Track every OpenAI
call. Know your costs.
Two lines of code. Automatic token tracking, cost attribution, and latency monitoring — across OpenAI, Anthropic, Groq, Gemini, and more. No proxies, zero added latency.
Questions? Reach out at support@tracklyai.in
Everything you need to understand
your AI spend
From zero-config provider detection to per-user cost attribution — Trackly gives you complete visibility without changing how you write code.
Zero-config provider detection
Pass your LLM to trackly.callback() and walk away. Provider resolved from LangChain's class namespace — not guessed from model names — so Groq, Ollama, Together, and Fireworks all work out of the box.
Detected automatically
Cost attribution by feature
See exactly which features are driving your bill. Tag calls with feature= and get a live breakdown.
Latency per model
P50 / P95 tracked per model, per feature.
▲ P95 · gpt-4o · last 24h
P50
198ms
P95
312ms
Per-user cost
Know your most expensive users instantly.
Live model pricing
Cost computed at ingest. Historical events stay accurate when providers change rates.
Cost alerts
Get notified before you overspend.
summarizer hit $20 limit
3× usage in last hour
Rich metadata
Tag any call. Filter anything.
Daily usage trends
30-day rolling view. Spot spikes, monitor growth, export to CSV.
4.8M
+23% vs last month
Start tracking in 6 simple steps
From sign-in to your first tracked LLM call — here's everything you need to get up and running with Trackly.
Sign in & view your Dashboard
Sign in & view your Dashboard
After signing in, you land on the Trackly Dashboard. If you don't have any projects yet, you'll be prompted to create your first one.
Navigate to Projects
Navigate to Projects
Head to Organization Settings → Projects to see all your tracking environments. Each project isolates its data and API keys.
Create a new Project
Create a new Project
Click "+ New Project", give it a name (e.g. "My App"), and hit Launch Project. Projects keep your tracking data cleanly separated.
Go to API Keys
Go to API Keys
Navigate to API Keys from the sidebar. You'll need a key to authenticate your SDK calls from your codebase.
Generate an API Key
Generate an API Key
Click "+ Create API Key", give it a descriptive name, and optionally scope it to a specific project for tighter access control.
Copy your API Key & start tracking
Copy your API Key & start tracking
Your key is generated! Copy it immediately — you won't be able to see it again. Drop it into your environment variables and start tracking.
Simple, transparent pricing
Start free. Scale when you're ready. No hidden fees — just raw performance and deep insights.
Starter
For side projects and experiments.
- 3 Projects
- 7-day log retention
- Basic analytics
- Community support
Pro
For growing teams that need reliable telemetry.
- Unlimited projects
- 30-day log retention
- Advanced analytics
- Team collaboration
- Email support
Scale
Advanced controls for high-volume traffic.
- Everything in Pro
- 90-day log retention
- Custom feature tags
- Priority support
- SLA guarantees
Need more? Contact us for enterprise pricing
Udaykumar Dhokia
Builder of Trackly · Software Developer
Trackly was built out of a real frustration. While working on agentic AI projects, I had no simple way to know how much each feature was costing me — especially when using Groq or Ollama where model names give no hint about the host platform.
I'm a Computer Engineering student from Ahmedabad with a focus on Full Stack Development, Agentic AI, and applied AI systems — RAG, vector search, and LLM tooling.
Got questions?
Let's talk.
Whether it's a bug, a feature request, a partnership idea, or just curiosity about how Trackly works — drop a message and I'll get back to you.