> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# LiteLLM / Bifrost

> Route WednesdayAI through a self-hosted LiteLLM or Bifrost proxy for centralised model management and cost tracking.

# LiteLLM / Bifrost

LiteLLM and Bifrost are self-hosted LLM proxies that sit between WednesdayAI and AI providers. They provide centralised key management, budget limits, usage tracking, and team access control.

## When to use a proxy

* Centralised API-key management for a team
* Per-user or per-team cost tracking
* Enforced model-access policies
* You already run LiteLLM or Bifrost in your infrastructure

## LiteLLM

[LiteLLM](https://github.com/BerriAI/litellm) exposes 100+ models behind a single OpenAI-compatible API. Configure it as a custom provider under `models.providers`:

```json5 theme={"dark"}
{
  agents: {
    defaults: {
      model: { primary: "litellm/claude-sonnet-4-6" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      litellm: {
        baseUrl: "http://localhost:4000",
        apiKey: "${LITELLM_API_KEY}", // references the env var
        api: "openai-completions",
        models: [{ id: "claude-sonnet-4-6", name: "Sonnet via LiteLLM" }],
      },
    },
  },
}
```

<Note>
  Set `LITELLM_API_KEY` in `~/.openclaw/.env` to your LiteLLM master key. The `apiKey` field references the env var — keep the actual key out of committed config files.
</Note>

The model reference must match how the model is configured in LiteLLM.

## Bifrost

Bifrost is WednesdayAI's native LLM-proxy integration. When requests route through Bifrost, the gateway captures the actual provider and model from the `x-bifrost-provider` and `x-bifrost-model` response headers and records them in run metadata — useful for auditing which backend handled each request.

```json5 theme={"dark"}
{
  agents: {
    defaults: {
      model: { primary: "bifrost/anthropic/claude-sonnet-4-6" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      bifrost: {
        baseUrl: "http://bifrost.internal:8080",
        apiKey: "your-bifrost-key",
        api: "openai-completions",
        models: [{ id: "anthropic/claude-sonnet-4-6", name: "Sonnet via Bifrost" }],
      },
    },
  },
}
```

Header capture comes from the bundled Bifrost extension. To enable it, run the interactive auth flow and select **Proxy / Gateway → Bifrost**:

```bash theme={"dark"}
openclaw auth
# choose: Proxy / Gateway → Bifrost
```

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection refused">
    The proxy is not running. Confirm LiteLLM or Bifrost is up and listening on the configured port.
  </Accordion>

  <Accordion title="401 from the proxy">
    The `apiKey` does not match the proxy's master key. Update the provider's `apiKey`.
  </Accordion>

  <Accordion title="Model not found">
    The model `id` must match exactly how it is configured in the proxy. Check the proxy's model list or admin UI.
  </Accordion>
</AccordionGroup>