LithosAI ships Day-0 API inference for DeepSeek-V4.1-Flash at 250+ tokens/s per user

JiaZhihao · x · 2026-09-11

Inference provider LithosAI announced Day-0 public API support for DeepSeek-V4.1-Flash, live within 12 hours of the model's release. Standard tier delivers 250+ tokens/s per user with faster tiers coming, targeting ultra low-latency agent workloads.

Original post →

More from Infra

Infra channel →