Connect subscriptions, hosted providers, or local inference servers to BitRouter.

A model source is where inference runs and how it is authenticated. BitRouter puts each source behind the same model ids and routing policy, so the calling agent does not need source-specific code.

Claude subscription

Use a Claude Pro or Max login through the claude-code provider.

Codex subscription

Use a ChatGPT Plus or Pro login through the openai-codex provider.

Local inference

Connect Ollama, vLLM, Unsloth, or another OpenAI-compatible server.

Custom provider

Add a hosted API or provider account with a key.

Pick the source shape

Source	Authentication	Setup
Claude or Codex subscription	Provider OAuth	`bro providers login <provider>`
Built-in BYOK provider	Environment variable or stored key	Export its key or use `bro providers login <provider> --api-key ...`
Custom hosted API	API key	Add a `providers:` entry
Local inference server	Usually loopback; optional key	Add a `providers:` entry

Subscription providers do not need a YAML block. Other sources use the same minimal shape:

providers:
  my-source:
    api_base: https://example.com/v1
    api_key: ${MY_SOURCE_API_KEY}
    api_protocol:
      - "*": chat_completions
    models:
      - id: example/model

Use the upstream's actual served model id in models. Keep secrets in environment variables rather than committing them to the file.

Verify a source

bro config validate
bro models --provider my-source
bro route my-source:example/model
bro start

config validate catches malformed configuration and unsafe upstream URLs.
models confirms the source is in the resolved catalog.
route previews resolution without making an inference request.
The provider-qualified form pins one source; the bare model id lets BitRouter select among every source that serves it.

To combine sources, define a virtual model or fallback chain. A common pattern is local inference first and a hosted source second.

Provider selection

Control which eligible source serves a model.

Model fallback

Move to another model or source after an eligible failure.

Supported models

Inspect the generated model and provider catalog.

Model sources