Inkling Lands on Modal Endpoints

andersonbcdefg · x · 2026-07-16

The post shares news of Inkling's launch: the model is now available on Modal's first endpoint with token-based billing.

Two implementation details are highlighted: first, Inkling was released by @thinkymachines; second, Modal uses a custom DFlash speculator, reportedly delivering 67% higher throughput and interactivity. It currently runs on Modal Auto Endpoints using SGLang.

Related event: Modal adds Inkling to Auto Endpoints with DFlash acceleration(5 posts)→

Original post →

More from Infra

Infra channel →