OpenClaw + Evrona
OpenClaw stands between messengers and the model. Address and key lie in openclaw.json.
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
Open ~/.openclaw/openclaw.json, or whichever file OPENCLAW_CONFIG names.
Fill in baseUrl and apiKey on the openai provider.
For the agent's model, name the provider and our Model ID joined by a slash.
{
"models": {
"providers": {
"openai": {
"baseUrl": "https://evrona.ru/v1",
"apiKey": "ev-YOUR_KEY"
}
}
},
"agents": {
"defaults": { "model": "openai/google/gemini-3.7-flash" }
}
}The prefix doubles up: openai/ is the provider name inside OpenClaw, while our Model ID already starts with the vendor. The same two values can be given through OPENAI_API_BASE and OPENAI_API_KEY.
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.