Qwen Code

Coding CLI tool. Compatible with the ApiMira OpenAI endpoint.

Qwen Code reads its settings from a .env file or asks for them with the /auth command.

What you need

Base URL

https://apimira.com/v1

API key

am-YOUR_KEYCreated in the dashboard, the API keys section. The full value is shown once.

Model ID

google/gemini-3.7-flashCopy it from the catalogue in full, including the prefix before the slash.

How to connect

1. 1Create .qwen/.env in the project folder — Qwen Code looks there first, then .env up the tree and ~/.qwen/.env.
2. 2Add the three variables from the block below.
3. 3Run qwen; you can switch models later with /model.

OPENAI_BASE_URL="https://apimira.com/v1"
OPENAI_API_KEY="am-YOUR_KEY"
OPENAI_MODEL="google/gemini-3.7-flash"

The interactive path gives the same result: run qwen, execute /auth and pick Custom Provider.

Function calling is supported, so agentic modes work. Strict JSON mode (response_format) and the retired functions format are rejected with an unsupported_parameter error — the parameter is never silently dropped. Image input is accepted by models marked "Sees images" on the Models page: a content part of type image_url with a data:image/png;base64,… URL (PNG, JPEG or WebP, up to 5 MB each, up to 50 per request). Remote URLs are not fetched, and a model without that mark answers with unsupported_capability — both errors name the reason outright.