Skip to main content

Getting Started

CostKey is an SDK that auto-tracks every AI API call's cost, tokens, and latency. One line of code, zero wrappers, zero proxies.

Install​

pip install costkey

Initialize​

Get your DSN from the CostKey dashboard or by running costkey init my-project.

import costkey

costkey.init(
    dsn="https://ck_your_key@app.costkey.dev/your_project_id",
    release="v1.0.0",  # Track cost per deploy
)

That's it​

Every AI API call your app makes is now tracked automatically. No wrappers, no decorators, no code changes.

import costkey
from anthropic import Anthropic

costkey.init(dsn="https://ck_your_key@app.costkey.dev/your_project_id")

client = Anthropic()

# This call is automatically tracked — cost, tokens, latency, stack trace
response = client.messages.create(
    model="claude-sonnet-4-5-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain quantum computing in one paragraph"}],
)
print(response.content[0].text)

Open the dashboard and you'll see:

  • Cost per call, calculated server-side from the model and token count
  • Token usage (input, output, cache, reasoning tokens)
  • Latency and streaming metrics (TTFT, tokens/sec)
  • Stack trace showing which function in your code made the call
  • Call site grouping so you can see which parts of your code cost the most
  • Body capture — inspect the exact prompt and completion for any call
  • Cost per deploy — set release to see how costs change across deployments
  • Executive summary — a plain-English summary of your AI spend for stakeholders

Add context​

Tag calls with metadata to slice costs by feature, team, or user.

with costkey.with_context(task="summarize", team="search", user_id="u_123"):
    response = client.messages.create(
        model="claude-sonnet-4-5-20250514",
        max_tokens=1024,
        messages=[{"role": "user", "content": f"Summarize: {document}"}],
    )

Group calls into traces​

When a single user action triggers multiple AI calls, group them with start_trace.

with costkey.start_trace(name="POST /api/search"):
    intent = classify_intent(query)       # AI call 1
    results = search(query, intent)       # AI call 2
    summary = summarize(results)          # AI call 3
    # All 3 calls appear as one trace in the dashboard

Shut down cleanly​

Before your process exits, flush any pending events.

costkey.shutdown()

Next steps​