the problem
You're flying blind.
Gateway caps protect your API key. Observability shows you charts. Nothing stops one heavy user from wrecking your margin.
how it works
Three lines. Zero runaway bills.
Your existing LLM code stays unchanged — noburn wraps around it.
Install the SDK
Drop into any Python project — no proxy, no middleware.
pip install noburn
Create a guard with a budget cap
Per-project or per-user. Set it once, enforced on every call.
guard = NoburnGuard( api_key="sk-nb-...", budget_cap_usd=0.02, # user_id="user_123" ← optional per-user cap )
Check before every LLM call
Sub-2ms client-side check. No network call required to block.
result = guard.check(model="gpt-4o", ...)
if result.blocked:
return handle_limit() # $0 charged
# proceed normally →the solution
noburn caps every user — then bills them.
Pre-flight enforcement
Estimates cost before the call. If it would exceed the budget — no DNS, no TCP, no tokens. $0 charged.
Real-time metering
Per-project and per-user spend tracked live. Webhooks fire the moment a threshold is crossed.
Passthrough billing
Charge your customers exactly what they cost. Connect Stripe and it flows automatically.
comparison
How noburn.dev is different.
The only self-serve tool that prevents the bill — not just measures it.
integrations
Works with your stack.
Drop-in wrapper — 2 lines of code.
early traction
Built in public. Growing in the open.
Real signals — no fake logos, no invented testimonials.
works with the tools your team already uses
documentation
Everything you need to integrate.
blog
Latest on LLM cost control.
What AI Features Actually Cost Per Active User: Production Numbers
LLM cost per user varies by two orders of magnitude depending on how the feature is designed.
Read →LLM Pricing Trends in 2026: What Token Costs Look Like After 18 Months of Competition
Token prices fell dramatically in 2024 and 2025. Here is what the pricing landscape looks like now.
Read →LLM Observability Tools in 2026: What Each One Actually Tracks
Helicone, LangSmith, Langfuse, Arize Phoenix — where every tool falls short.
Read →who built this
One builder. One real problem.
noburn.dev
I built noburn after a runaway LangGraph agent drained $300 in a single afternoon — in my own project. Helicone showed me exactly what happened, in a beautiful chart. Nothing stopped it. I had to pull the API key offline myself.
noburn is built for developers who've been there — or want to stop it before it happens. I'm shipping it in the open and will be in the early community personally.
↗ github.com/orvi2014faq
Common questions.
Still have questions? Join the waitlist and ask us directly.
See if spots remain →pricing
Join the waitlist. Lock your price.
First 30 → Founding Member (free 3mo → $9/mo forever). First 100 → Builder ($9/mo, GitHub star). Everyone else → Pro at $49/mo.
Founding Member
3 months · then $9/mo forever
- [✓]All Pro features — 5M req/mo, 10 seats
- [✓]$9/mo locked forever after trial
- [✓]60-day window to claim from invite
- [✓]First 30 on waitlist only
Builder
billed from day one · locked forever
- [✓]500k guard checks / month†
- [✓]3 projects · 3 seats‡
- [✓]Webhooks + per-user metering
- [✓]Locked at $9/mo forever
- [✓]Requires ⭐ GitHub star
Pro
always available
- [✓]5M guard checks / month
- [✓]Unlimited projects · 10 seats‡
- [✓]Passthrough billing (Stripe)
- [✓]$1 per extra 1M checks (overage)
- [✓]Priority support
† A guard check is one call to guard.check() before an LLM request. At Builder's 500k/mo limit, all guard.check() calls return blocked until the next billing cycle or you upgrade to Pro.
‡ Project = a separate guardrail config (e.g. one per app or environment). Seat = a team member with dashboard access.