Jev

Overview

Jev is TypeSafe’s System One decision model (e.g. jev-1.13.0) outputting typed Noul/Choice/Score answers with calibrated probabilities — no text generation, structurally no hallucination on predefined outputs.

Competitive Landscape

• 2026-10-09: microsoft-decision-1 joins Foundry/OpenRouter as hyperscaler decision-scoring SKU in same category (2026-10-09-microsoft-decision-1-model-foundry)
• 2026-09-30: openai decisions-api mirrors Jev’s structured classification for agent monitoring — demo cited ~$2.94(Jev)vs$372 (frontier LLM) per monitoring task (2026-09-30-openai-decisions-api-jev-clone)

Benchmarks (early adopter reports)

• Vercel: 5–18× faster than LLM classifiers vs OpenAI Luna
• Bryo AI: 10–20× cheaper than Gemini for routing tasks
• Cloudflare AI catalog lists 32K context window

Benchmarks are early adopter/vendor reports, not peer-reviewed. Base architecture suspected to build on open-weight LLM backbone.

Related

• typesafe-ai
• system-one-models
• rlcd
• calibrated-decisions
• rlhf
• model-routing

Sources

• 2026-09-19-typesafe-jev-official-blog
• 2026-09-18-typesafe-jev-calibrated-decision-model