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

# OpenRouter

> Access hundreds of AI models through a single API key with OpenRouter.

## What it's good for

Widest model selection available — access Claude, GPT-4, Llama, Mistral, and hundreds more through one API key. Good for trying different models without managing separate accounts, or for accessing models not directly supported by Spaceduck's other providers.

## Requirements

* An OpenRouter account and API key
* Sign up and get your key at [openrouter.ai/keys](https://openrouter.ai/keys)

## Configure in Spaceduck

### Chat

<Steps>
  <Step title="Set your API key">
    In **Settings > Chat**, select **OpenRouter** as the provider, then enter your API key.

    Or via CLI:

    ```bash theme={null}
    spaceduck config secret set /ai/secrets/openrouterApiKey
    ```
  </Step>

  <Step title="Select a model">
    In **Settings > Chat**:

    * **Provider**: OpenRouter
    * **Model**: use the OpenRouter model ID, e.g.:
      * `anthropic/claude-3.5-sonnet`
      * `meta-llama/llama-3.1-70b-instruct`
      * `mistralai/mistral-large-latest`

    Or via CLI:

    ```bash theme={null}
    spaceduck config set /ai/provider openrouter
    spaceduck config set /ai/model "anthropic/claude-3.5-sonnet"
    ```

    <Tip>
      Browse available models and pricing at [openrouter.ai/models](https://openrouter.ai/models).
    </Tip>
  </Step>

  <Step title="Verify">
    Send a message in the chat. You should see a streaming response.
  </Step>
</Steps>

### Embeddings

OpenRouter does not provide an embeddings API. If you want semantic recall, pair OpenRouter with a separate embedding provider:

* **Local**: [llama.cpp embeddings](/providers/llamacpp#embeddings) or LM Studio
* **Cloud**: Bedrock (Titan) or Gemini (`text-embedding-004`)

This is the [two-server pattern](/providers/overview#the-two-server-pattern) — chat on OpenRouter, embeddings elsewhere.

## Test and troubleshoot

| Problem                 | Cause                 | Fix                                                                   |
| ----------------------- | --------------------- | --------------------------------------------------------------------- |
| `401 Unauthorized`      | Invalid API key       | Check your key at [openrouter.ai/keys](https://openrouter.ai/keys)    |
| `402 Payment Required`  | Insufficient credits  | Add credits at [openrouter.ai/credits](https://openrouter.ai/credits) |
| Model not found         | Wrong model ID format | Use the full `org/model-name` format from OpenRouter's model list     |
| `429 Too Many Requests` | Rate limit hit        | Wait and retry, or use a different model                              |