Jev model claims 40-400x cheaper than Gemini; dev backtest finds it faster and more consistent

FrankFelixAI · x · 2026-09-16

A stealth team co-founded by a ChatGPT co-inventor launched Jev, a new frontier model trained with a method called RLCD, pitched as "frontier composable intelligence optimized for decisions" — claiming 20-200x speed and 40-400x cost advantages (output tokens free). Developer julianharris got access and backtested it against his optimized Gemini-2.5-flash-lite setup (flash pricing rose 10x and doubles again next year) on his MCP-based multi-user spec governance system.

Verdict: Jev is faster (though not as fast as claimed), way cheaper, and utterly consistent — whereas Gemini contradicts itself over time. The company behind it, Ceetrix, sells spec enforcement for AI coding agents: 13 gates enforce traceability from PRD to design to tasks to tested code, addressing agents that claim "done" while introducing regressions. Free during beta.

Original post →

More from coding & agent

coding & agent channel →