Talk to a Friendli Expert
We’ll help you run open-weight models and AI agents at their fastest and most efficient—with production-grade reliability at scale.
Tell us what you’re building, or what’s slowing it down.
GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
We’ll help you run open-weight models and AI agents at their fastest and most efficient—with production-grade reliability at scale.
Tell us what you’re building, or what’s slowing it down.