Skip to main content

Chutes

Chutes exposes open-source model catalogs through an OpenAI-compatible API. Velaclaw supports both browser OAuth and direct API-key auth for the bundled chutes provider.

Getting started

1

Run the OAuth onboarding flow

Velaclaw launches the browser flow locally, or shows a URL + redirect-paste flow on remote/headless hosts. OAuth tokens auto-refresh through Velaclaw auth profiles.
2

Verify the default model

After onboarding, the default model is set to chutes/zai-org/GLM-4.7-TEE and the bundled Chutes catalog is registered.
Both auth paths register the bundled Chutes catalog and set the default model to chutes/zai-org/GLM-4.7-TEE. Runtime environment variables: CHUTES_API_KEY, CHUTES_OAUTH_TOKEN.

Discovery behavior

When Chutes auth is available, Velaclaw queries the Chutes catalog with that credential and uses the discovered models. If discovery fails, Velaclaw falls back to a bundled static catalog so onboarding and startup still work.

Default aliases

Velaclaw registers three convenience aliases for the bundled Chutes catalog:

Built-in starter catalog

The bundled fallback catalog includes current Chutes refs:

Config example

You can customize the OAuth flow with optional environment variables:See the Chutes OAuth docs for redirect-app requirements and help.
  • API-key and OAuth discovery both use the same chutes provider id.
  • Chutes models are registered as chutes/<model-id>.
  • If discovery fails at startup, the bundled static catalog is used automatically.

Model providers

Provider rules, model refs, and failover behavior.

Configuration reference

Full config schema including provider settings.

Chutes

Chutes dashboard and API docs.

Chutes API keys

Create and manage Chutes API keys.