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

# Anthropic

> Use Anthropic's Claude models directly — the default and recommended LLM provider.

Anthropic is the **default and recommended** LLM provider for MergeWatch. It offers the simplest setup — just add your API key and you are ready to go. Works on every platform (Docker, AWS, GCP, bare metal).

## Configuration

Set these environment variables in your `.env` file or container environment:

| Variable            | Required | Value                                                        |
| ------------------- | -------- | ------------------------------------------------------------ |
| `LLM_PROVIDER`      | Yes      | `anthropic`                                                  |
| `ANTHROPIC_API_KEY` | Yes      | Your Anthropic API key                                       |
| `LLM_MODEL`         | Yes      | Anthropic model ID to use (e.g., `claude-sonnet-4-20250514`) |

<Note>
  When `LLM_PROVIDER=anthropic`, you **must** set `LLM_MODEL` to an Anthropic-native model ID. The built-in defaults (`us.anthropic.claude-sonnet-4-20250514-v1:0` for the primary model and `us.anthropic.claude-haiku-4-5-20251001-v1:0` for the light model) are [Bedrock inference profile IDs](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles.html) and are not valid on the Anthropic API.
</Note>

## Model roles

MergeWatch uses two model slots per review:

* **Primary model** (`model` in `.mergewatch.yml`) — runs the agent pipeline (security, bugs, style, error handling, test coverage, comment accuracy). Use **Claude Sonnet 4** for the best review quality.
* **Light model** (`lightModel` in `.mergewatch.yml`) — runs the summary and diagram passes. **Claude Haiku 4.5** is a good cost-optimized choice here.

Setting `LLM_MODEL` overrides **both** slots with the same model. For split primary/light models, configure them in `.mergewatch.yml` instead — see [mergewatch.yml reference](/configuration/mergewatch-yml).

## Example `.env` file

```bash theme={null}
# LLM Provider
LLM_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-api03-...

# Pick a model — Sonnet for the highest review quality
LLM_MODEL=claude-sonnet-4-20250514
```

## Model suggestions

| Anthropic model ID          | Best for                                                      |
| --------------------------- | ------------------------------------------------------------- |
| `claude-sonnet-4-20250514`  | Recommended. Highest review quality for deep agent analysis.  |
| `claude-haiku-4-5-20251001` | Cost-optimized. Faster and cheaper; good for summary/diagram. |

## Pricing

You pay Anthropic directly for API usage. MergeWatch does not add any markup or proxy fees. See the [Anthropic pricing page](https://www.anthropic.com/pricing#702702) for current per-token rates.

## Next steps

<CardGroup cols={2}>
  <Card title="Configure review behavior" icon="sliders" href="/configuration/review-behavior">
    Tune sensitivity, ignored paths, and review focus areas.
  </Card>

  <Card title="LiteLLM Proxy" icon="shuffle" href="/self-hosting/llm-providers/litellm">
    Use OpenAI, Azure, Gemini, or 100+ other providers via LiteLLM.
  </Card>

  <Card title="Environment variables" icon="gear" href="/reference/env-vars">
    Full list of supported environment variables.
  </Card>

  <Card title="Platform guides" icon="server" href="/self-hosting/platforms/google-cloud-run">
    Deploy MergeWatch on your platform of choice.
  </Card>
</CardGroup>