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

# Anthropic SDK

> Automatically trace supported direct Anthropic SDK calls with PromptLayer.

PromptLayer can auto-instrument the official Anthropic SDK and export supported calls as OpenTelemetry spans. Each supported direct SDK call appears in PromptLayer as both a trace span and an associated request log without changing how you create or use the Anthropic client.

<Note>
  This guide covers the Anthropic model SDK. If you use the Claude Agent SDK or Claude Code, follow the [Claude integration](/features/observability/traces/integrations#claude-code) instead.
</Note>

## Supported APIs

| API surface                                   | Python                                                                                  | JavaScript                                      |
| --------------------------------------------- | --------------------------------------------------------------------------------------- | ----------------------------------------------- |
| Messages (`messages.create`)                  | Supported (sync and async)                                                              | Supported                                       |
| Messages streaming                            | Supported (`messages.create(..., stream=True)` and `messages.stream()`; sync and async) | Supported (`messages.create({ stream: true })`) |
| Structured message parsing (`messages.parse`) | Supported (sync and async)                                                              | Not supported                                   |
| Beta Messages                                 | Not documented                                                                          | Supported                                       |
| Beta Messages streaming                       | Not documented                                                                          | Supported                                       |
| Anthropic Vertex                              | Supported                                                                               | Supported                                       |

`Not documented` means the surface is outside the verified coverage for that language.

The Anthropic Bedrock client is not included in this provider integration. To trace direct Boto3 or AWS SDK v3 Bedrock Runtime calls, follow the [AWS Bedrock guide](/features/observability/traces/auto-instrumentation/bedrock). Other Anthropic SDK calls continue to work normally, but unsupported surfaces do not automatically create PromptLayer traces or request logs.

## Prerequisites

* A [PromptLayer API key](/quickstart#prerequisites) for the workspace that should receive the traces
* An Anthropic API key, or the standard Google Cloud credentials and project configuration for Anthropic Vertex
* Python 3.10 or later for Python, or Node.js 20 or later for JavaScript

Export the direct Anthropic API keys before the application starts:

```bash theme={null}
export PROMPTLAYER_API_KEY="pl_..."
export ANTHROPIC_API_KEY="sk-ant-..."
```

PromptLayer captures supported message content by default. Review the [content-capture behavior and opt-out values](/features/observability/traces/auto-instrumentation/overview#capture-prompts-and-responses) before sending provider requests.

## Python

### 1. Install the SDKs

```bash theme={null}
pip install "promptlayer[otel-genai-instrumentation]" anthropic
```

Install Anthropic's Vertex dependencies if your application uses `AnthropicVertex`.

### 2. Configure Anthropic instrumentation

```python theme={null}
from anthropic import Anthropic
from promptlayer import configure_tracing

tracer_provider = configure_tracing(providers=("anthropic",))
client = Anthropic()

try:
    message = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=256,
        messages=[
            {
                "role": "user",
                "content": "Explain distributed tracing in one sentence.",
            }
        ],
    )
    print(message.content[0].text)
finally:
    client.close()
    tracer_provider.force_flush()
```

The same `anthropic` selector instruments `AnthropicVertex`. Sync and async clients are supported.

<Accordion title="Use an existing PromptLayer client">
  If your application already creates a PromptLayer client, select Anthropic when enabling tracing:

  ```python theme={null}
  from anthropic import Anthropic
  from promptlayer import PromptLayer

  pl = PromptLayer(
      enable_tracing=True,
      tracing_providers=("anthropic",),
  )
  client = Anthropic()
  ```

  Omit `tracing_providers` to instrument every supported provider SDK that is installed.
</Accordion>

## JavaScript

### 1. Install the SDKs

```bash theme={null}
npm install promptlayer @anthropic-ai/sdk
```

For Anthropic Vertex, also install `@anthropic-ai/vertex-sdk`.

### 2. Preload PromptLayer instrumentation

The preload must run before the application imports the Anthropic SDK:

```bash theme={null}
node --import promptlayer/register app.mjs
```

### 3. Use the Anthropic SDK normally

```javascript theme={null}
import Anthropic from "@anthropic-ai/sdk";
import { shutdownTracing } from "promptlayer";

const client = new Anthropic();

try {
  const message = await client.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 256,
    messages: [
      {
        role: "user",
        content: "Explain distributed tracing in one sentence.",
      },
    ],
  });
  console.log(message.content);
} finally {
  await shutdownTracing();
}
```

The preload instruments every supported provider. To instrument only Anthropic, call `configureTracing({ providers: ["anthropic"] })` in a bootstrap module and dynamically import the application afterward. See [Select Providers](/features/observability/traces/auto-instrumentation/overview#select-providers).

## Verify the Integration

Run one supported Anthropic request, flush or shut down tracing, and open [Traces](/features/observability/traces) in PromptLayer. The Anthropic span should have an associated request log.

If no span appears:

* Confirm instrumentation is configured before the first Anthropic request.
* In JavaScript, confirm the preload or bootstrap runs before the Anthropic SDK module loads.
* Confirm the call uses an API surface listed in [Supported APIs](#supported-apis).
* Confirm `PROMPTLAYER_API_KEY` belongs to the workspace you are checking.
* Flush or shut down tracing before a short-lived process exits.