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.
Related event: TypeSafe exits stealth with decision model Jev and RLCD training method(86 posts)→
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02