U9 AI · DOCUMENTATION
Open WebUI setup
Configure Open WebUI with the correct U9 address, model and compatibility checks.
Download Markdown ↓Compatibility and prerequisites#
This guide prepares Open WebUI 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#
- As an administrator, open Settings → Admin → Connections and add an OpenAI API Connection.
- Set URL to the U9 /v1 address, API Key to your U9 key and Provider to Default.
- Run Verify Connection and allowlist the intended Model IDs rather than exposing the entire multimodal catalog as chat models.
- Save and select the model in chat. Review credential and connection sharing on a multi-user server.
Configuration values#
| Setting | Value |
|---|---|
| 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#
Prefer a server-side provider connection and verify server reachability. Do not add this as a Tools / OpenAPI tool server. Embeddings, RAG, audio and image operations require separate endpoint support.
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.