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

# Anthropic Proxy API

> Use WhyOps as a drop-in proxy for the Anthropic API when you are not using one of the published WhyOps SDK packages.

WhyOps supports Anthropic's Claude models via a drop-in API proxy. You can use the official Anthropic SDKs by pointing the `baseURL` to the WhyOps proxy and using your WhyOps API Key.

<CardGroup cols={2}>
  <Card title="Use the TypeScript SDK" icon="code" href="/docs/integrations/typescript-sdk">
    Prefer `@whyops/sdk` if you want Anthropic proxy patching plus manual runtime traces from one client.
  </Card>

  <Card title="Use the Python SDK" icon="terminal" href="/docs/integrations/python-sdk">
    Prefer `whyops` if you want the same Anthropic proxy flow with sync and async instrumentation helpers.
  </Card>
</CardGroup>

## Setup

1. **Obtain API Keys**:
   * Get an API key from your [WhyOps Dashboard](https://app.whyops.com).
   * Add your Anthropic API key in the **Providers** section of the WhyOps Dashboard.

2. **Configure SDK**:

<Tabs>
  <Tab title="TypeScript">
    ```typescript theme={null}
    import Anthropic from '@anthropic-ai/sdk';

    const anthropic = new Anthropic({
      apiKey: process.env.WHYOPS_API_KEY, // Your WhyOps API Key
      baseURL: 'https://proxy.whyops.com', // The WhyOps Proxy URL
      defaultHeaders: {
        'X-Agent-Name': 'research-agent' // Required: Identifies the agent
      }
    });

    // Proceed as normal
    const msg = await anthropic.messages.create({
      model: 'claude-3-5-sonnet-20241022',
      max_tokens: 1000,
      messages: [{ role: 'user', content: 'Analyze this dataset.' }],
    });
    ```
  </Tab>

  <Tab title="Python">
    ```python theme={null}
    import os
    from anthropic import Anthropic

    client = Anthropic(
      api_key=os.environ.get("WHYOPS_API_KEY"),
      base_url="https://proxy.whyops.com",
      default_headers={
        "X-Agent-Name": "research-agent"
      }
    )

    message = client.messages.create(
      max_tokens=1000,
      messages=[
        {
          "role": "user",
          "content": "Analyze this dataset.",
        }
      ],
      model="claude-3-5-sonnet-20241022",
    )
    ```
  </Tab>
</Tabs>

## Supported Endpoints

The proxy fully supports and parses the following Anthropic endpoints:

* **`/messages`**: Standard message creation, including streaming, tool calling, and Claude's extended thinking (chain of thought).

## How WhyOps handles Anthropic Data

1. **Extended Thinking**: WhyOps fully supports Anthropic's `<thinking>` blocks. When using models like Claude 3.5 Sonnet or Opus, WhyOps parses and captures these internal reasoning steps as discrete `llm_thinking` events in your decision graph.
2. **Streaming Parsing**: If you use the streaming API, WhyOps uses a custom SSE parser (`AnthropicParser`) to reconstruct the full message, tool calls, and thinking blocks as they stream back to your application, ensuring zero added latency.
3. **Trace IDs**: WhyOps automatically handles trace grouping across Anthropic message arrays.