Kimi K2.5 Now on Cloudflare Workers AI — Frontier Open Model on Edge Infrastructure with 77% Cost Savings

Cloudflare Blog·high signal

Cloudflare added Moonshot AI's Kimi K2.5 to Workers AI on March 19, making it the first frontier-scale open-source model available on edge compute with a full 256K context window, multi-turn tool calling, vision inputs, and structured outputs. Cloudflare reports 77% cost savings ($2.4M/year on a single workload) versus mid-tier proprietary models, with prefix caching and session affinity now exposed as first-class features. This significantly lowers the barrier for deploying capable agentic workloads at the edge without managing GPU infrastructure.