Skip to content
Plans

Start free. Add control as you scale.

Every plan includes the core gateway, spend visibility, and multi-provider routing. Upgrade when traffic and team complexity increase.

Pricing

Pricing that scales with your AI usage

Start free, add capacity as you grow, and keep costs predictable with built-in guardrails.

Free

Free

For prototypes and early production.

  • 2 projects
  • 2 API keys per project
  • 10,000 requests/mo
  • 60 RPM rate limit
  • US East region only
  • 7-day analytics retention
  • In-app notifications
Join Waitlist
Most Popular

Pro

$29/mo

For teams that need stronger controls.

  • 10 projects
  • 10 API keys per project
  • 500,000 requests/mo
  • 500 RPM rate limit
  • All 4 regions
  • 90-day analytics retention
  • IP filtering (allowlist/blocklist)
  • Audit logs (30 days)
  • Email notifications
  • AI assistant
  • 5 team members
  • Daily + monthly spend caps
  • Anomaly detection + spike protection
  • Provider fallbacks
Join Waitlist

Business

$99/mo

For high-volume and enterprise AI operations.

  • Unlimited projects
  • Unlimited API keys
  • 5,000,000 requests/mo
  • 5,000 RPM rate limit
  • All 4 regions + priority routing
  • 1-year analytics retention
  • IP filtering + CIDR
  • Audit logs (1 year)
  • Email notifications
  • AI assistant
  • Unlimited team members
  • Daily + monthly + per-key caps
  • Anomaly detection + spike protection
  • Provider fallbacks
  • PII redaction
Join Waitlist
Compare

Compare plan limits

FeatureFreeProBusiness
Projects210Unlimited
API Keys / Project210Unlimited
Requests / Month10,000500,0005,000,000
Rate Limit (RPM)605005,000
Team Members15Unlimited
Regions1 (US East)All 4All 4 + Priority
Analytics Retention7 days90 days1 year
IP Filtering
Audit Logs30 days1 year
Email Notifications
AI Assistant
Spend Caps
Anomaly Detection
Spike Protection (Auto-Pause)
Provider Fallbacks
PII Redaction
FAQ

Pricing Questions

Clear answers on plans, limits, billing, and upgrades.

Need something custom? Contact Us

Put AI spend and reliability on autopilot

Route every model call through one policy layer for budgets, failover, and request-level analytics.