U9 AI · DOCUMENTATION
n8n setup
Configure n8n with the correct U9 address, model and compatibility checks.
Download Markdown ↓Compatibility and prerequisites#
This guide prepares n8n 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#
- Create a dedicated OpenAI credential with your U9 key and U9 /v1 Base URL. Leave Organization ID blank.
- Attach it to the intended OpenAI Chat Model or text node and select or enter an available model ID.
- Check whether that node operation uses Chat Completions or Responses. A passing credential check does not validate every operation.
- Manually run one short text node, inspect output and spending, then connect the workflow or agent.
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#
Store secrets in n8n Credentials, not ordinary node JSON or shared exports. For asynchronous video through HTTP Request, follow the model-specific submit/poll contract and avoid blind creation retries.
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.