U9 AI · DOCUMENTATION
Cline setup
Configure Cline with the correct U9 address, model and compatibility checks.
Download Markdown ↓Compatibility and prerequisites#
This guide prepares Cline 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#
- Open extension settings and select OpenAI Compatible as API Provider.
- Enter the U9 /v1 base URL, your U9 key and the exact available text model ID.
- Set context, maximum output and capabilities from actual model specifications, not guessed defaults.
- Test a short question, then a file read and one tool-call round trip in a temporary project. Preserve existing approval settings.
Configuration values#
| Setting | Value |
|---|---|
| Base URL | https://u9ai.ai/v1 |
| 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#
Chat success does not establish agent compatibility. For tool failures, inspect model capabilities, streaming events and client version rather than disabling approvals.
Acceptance and handoff#
First follow 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. For failures, include client version, model ID, endpoint, status and sanitized errors in a ticket. 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.