Skip to main content

​
Quickstart

​
Step 1 — Wrap your client

from tokensense import observe
import anthropic

client = observe(anthropic.Anthropic())

​
Step 2 — Use it exactly as before

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain async/await in Python"}]
)
print(response.content[0].text)

​
Step 3 — See the output

→ ✓ model=claude-sonnet-4-6 | in=18 out=312 tokens | $0.0052 | 847ms
That’s it. One import, one wrapper. Every call is now tracked. Your existing code doesn’t change.