Stop using LLM prose for routing: Jev returns structured decisions at $0.042 per million tokens

mikegiannulis · x · 2026-09-18

The author calls out an absurd pattern: asking a model that can write novels "which bucket does this message go in?" then parsing generated text. TypeSafe AI's Jev skips the prose entirely, returning choices, scores, and probabilities directly — at $0.042 per million input tokens with free output.

Related event: Jev Outputs Structured Decisions Directly at $0.042/M Tokens(2 posts)→

Original post →

More from coding & agent

coding & agent channel →