Flat monthly — zero token markup

Simple, predictable
pricing for AI.

No per-token fees. No hidden markups. No surprise bills. Cancel anytime. Start in 30 seconds.

Starter
$29/mo
For solo developers shipping AI features. All 4 model tiers included.
  • 1M tokens per month
  • All 4 model tiers
  • Smart auto-routing
  • 30 requests/minute
  • Email support
Get Started
No credit card required
Pro
$99/mo
For teams building production AI applications. Research API + code generation.
  • 10M tokens per month
  • Everything in Starter
  • 120 requests/minute
  • Research API access
  • Code generation (Claude Opus)
  • Priority support
Get Pro
7-day free trial
Max
$199/mo
For enterprises with heavy AI workloads. 500 RPM. Ensemble routing. SLA.
  • 50M tokens per month
  • Everything in Pro
  • 500 requests/minute
  • Ensemble routing
  • 24/7 support + SLA
Get Max
Annual billing available
$0
Token markup
96/96
Benchmark accuracy
91%
Token savings
10+
Models included

FAQ

Common questions.

What is a token?

A token is roughly 0.75 words. 1M tokens = ~750,000 words or ~3,000 pages of text. 10M tokens handles most production workloads.

Which models do I get?

Starter includes 325-fast and 325-balanced. Pro and Max unlock 325-ultra, Research API, and Code Generation. All tiers include smart auto-routing.

Can I switch plans?

Yes. Upgrade or downgrade anytime. If you upgrade mid-month, we prorate the difference. Downgrades take effect next billing cycle.

What if I exceed my tokens?

We'll notify you at 80% and 95% usage. At 100%, requests return 429 until your next billing cycle or you upgrade. No overage charges, ever.

Is there a free trial?

Pro plan includes a 7-day free trial with 1M tokens. No credit card required. Cancel anytime during the trial.

How does smart routing save tokens?

325-auto analyzes your prompt and routes to the cheapest model that can handle it. Simple HTML queries go to 325-fast (~0.3s). Complex analysis goes to 325-ultra. 91% average savings vs always using the most expensive model.