Anthropic

Connect your Anthropic-powered application to Latitude for observability.

Work in progress: Telemetry documentation is still being updated. Integration steps and APIs may be incomplete or out of date. Verify against your SDK versions and check back for revisions.

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses the Anthropic SDK.

You’ll keep calling Anthropic exactly as you do today. Telemetry simply observes and enriches those calls.

---

Requirements

• A Latitude account and API key
• A Latitude project slug
• A project that uses the Anthropic SDK

---

Steps

1. Install

   TypeScript

   npm

   npm install @latitude-data/telemetry
   

   Python

   pip

   pip install latitude-telemetry
   
2. Initialize and use

   TypeScript

   import { initLatitude, capture } from "@latitude-data/telemetry"
   import Anthropic from "@anthropic-ai/sdk"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["anthropic"],
   })
   
   await latitude.ready
   
   const client = new Anthropic()
   
   await capture("generate-reply", async () => {
     const message = await client.messages.create({
       model: "claude-sonnet-4-20250514",
       max_tokens: 1024,
       messages: [{ role: "user", content: "Hello" }],
     })
     return message.content[0].text
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   from anthropic import Anthropic
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["anthropic"],
   )
   
   client = Anthropic()
   
   def generate_reply():
       message = client.messages.create(
           model="claude-sonnet-4-20250514",
           max_tokens=1024,
           messages=[{"role": "user", "content": "Hello"}],
       )
       return message.content[0].text
   
   capture("generate-reply", generate_reply)
   
   latitude.shutdown()
   

---

Streaming

When streaming, consume the stream inside capture() so the span covers the full operation:

TypeScript

await capture("stream-reply", async () => {
  const stream = client.messages.stream({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    messages: [{ role: "user", content: input }],
  })

  for await (const event of stream) {
    if (
      event.type === "content_block_delta" &&
      event.delta.type === "text_delta"
    ) {
      res.write(event.delta.text)
    }
  }
  res.end()
})

Python

def stream_reply():
    with client.messages.stream(
        model="claude-sonnet-4-20250514",
        max_tokens=1024,
        messages=[{"role": "user", "content": input}],
    ) as stream:
        for text in stream.text_stream:
            yield text

capture("stream-reply", stream_reply)

---

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

1. Open your project in the Latitude dashboard
2. Each execution shows input/output messages, model, token usage, latency, and errors

---

That’s It

No changes to your Anthropic calls: just initialize Latitude and your LLM calls are traced.