Jev

TypeSafe AI's first System One model: a non-LLM decision engine returning typed, calibrated choices instead of generated text.

TypeSafe AI · Infrastructure and inference/serving · model

Published in Feed

Overview

Jev is TypeSafe AI's first System One model, built to make fast structured decisions such as routing, classification, scoring, and extraction by returning typed probabilistic outputs instead of free-form text. TypeSafe says it matches existing LLMs on System One-style decision tasks while responding in 70-500ms, which it markets as up to 193x faster and 445x cheaper than comparable LLM calls, and every output ships with a calibrated confidence score. It launched in early access on September 22, 2026, at $0.042 per million input tokens with output tokens priced at zero. On October 14, 2026 TypeSafe published Jev 1.14.0 (under jev-preview, with jev-latest to follow in about a week), adding image inputs and longer context behind opt-in 'danger zone' headers and a new box type; TypeSafe says image performance trails text-only. On October 16, TechCrunch reported Vercel data showing 35% of paid teams on its AI gateway used Jev within two weeks of launch, nearly double the second most popular model, Sonnet 5.5, with Vercel using it to replace GPT-6 Luna for classifying harmful commands. Vercel's gateway likely undercounts OpenAI and Anthropic direct API use. On October 24, 2026 TypeSafe's CEO disclosed that a bug exposed every customer's Jev outputs; the exposure resembles an insecure direct object reference but no postmortem or confirmed root cause had been published, and the notice came faster than the 72-hour window in TypeSafe's data processing addendum.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Returns typed, structured decisions instead of generated text
  • 70-500ms response time via parallel rather than sequential sampling
  • Calibrated confidence score attached to every output
  • Vendor claims it cannot produce hallucinated or type-invalid outputs
  • Vendor claims up to 193x faster and 445x cheaper than comparable LLMs on decision tasks
  • Jev 1.14.0 (Oct 14, 2026): image inputs and longer context via opt-in headers, new box type; 60 days' notice before deprecating 1.13.0
  • Vercel-reported adoption: 35% of paid teams on its AI gateway within two weeks of launch
  • Security incident (disclosed Oct 24, 2026): all customers' Jev outputs exposed; root cause unconfirmed, no postmortem yet

Use cases

  • Routing and classification inside application logic
  • Real-time scoring and extraction pipelines
  • Verification steps in agentic workflows
  • High-volume conditional logic that doesn't need generated prose

Pricing

Early access: $0.042 per million input tokens; output tokens free ('too cheap to meter'). No published enterprise tier yet.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
22 Sept 2026
Record updated
26 Oct 2026
Record last checked
26 Oct 2026

Explore the Feed

Other entries filed under infrastructure and inference/serving; inclusion does not imply equivalent features.

  • NVIDIA PAIR (Personal AI Router)

    NVIDIA's free, open-source personal AI router that spreads local model workloads across PCs on your network; out of beta Oct 13, 2026.

  • Agent37

    YC F26 startup selling low-cost agent sandboxes (gVisor or full VM) with prebuilt harnesses for Claude Code, Hermes and opencode.

  • Microsoft-Decision-1

    Microsoft's Qwen3.5-9B-based decision-scoring model returns calibrated option probabilities in one pass, at $0.042 per million input tokens.

Browse the Feed