Simple, Predictable Pricing
Start with a generous 3-month free trial.
All plans include
⚡High-speed cache lookups
🧠Similarity-based caching for near-duplicate prompts
⏱️Configurable TTL per namespace
📊Metrics dashboard (hit rate, savings, logs)
🔒Per-user isolation & multi-tenant safety
🧩Provider-agnostic — OpenAI, Claude, Gemini, custom LLMs
Starter
For indie devs and teams validating new ideas
$19
monthly • after free trial
- 📦 50,000 requests / month
- 📁 3 namespaces
- 🚦 200 / min
Growth
Ideal for SaaS apps and customer-facing AI workflows
$49
monthly • after free trial
- 📦 250,000 requests / month
- 📁 25 namespaces
- 🚦 800 / min
Scale
High-volume caching for production workloads
$149
monthly • after free trial
- 📦 1,000,000 requests / month
- 📁 Unlimited namespaces
- 🚦 3000 / min