Simple, transparent pricing
Start free with an account and your own API keys. Upgrade when you need more scale. Cancel anytime.
Free
For getting started — try it with no card required.
Free forever
500K tokens / day
- ✓ Access to 40+ free models
- ✓ Adaptive routing
- ✓ Private dashboard & API keys
- ✓ Community support
Pro
For individuals and small projects getting started with AI routing.
Billed monthly
$35 / week usage budget
- ✓ Access to 57+ models
- ✓ OpenAI-compatible API — any OpenAI SDK or agent
- ✓ Adaptive routing + automatic failover
- ✓ Gateway tool loop for coding agents
- ✓ Email support · 24h
Pro+
For regular work and products that are scaling up.
Billed monthly
$70 / week usage budget
- ✓ Everything in Pro
- ✓ Double the usage budget
- ✓ More concurrent requests
- ✓ Detailed usage analytics
- ✓ Priority email support
Max
For builders who need faster routing, reliability and higher limits.
Billed monthly
$140 / week usage budget
- ✓ Everything in Pro+
- ✓ 4× Pro limits
- ✓ More concurrent requests
- ✓ Developer productivity tools
- ✓ Priority email support
Ultra
For power users and teams running high-volume AI workloads.
Billed monthly
$700 / week usage budget
- ✓ Everything in Max
- ✓ 20× Pro limits
- ✓ Very high concurrent requests
- ✓ Early access to new features
- ✓ Peak-hour priority
Power
For teams and the largest-scale production workloads.
Billed monthly
$1,400 / week usage budget
- ✓ Everything in Ultra
- ✓ 40× Pro limits
- ✓ Maximum concurrent requests
- ✓ Highest output limits
- ✓ Top-priority support · 12h
Adaptive mode pricing
Requests to model adaptive are billed at one flat rate — $0.50 / 1M input and $2.00 / 1M output tokens — whichever model serves them.
Specific models
Requesting a model directly bills that model's per-token price, counted against your plan's usage budget. See all model prices →
Need enterprise routing?
Custom limits, dedicated capacity, audit logs, SSO, invoice billing and SLA options.
Contact sales →