About Kento
Add semantic caching to any LLM provider with one line of code. Kento reduces AI costs by 40% by serving instant responses for repeat queries. Works with OpenAI, Anthropic, and Google.
Key Features
- 1,000 requests/month
- 7-day cache retention
- Savings dashboard
- Community support
- 50,000 requests/month
- 30-day cache retention
- Analytics dashboard with trends