> ## 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.

# Bifrost

> Route WednesdayAI through Bifrost AI — an LLM proxy with routing, caching, fallbacks, and cost tracking.

# Bifrost

[Bifrost](https://github.com/maximhq/bifrost) is an LLM proxy that routes requests to multiple backends — Anthropic, OpenAI, Bedrock, Gemini, Ollama, and more — with routing rules, prompt cache optimisation, semantic caching, fallback chains, and cost tracking.

WednesdayAI communicates with Bifrost as a single provider (`bifrost`) using an OpenAI-compatible API. Bifrost handles all model-specific logic internally.

<Note>
  Bifrost is self-hosted. You must run a Bifrost instance (locally or on your own infrastructure) before configuring WednesdayAI to use it.
</Note>

## Prerequisites

* A running Bifrost instance. See the [Bifrost documentation](https://github.com/maximhq/bifrost) for setup.
* Optionally, a Bifrost virtual key for authentication.

## Quick setup

### 1. Start Bifrost

Follow the [Bifrost setup guide](https://github.com/maximhq/bifrost) to start your instance and note its base URL.

### 2. Configure WednesdayAI

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

Enter your base URL, optional virtual key, and the model aliases you want available (e.g. `medium`, `fast`, `anthropic/claude-sonnet-4-6`).

### 3. Manual config snippet

```json5 theme={"dark"}
{
  models: {
    providers: {
      bifrost: {
        baseUrl: "http://localhost:8080", // your Bifrost instance URL
        apiKey: "BIFROST_API_KEY",        // optional virtual key; omit if not used
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "bifrost/medium" }, // routing alias defined in Bifrost
    },
  },
}
```

<Note>
  `apiKey` is the name of the environment variable, not the key value itself. Keep secrets in `.env`, not in committed config files.
</Note>

## Model aliases vs direct model IDs

You can use either:

* **Routing aliases** (`medium`, `fast`) — Bifrost maps these to real models via its routing rules.
* **Direct model IDs** (`anthropic/claude-sonnet-4-6`) — bypasses routing and targets that model directly.

Bifrost decides which backend and model to use. WednesdayAI does not influence routing.

## Provider settings

| Setting         | Value                        |
| --------------- | ---------------------------- |
| Provider ID     | `bifrost`                    |
| API             | OpenAI-compatible            |
| Auth env var    | `BIFROST_API_KEY` (optional) |
| Default timeout | 600 seconds                  |

## Usage dashboard

When Bifrost is configured to forward response headers, WednesdayAI records both the configured alias and the actual backend provider/model per call:

* `byProvider` shows actual provider spend (e.g. `anthropic: $0.42`)
* `byConfiguredModel` shows spend by alias (e.g. `medium: $0.42`)

## Caching

Bifrost's prompt cache optimisation and semantic cache run on the Bifrost side. WednesdayAI does not send `cache_control` markers to Bifrost — Bifrost's `CacheOptimizer` analyses request structure autonomously.

## Verification

```bash theme={"dark"}
openclaw models status --probe-provider bifrost
```

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection refused">
    Verify your Bifrost instance is running and the `baseUrl` in your config matches its address and port.
  </Accordion>

  <Accordion title="Agent stalls after first turn">
    This is an upstream provider defect, not a WednesdayAI or Bifrost bug. Some backends (observed on Cloudflare- and Parasail-hosted vLLM endpoints) emit `finish_reason=tool_calls` without the accompanying tool-call chunks.

    **Fix:** Exclude the offending upstreams at the Bifrost routing layer — pin routes to compliant backends (e.g. SiliconFlow) and exclude non-compliant ones (e.g. Cloudflare).
  </Accordion>

  <Accordion title="401 Unauthorized">
    If you configured a virtual key, verify `BIFROST_API_KEY` is set correctly in `~/.openclaw/.env`.
  </Accordion>
</AccordionGroup>

## Related

* [AI providers overview](/admin/providers/index)
* [Reference: config](/reference/config)