Qwen Code CLI

Qwen Code CLI is a terminal coding agent that speaks the OpenAI API. Three environment variables point it at the gateway.

What you get

• Qwen Code running against any model on the gateway, billed to your project's sponsor budget.

Prerequisites

• Your project access key and base URL from your project control panel — YOUR_PROJECT_KEY and https://v1.opentokenmarket.dev.

• Qwen Code installed:

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

Configure

export OPENAI_BASE_URL="https://v1.opentokenmarket.dev"
export OPENAI_API_KEY="YOUR_PROJECT_KEY"
export OPENAI_MODEL="qwen3-coder-plus"

• OPENAI_BASE_URL includes /v1.
• Set OPENAI_MODEL to any name from the model catalog — it does not have to be a Qwen model.

Put these in your shell profile, or in a .env file that Qwen Code loads from the project directory.

Run

qwen

Verify

curl https://v1.opentokenmarket.dev/chat/completions \
  -H "Authorization: Bearer YOUR_PROJECT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-coder-plus","messages":[{"role":"user","content":"ping"}]}'

Troubleshooting

• 404 on requests — OPENAI_BASE_URL is missing the trailing /v1.
• 401 Unauthorized — OPENAI_API_KEY isn't your project access key.
• model not found — OPENAI_MODEL isn't on this gateway. Check the model catalog.
• budget has been exceeded — ask your sponsor to top up the project.

Which model names to use

OPENAI_MODEL must match the Model name column in the model catalog.