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

# Anthropic SDK

> Audit Anthropic API calls and token usage

<Note>
  **Prefer zero setup?** Use `plog run` or `import provenlog.auto` instead. See [Auto-Instrumentation](/integrations/auto-instrumentation).
</Note>

## Setup

```python theme={null}
from anthropic import Anthropic
from provenlog.integrations.anthropic import Trail

with Trail(agent_id="my-anthropic-agent") as trail:
    client = trail.wrap(Anthropic())
    response = client.messages.create(
        model="claude-sonnet-4-5-20250929",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello!"}]
    )
```

## What gets captured

| Event            | Action Type                 | Details                                      |
| ---------------- | --------------------------- | -------------------------------------------- |
| Message creation | `LLM_CALL`                  | Model, messages, parameters                  |
| Message response | `LLM_RESPONSE`              | Content, token usage, stop reason            |
| Streaming        | `LLM_CALL` / `LLM_RESPONSE` | Same as above, captured on stream completion |

## How it works

The Trail uses transparent method wrapping on the Anthropic client. It intercepts `messages.create()` and `messages.stream()` calls, captures inputs and outputs, and logs them to the audit trail.

The wrapped client behaves identically to the original — ProvenLog never modifies the API call or response.

## Configuration

```python theme={null}
# Simple — uses default embedded mode
trail = Trail(agent_id="my-anthropic-agent")

# With explicit client for custom configuration
from provenlog import ProvenLogClient

client = ProvenLogClient("http://localhost:7600", agent_id="my-agent")
trail = Trail(client=client, agent_id="my-anthropic-agent")
```