TypeSafe AI's evaluation model Jev launches on Vercel AI Gateway at $0.04/M tokens

hackgoofer · x · 2026-09-17

TypeSafe AI's Jev, a 'System One' evaluation model for fast structured decisions in software, is now available on the Vercel AI Gateway. It evaluates shared state against typed questions and returns choices, scores, and boolean probabilities — supporting classification, routing, rubric-based assessment, and automated verification, with multiple questions evaluated in parallel per request. Input price is $0.04 per 1M tokens, and it's callable via the AI SDK's experimentalevaluate for agent workflows.

Related event: TypeSafe AI's Jev saturates evals at 6x speed(4 posts)→

Original post →

More from coding & agent

coding & agent channel →