onomeoonomeoBeta
Feedback
All tools

Use onomeo in Qwen Code

Qwen Code is a coding agent that works in the terminal, and it has a form of its own for adding a provider. Follow the four steps below to add this site and use its models.

A coding agent for the terminal, from the Qwen team.

The three values it asks for

OpenAI-compatible

Use these details in any OpenAI-compatible tool.

Base URL
https://onomeo.com/v1
API key
Model

No key yet? Create one on the My account page, then come back — the fields below fill in by themselves. Go to My account

Step by step

  1. Install Qwen Code

    On Windows, press the Windows key, type PowerShell and press Enter. On macOS, open Terminal. Paste the line below and press Enter.

    npm install -g @qwen-code/qwen-code@latest

    Qwen Code needs Node.js 22 or newer. If npm is not found, install Node.js (the LTS version) from nodejs.org first, then close PowerShell and open it again.

  2. Start it and choose Custom Provider

    Go to your project folder first (for example, type cd D:\my-project and press Enter), then run the line below. The first start shows Connect a Provider: press the down arrow key twice to reach Custom Provider, then press Enter. If that menu does not appear, type /auth and press Enter.

    qwen
    Qwen Code's Connect a Provider menu with Custom Provider highlighted
    Choose the last entry, Custom Provider.

    Started inside an editor's terminal, Qwen Code first asks whether to connect the editor; either answer works.

  3. Answer the seven questions

    Protocol: OpenAI-compatible is already selected, press Enter. API: Chat Completions is already selected, press Enter. Base URL: paste the address below and press Enter. API Key: paste your key (copy it from "The three values it asks for" above) and press Enter. Model IDs: type auto and press Enter. Advanced Config: press Enter. The last one shows the settings it will save: press Enter. Qwen Code then says Successfully configured Custom Provider.

    https://onomeo.com/v1

  4. Give it a task

    Type what you want done and press Enter. Qwen Code writes files and runs commands in that folder by itself.

    Qwen Code wrote hello.py, ran it and reports that it prints Hello from onomeo
    Here it was asked to create hello.py: it wrote the file, ran it to check, and reported the output.

    The top box and the bottom line read coder-model. That is Qwen Code's own label; the requests go to the model you entered, auto. In its Auto mode, Qwen Code also checks each step with an extra request, so a task takes more calls. Measured on 9 October 2026 with Qwen Code 0.25.0: the task above took 7 calls on auto and was not charged.

If it will not connect

  • Keep /v1 on the end of the Base URL and add nothing after it; Qwen Code adds /chat/completions itself.
  • To use more than one model, separate them with commas under Model IDs, then switch between them with /model.
  • Coding sends whole files along with each request. On free models that is not charged, but a long request counts as several calls; Claude, GPT and other big models are charged by usage, and the balance goes quickly.
  • 401: the key is wrong; type /auth and go through Custom Provider again with the right key. 402: insufficient balance. Claude, GPT and other big models are charged by usage; top up on the Pricing page or switch to a free model.
  • Once your own provider keys are connected on the My providers page, enter my/<provider>/<model> under Model IDs to answer on your own allowance instead. Nothing else changes, and this site does not charge for these calls.
Qwen Code's own documentation