Appearance
Site language
Price currency
Compatible tools
Terminal agentWorks

Aider + Evrona

Aider changes code in your repository and commits by itself. Address and key are set through environment variables.

What to prepare

Base URLGateway address
https://evrona.ru/v1
Your API keyExample; yours is in the dashboard
ev-YOUR_KEY
Model IDAny catalog model
google/gemini-3.7-flash

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

  1. Set OPENAI_API_BASE and OPENAI_API_KEY — either in the shell or in the project .env.

  2. Launch aider, adding the openai/ prefix to the Model ID.

  3. After that the usual routine: /add files, state the task, /diff to look at the edits.

terminal
export OPENAI_API_BASE="https://evrona.ru/v1"
export OPENAI_API_KEY="ev-YOUR_KEY"

aider --model openai/openai/gpt-6-astra
Good to know

The prefix looks doubled — openai/openai/gpt-6-astra. That is right: the first openai/ tells aider to speak the OpenAI-compatible protocol, and everything after it arrives to us as the Model ID.

Gateway capabilities and limits

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.