# Chatbox setup

## Compatibility and prerequisites

This guide prepares Chatbox 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 choose Add.
2. Select OpenAI API compatible and name the provider U9 AI.
3. Set API Host to the root origin and API Path to /v1/chat/completions. Use your U9 API key and avoid duplicate /v1.
4. Add at least one available model, save and run Check, then select it in a new conversation.

## 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

If your version only exposes a Base URL field, use https://u9ai.ai/v1 and confirm the final path. Do not enable image, web, file or tool capabilities unless both the model and endpoint support them.

## 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

[Chatbox](https://docs.chatboxai.app/en/guides/providers)