks for a versioned endpoint base, follow its path preview. A trailing / means only chat/completions is appended; a trailing # fixes the complete request URL. Always confirm the preview is https://u9ai.ai/v1/chat/completions. Enable the provider switch after saving.

[API Host settings](https://www.cherryai.com/docs/en/pre-basic/settings/providers/)