Pricing

Start free, scale with confidence

Every plan includes exact-match caching, encrypted key storage, and an OpenAI-compatible API. Free includes 10,000 embedding tokens a month. Pro and Enterprise raise that cap. No credit card required for Free.

Free

For hobbyists and experimentation

Free
  • 1,000 requests / month
  • 3 req/s, 20 req/min burst limit
  • 1 API key
  • Exact-match caching
  • 10,000 embedding tokens / month
  • 500 stored vectors
  • 7-day audit logs
  • Community support
Get Started
Most Popular

Pro

For developers shipping to production

$9/mo
  • 50,000 requests / month
  • 20 req/s, 200 req/min burst limit
  • 5 API keys
  • Semantic cache (managed or BYO)
  • 2M embedding tokens / month
  • 25,000 stored vectors
  • Text + image + video caching
  • Custom model registry
  • 30-day audit logs
  • Email support
Get Started

Enterprise

For teams at scale

$39/mo
  • 500,000 requests / month
  • 100 req/s, 2,000 req/min burst limit
  • Unlimited API keys
  • Semantic cache (managed or BYO)
  • 15M embedding tokens / month
  • 200,000 stored vectors
  • Text + image + video caching
  • Custom model registry
  • 90-day audit logs
  • Priority support
Contact Sales

All plans include SSL encryption, 99.9% uptime SLA, and multi-provider support (OpenAI, Gemini, custom endpoints). Free includes exact-match caching and 10,000 embedding tokens a month. After that allowance is used, requests that need a new embedding return an upgrade error. Pro and Enterprise raise the embedding and vector caps.
Need higher limits? Contact us for custom enterprise pricing.