Qwen Code + Evrona
Qwen Code takes its settings from a .env file or asks for them with the /auth command.
What to prepare
No key yet? Create an account — keys are created in the dashboard under “API keys”, and the full value is shown only once. Copy the Model ID from the catalog in full, including the prefix before “/”.
Connection steps
Create .qwen/.env in the project folder — that is where Qwen Code looks first, then at .env up the tree and at ~/.qwen/.env.
Move the three variables from the block below into it.
Launch qwen; the model can be swapped later with /model.
OPENAI_BASE_URL="https://evrona.ru/v1"
OPENAI_API_KEY="ev-YOUR_KEY"
OPENAI_MODEL="google/gemini-3.7-flash"The interactive route leads to the same result: launch qwen, run /auth and choose Custom Provider.
Function calling is supported, so agentic modes work. Strict JSON mode (response_format) and the retired functions format are turned down with an unsupported_parameter error — no parameter is lost in silence. Image input is taken by models marked "Understands images" in the catalog: 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 returns unsupported_capability — both errors name the reason outright.