> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/yetone/avante.nvim/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Provider

> Configure Anthropic's Claude models in Avante.nvim

Claude is Anthropic's family of AI models, known for their advanced reasoning capabilities and extended thinking modes. Avante.nvim supports both API key authentication and Claude Pro/Max subscription authentication.

## Quick Start

### API Key Authentication

<Steps>
  <Step title="Get your API key">
    Sign up at [Anthropic Console](https://console.anthropic.com/) and create an API key.
  </Step>

  <Step title="Set environment variable">
    Add to your shell configuration:

    ```sh theme={null}
    # Scoped (recommended)
    export AVANTE_ANTHROPIC_API_KEY=your-api-key

    # Or global
    export ANTHROPIC_API_KEY=your-api-key
    ```
  </Step>

  <Step title="Configure provider">
    ```lua theme={null}
    {
      "yetone/avante.nvim",
      opts = {
        provider = "claude",
      },
    }
    ```
  </Step>
</Steps>

### Claude Pro/Max Subscription

If you have a Claude Pro or Max subscription, you can authenticate using OAuth:

<Steps>
  <Step title="Enable OAuth authentication">
    ```lua theme={null}
    {
      "yetone/avante.nvim",
      opts = {
        provider = "claude",
        providers = {
          claude = {
            auth_type = "max", -- Use "max" for subscription auth
          },
        },
      },
    }
    ```
  </Step>

  <Step title="Authenticate in browser">
    When you open Neovim, the authentication process will start in your browser.
  </Step>

  <Step title="Enter authorization code">
    Copy the code shown in your browser and paste it into the Neovim prompt.
  </Step>
</Steps>

<Note>
  If you previously had a different provider selected, run `:AvanteSwitchProvider claude` to initiate authentication.
</Note>

## Configuration

### Basic Configuration

```lua theme={null}
providers = {
  claude = {
    endpoint = "https://api.anthropic.com",
    model = "claude-sonnet-4-5-20250929",
    timeout = 30000,
    context_window = 200000,
    extra_request_body = {
      temperature = 0.75,
      max_tokens = 64000,
    },
  },
}
```

### Available Models

<CodeGroup>
  ```lua Claude Sonnet 4.5 (Latest) theme={null}
  providers = {
    claude = {
      model = "claude-sonnet-4-5-20250929",
      extra_request_body = {
        max_tokens = 64000,
      },
    },
  }
  ```

  ```lua Claude Opus 4 theme={null}
  providers = {
    claude = {
      model = "claude-3-opus-20240229",
      extra_request_body = {
        max_tokens = 20480,
      },
    },
  }
  ```

  ```lua Claude Haiku 3.5 theme={null}
  providers = {
    ["claude-haiku"] = {
      __inherited_from = "claude",
      model = "claude-3-5-haiku-20241022",
      extra_request_body = {
        max_tokens = 8192,
      },
    },
  }
  ```
</CodeGroup>

### Authentication Types

<CodeGroup>
  ```lua API Key (Default) theme={null}
  providers = {
    claude = {
      auth_type = "api",
    },
  }
  ```

  ```lua Claude Pro/Max Subscription theme={null}
  providers = {
    claude = {
      auth_type = "max",
    },
  }
  ```
</CodeGroup>

## Environment Variables

Claude uses the following environment variables:

| Variable            | Scoped Version             | Purpose            |
| ------------------- | -------------------------- | ------------------ |
| `ANTHROPIC_API_KEY` | `AVANTE_ANTHROPIC_API_KEY` | API authentication |

<Note>
  When using `auth_type = "max"`, API keys are not required as OAuth is used instead.
</Note>

## Advanced Features

### Prompt Caching

Claude supports prompt caching to reduce costs and latency for repeated prompts:

```lua theme={null}
providers = {
  claude = {
    -- Prompt caching is enabled by default
    support_prompt_caching = true,
  },
}
```

Avante automatically applies caching to:

* System prompts
* Tool definitions
* The last text message in history

### Extended Thinking

Claude models support extended thinking for complex reasoning tasks. This is automatically enabled when the model returns thinking content.

```lua theme={null}
-- Thinking is displayed with <think> tags in the output
-- Example:
-- <think>
-- Let me analyze this code structure...
-- </think>
-- 
-- Here's the solution:
```

### Custom Endpoint

For self-hosted or proxy setups:

```lua theme={null}
providers = {
  claude = {
    endpoint = "https://your-custom-endpoint.com",
  },
}
```

### Proxy Configuration

```lua theme={null}
providers = {
  claude = {
    proxy = "http://proxy.example.com:8080",
    allow_insecure = false,
  },
}
```

## Rate Limiting

Claude automatically handles rate limiting by:

1. Detecting rate limit headers
2. Calculating sleep time based on reset timestamps
3. Pausing requests until limits reset

You can monitor rate limits in the response headers:

* `anthropic-ratelimit-tokens-remaining`
* `anthropic-ratelimit-tokens-reset`
* `anthropic-ratelimit-requests-reset`

## Troubleshooting

### Authentication Failed

<AccordionGroup>
  <Accordion title="API Key Not Found">
    Ensure your API key is set in your environment:

    ```sh theme={null}
    echo $ANTHROPIC_API_KEY
    # or
    echo $AVANTE_ANTHROPIC_API_KEY
    ```

    Restart Neovim after setting the variable.
  </Accordion>

  <Accordion title="OAuth Code Invalid">
    If the OAuth code doesn't work:

    1. Ensure you copied the entire code from the browser
    2. Try the authentication flow again
    3. Check that `auth_type = "max"` is set correctly
  </Accordion>

  <Accordion title="Token Expired">
    OAuth tokens are automatically refreshed. If you see expiration errors:

    1. Wait a moment for auto-refresh
    2. Restart Neovim to trigger re-authentication
  </Accordion>
</AccordionGroup>

### Quota Exceeded

If you see quota errors:

```
insufficient_quota: You don't have any credits or have exceeded your quota
```

Check your usage at [Anthropic Console](https://console.anthropic.com/) and add credits or upgrade your plan.

### Temperature Errors

Claude requires temperature between 0 and 1:

```lua theme={null}
extra_request_body = {
  temperature = 0.75, -- Must be 0.0 to 1.0
}
```

## Best Practices

<CardGroup cols={2}>
  <Card title="Model Selection" icon="brain">
    * **Sonnet 4.5**: Best balance of speed and capability
    * **Opus 4**: Maximum capability for complex tasks
    * **Haiku 3.5**: Fastest, best for simple tasks
  </Card>

  <Card title="Token Management" icon="gauge">
    * Use prompt caching for repeated contexts
    * Set appropriate `max_tokens` limits
    * Monitor usage in Anthropic Console
  </Card>

  <Card title="Temperature Settings" icon="temperature-half">
    * `0.0-0.3`: Focused, deterministic responses
    * `0.4-0.7`: Balanced creativity and consistency
    * `0.8-1.0`: More creative and varied responses
  </Card>

  <Card title="OAuth vs API Key" icon="key">
    * **OAuth**: For Claude Pro/Max subscribers
    * **API Key**: For pay-per-use developers
    * Both work with same models
  </Card>
</CardGroup>

## Example Configurations

<CodeGroup>
  ```lua Development Setup theme={null}
  {
    provider = "claude",
    providers = {
      claude = {
        model = "claude-sonnet-4-5-20250929",
        timeout = 30000,
        extra_request_body = {
          temperature = 0.7,
          max_tokens = 32000,
        },
      },
    },
  }
  ```

  ```lua Fast Responses theme={null}
  {
    provider = "claude",
    providers = {
      ["claude-haiku"] = {
        __inherited_from = "claude",
        model = "claude-3-5-haiku-20241022",
        timeout = 15000,
        extra_request_body = {
          temperature = 0.5,
          max_tokens = 8192,
        },
      },
    },
  }
  ```

  ```lua With Subscription theme={null}
  {
    provider = "claude",
    providers = {
      claude = {
        auth_type = "max",
        model = "claude-sonnet-4-5-20250929",
        extra_request_body = {
          temperature = 0.75,
          max_tokens = 64000,
        },
      },
    },
  }
  ```
</CodeGroup>

## Related Resources

* [Anthropic API Documentation](https://docs.anthropic.com/)
* [Model Pricing](https://www.anthropic.com/pricing)
* [Provider Overview](/providers/overview)
* [Custom Providers](/providers/custom-providers)