# WorkBuddy setup

## Compatibility and prerequisites

This guide prepares WorkBuddy 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 model settings and add a custom model using Custom.
2. Select an OpenAI-compatible text model and enter your U9 key and exact model ID.
3. To avoid automatic path completion differences, enable Custom protocol and enter the complete /v1/chat/completions URL. This mode uses the URL as entered.
4. Save, select this custom model in a new task and test a short conversation.

## Configuration values

| Setting | Value |
| --- | --- |
| URL · Custom protocol ON | https://u9ai.ai/v1/chat/completions |
| 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

Custom protocol changes URL handling, not the model protocol. Do not paste a U9 key into a Tencent Token Plan preset. Image and tool capabilities must match the actual model.

## 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

[WorkBuddy](https://www.workbuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Model)