New to Metrx? This guide will have you tracking AI costs in under 5 minutes.
1. Get an API Key
Sign up at app.metrxbot.com and generate an API key from your organization settings. Your API key grants access to the Gateway.
2. Choose Your Integration Method
The Gateway is a drop-in replacement for your existing LLM API calls. Route through Metrx with minimal code changes:
# Instead of calling OpenAI directly:
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer sk_openai_xxxx" \
...
# Route through Metrx:
curl https://gateway.metrxbot.com/v1/chat/completions \
-H "Authorization: Bearer sk_live_xxxx" \
-H "X-Provider-Key: sk_openai_xxxx" \
...What changes:
- URL:
api.openai.com→gateway.metrxbot.com - Auth: Your OpenAI key moves to
X-Provider-Key - New
Authorizationheader with your Metrx API key
3. Track Costs and Outcomes
Once integrated, costs are automatically calculated and tracked. Log into your dashboard at app.metrxbot.com to see:
- Real-time cost tracking
- Call counts by model
- Performance metrics (latency, error rates)
- Usage vs. plan limit
4. Next Steps
Read the Integration Guide
The Integration Guide has detailed examples for Node.js, Python, streaming, webhooks, and migration from direct API calls.
Explore the API Reference
The API Reference documents every endpoint, header, and error code.
Understand the Architecture
The Architecture page explains how the Gateway, Workers, and Database fit together.
Pricing
| Offer | What you get | Price |
|---|---|---|
| Free | Cost + token analytics, ROI on one showroom agent, one sample verdict | $0 |
| Verify | One causal verdict on your own production traffic | $149 ($99 founding rate) — no verdict, no charge |
| Platform | The optimization engine — full attribution, P&L, ROI, safe auto-apply | Talk to us — a monthly fee indexed to your managed LLM spend |
| Enterprise | Authority you define per change class, MSA + procurement, optional performance-fee | Custom |
See metrxbot.com/pricing for current pricing and to see your Platform price.