Stop guessing
your LLM costs.
Track every API call, monitor costs in real-time, and get alerts before your budget runs out. One line of code.
uv add costrace / npm install costrace
// integrations
// features
Everything you need to
control LLM costs
Real-time Cost Tracking
Track every API call across OpenAI, Anthropic, and Gemini. See costs broken down by model, team, and project with zero configuration.
$12.4K
tracked this month
Latency Monitoring
Monitor response times across all your LLM providers. Identify slow endpoints and optimize your AI pipeline performance.
142ms
avg response time
Geographic Insights
See where your API calls originate. Understand geographic distribution patterns and optimize for latency and compliance.
14
regions tracked
// setup
Two lines of code.
That's the entire setup.
Install the SDK
Add Costrace to your project with a single command.
uv add costracebashInitialize with one line
Pass your API key and you're ready to go.
costrace.init(api_key="ct_...")pythonView your dashboard
Traces appear automatically as you call OpenAI, Anthropic, or Gemini.
# That's it. No other config.python// integration
One line. Every provider.
Add Costrace to your project and every LLM API call is tracked automatically. No wrappers, no config files.
import costrace
from openai import OpenAI
costrace.init(api_key="ct_your_api_key")
# Use OpenAI as you normally would
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
# Cost, latency, and tokens tracked automatically// pricing
Start free. Scale when ready.
Free
For side projects and experimentation
Pro
For teams shipping AI to production