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

# Anthropic (TypeScript)

> Trace Claude API calls in TypeScript

## Installation

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

## Quick Start

```typescript theme={null}
import fallom from "@fallom/trace";
import Anthropic from "@anthropic-ai/sdk";

// Initialize Fallom once at app startup
await fallom.init({ apiKey: process.env.FALLOM_API_KEY });

// Create a session for this conversation/request
const session = fallom.session({
  configKey: "my-app",
  sessionId: "session-123",
  customerId: "user-456",
});

// Wrap your Anthropic client
const anthropic = session.wrapAnthropic(new Anthropic());

// Use as normal - automatically traced!
const response = await anthropic.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.content[0].text);
```

## With System Prompt

```typescript theme={null}
const response = await anthropic.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  system: "You are a helpful assistant who speaks like a pirate.",
  messages: [{ role: "user", content: "Tell me about the weather." }],
});
```

## Streaming

```typescript theme={null}
const stream = await anthropic.messages.stream({
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a poem about coding." }],
});

for await (const event of stream) {
  if (event.type === "content_block_delta") {
    process.stdout.write(event.delta.text || "");
  }
}
```

## With Extended Thinking

```typescript theme={null}
const response = await anthropic.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 16000,
  thinking: {
    type: "enabled",
    budget_tokens: 10000,
  },
  messages: [{ role: "user", content: "Solve this complex problem..." }],
});

// Access thinking and response
const thinking = response.content.find((c) => c.type === "thinking");
const text = response.content.find((c) => c.type === "text");
```

## Model A/B Testing

```typescript theme={null}
import fallom from "@fallom/trace";
import Anthropic from "@anthropic-ai/sdk";

await fallom.init({ apiKey: "your-fallom-api-key" });

const session = fallom.session({
  configKey: "my-experiment",
  sessionId: "session-123",
});

const anthropic = session.wrapAnthropic(new Anthropic());

// Get assigned model for this session
const modelId = await session.getModel({ fallback: "claude-sonnet-4-20250514" });

const response = await anthropic.messages.create({
  model: modelId,
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});
```

## What Gets Traced

| Field       | Description                      |
| ----------- | -------------------------------- |
| Model       | `claude-sonnet-4-20250514`, etc. |
| Duration    | Total request time (ms)          |
| Tokens      | Input, output tokens             |
| Cost        | Calculated from token usage      |
| Prompts     | System + user messages           |
| Completions | Model response                   |
| Session     | Your config key + session ID     |

## Next Steps

<CardGroup cols={2}>
  <Card title="Model A/B Testing" icon="flask" href="/model-testing">
    Compare Claude models in production.
  </Card>

  <Card title="OpenAI" icon="microchip" href="/integrations/typescript/openai">
    Also using OpenAI? See that guide.
  </Card>
</CardGroup>