Appearance
Site language
Price currency
Compatible tools
Terminal agentWorks

Hermes Agent + Evrona

Hermes Agent asks for the address in a wizard and keeps it — editing the config by hand is not required.

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. Run the hermes model command.

  2. Pick the "Custom endpoint" option.

  3. Type in the address with /v1, your key and a Model ID.

hermes model

# Custom endpoint (self-hosted / VLLM / etc.)
API Base URL: https://evrona.ru/v1
API Key:      ev-YOUR_KEY
Model:        google/gemini-3.7-flash
Good to know

The wizard puts the key into ~/.hermes/.env and the settings into ~/.hermes/config.yaml; both files can also be edited by hand, the format is below.

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.