Free tier · CarbonLayer
Free sustainable inference for AI builders.
50K carbon-tracked inferences a month. No card. No model gymnastics. Every call already lands in /api/savings — including the ones you didn't know to track.
Already shipping? Upgrade to Verified and ship the embed badge with the same dispatch log you already produce.
What you get
Built around three things AI engineers ask for.
Per-inference carbon + water tracking
Every POST to /api/inference writes gCO2 + mL water against a 600 gCO2/kWh hyperscaler baseline. Read your savings at /api/savings — same log every call lands in.
CarbonLayer-verified badge
One snippet of HTML, derived live from your dispatch log. Drop it on your site or quarterly report and the strip auto-updates with your real numbers.
Renewable-window scheduling
POST /api/renewable-windows queues batch jobs for the cleanest hour in the next 24h. Heavy work shifts automatically when local grid carbon drops.
Two tiers, hand-authored
Start free, upgrade when you ship the report.
Tier numbers are static on this page — paid traffic doesn't need a live derivation, it needs a clear two-tile choice. Visit /pricing if you want the live savings-derived version.
Free tier
For prototypes, side projects, and engineers evaluating carbon-aware dispatch without a budget conversation.
- 50K inferences / month
- Per-call carbon + water tracking
- Renewable-window scheduler access
- Public /api/savings read
50K inferences / month cap. No embed badge, no priority dispatch.
Verified tier
For teams shipping a sustainability report or marketing claim backed by a public, audit-ready dispatch log.
- 1M inferences / month included
- CarbonLayer-verified embed badge
- Priority dispatch (<250 ms)
- Regional carbon drill-down
- Quarterly audit export
First call in 30 seconds
No SDK, no wrapper, no shim layer.
POST a request from curl, get back the same JSON every model wrapper on Earth would parse — alongside the dispatch region, the carbon intensity at dispatch time, and your running per-call totals.
# Fire an inference, track the dispatch
curl -sX POST {{api}}/api/inference
-H "content-type: application/json"
-d '{
"prompt": "Suggest 3 ways to halve the warehouse's overnight energy bill",
"model": "claude-haiku",
"tokens": 600
}
# Query lifetime savings
curl -s {{api}}/api/savings | jq .
# Schedule a weekly batch for the next renewable window
curl -sX POST {{api}}/api/renewable-windows
-H "content-type: application/json"
-d '{"prompt": "weekly emissions rollup","priority": "low"}'Not ready to sign up?
Drop your work email. We'll ping you when the free tier widens.
One message when something material changes — quota bump, new region, or a new dispatch policy you'll want to know about. Nothing in between.
Waitlist
50K free inferences, no card. Verified tier adds the embed badge, priority dispatch, and a quarterly audit export.