provod.ai / docs
Integrations

Hermes Agent

Connect an installed Hermes Agent to the provod.ai API through Chat Completions.

Last updated on

Configuration checks and catalog reads do not create a generation. Sample model requests below are optional and use your balance; run them only intentionally.

Hermes needs a model with tools and a context window of at least 64,000 tokens. Check the detected context size during setup.

Prepare a key and balance

This guide starts with an installed Hermes Agent. The hermes command must be available in your terminal.

In API keys, select Create key, name it Hermes, and immediately copy the full value: it is not shown again. Keep the key and local files containing it out of repositories.

Open Balance, select Top up balance, choose a payment method and amount, complete payment, and check the available funds. The key and balance must belong to the same workspace. See API authentication and balance funding for details.

Configure the provider

If a Hermes chat is open, exit it with /quit first. Run in your terminal:

Terminal
hermes model

Select Custom endpoint (enter URL manually) and fill in the wizard. Use the option name: its number depends on the version and saved providers.

FieldValue
API base URLhttps://api.provod.ai/v1
API keyThe full provod.ai key
API compatibility modeChat Completions

Select a model

The wizard retrieves Available models through GET /v1/models.

  • Select model: the exact ID of an available text model with tools support. Check capabilities in the model catalog.
  • Context length in tokens: press Enter for automatic detection.
  • Display name: enter Provod.ai and press Enter to save.

Verify the connection

Terminal
hermes config get model.base_url
hermes config get model.default
hermes config get model.api_mode

Expected values: https://api.provod.ai/v1, your selected model ID, and chat_completions.

Terminal
hermes

Send Reply with ok. A model response confirms that the request completed; saving settings or retrieving the catalog alone does not.

Troubleshooting

On this page