TypeSafe AI Launches Jev, a Decision-Only Model That Outputs No Text
TypeSafe AI launched its first model, Jev, a frontier model that "only decides, never writes": given an application state and a set of typed questions, it returns options, scores and probabilities for code to execute directly, with no text generation at all. The team is reportedly co-founded by a researcher behind ChatGPT (community retellings variously name Milind, Diogo, or kylejeong, mostly as a ChatGPT co-inventor/co-author), who claims to have spent two years in stealth developing a new training method called RLCD. Jev is positioned as "composable intelligence" optimized for decisions rather than a better chatbot, arguing that superhuman chat models have not delivered AGI. TechCrunch also covered it as a cheaper, faster path to software intelligence for developers.
Confirmed
- Jev is live on Vercel AI Gateway, open to all users, supports zero data retention (ZDR), priced at $0.04 per million input tokens with free output tokens (m11, m16)
- It returns structured decisions rather than text, covering classification, routing, rubric scoring, tool selection and guardrails; independent engineer @mostlyidempotent measured latency of roughly 70ms (m8)
- @Sam Witteveen's hands-on test confirms it targets fast System 1 classification, not long-chain reasoning (m1); @Cagnazzo82 demoed Jev playing Subway Surfers in real time (m2)
- Developer grichadev tested it in a security pipeline: over 5x cheaper, faster and notably more accurate than prior setups; he called it the first new model to genuinely impress him, with Sentry and other real pipelines adopting it (m18)
Unconfirmed
- The claimed "20-200x faster, 40-400x cheaper" figures are vendor claims; apart from grichadev's single-scenario test, broad third-party validation is lacking (m3, m5)
- The founder's identity is inconsistently reported as Milind, Diogo or kylejeong, each described as a ChatGPT co-inventor; no official clarification exists (m5, m12, m20)
- Technical details of RLCD as a new reinforcement learning paradigm have not been publicly elaborated (m6, m8, m10)
Why it matters
- If the cost and speed claims hold, many small decision tasks currently done by generating and parsing LLM tokens (classification, routing, guardrails) could migrate to such specialized models, cutting AI application cost and latency (m13, m18)
- It represents a "models are not just chatbots"路线: structured, composable outputs embedded directly into software decision layers (m15, m19)
- One commenter highlights an overlooked point: TypeSafe calls itself a "data research lab"—data construction may be its real moat, and demand for data like agent trajectory monitoring may explode (m14)
2026-09-17 ~ 2026-09-19 · 73 related posts
- Episode 1: TypeSafe exits stealth with decision model Jev and RLCD training method(2026-09-16, 86 posts)
- Episode 2: TypeSafe AI launches Jev, a dedicated evaluation model showing major speed and cost gains in tests(2026-09-16, 8 posts)
- Episode 3: Vercel fx to adopt Jev safety reviewer, up to 18x faster(2026-09-17, 3 posts)
- Episode 4: OpenJev Open-Source Clone Runs Jev-Style API on One RTX 3090(2026-09-17, 3 posts)
- Episode 5: TypeSafe AI Launches Jev, a Decision-Only Model That Outputs No Text(2026-09-17, 73 posts)
- Episode 6: Mystery decision model Jev sparks wave of community benchmarks(2026-09-18, 6 posts)
- Episode 7: TypeSafe AI's Jev model and RLCD method spark debate(2026-09-18, 3 posts)
- Episode 8: LangChain Publishes Tutorial on Building an Agent Harness with Jev(2026-09-18, 7 posts)
- Episode 9: Jev Ecosystem Explodes with Wave of Popular GitHub Projects(2026-09-18, 4 posts)
- Episode 10: Jev, the Decision-Only AI Model, Goes Viral for Speed and Cost(2026-09-18, 33 posts)
- Episode 11: TypeSafe Jev Decision Models Spark Debate on Breakthrough, Skepticism and Replication(2026-09-18, 7 posts)
- Episode 12: Jev Matches Classifiers at 100x Lower Cost(2026-09-19, 2 posts)
- Episode 13: Jev Positioned as LLM Router, Not a Replacement(2026-09-19, 2 posts)
- Episode 14: Developers Hail Jev as Top Value Model for Batch Labeling(2026-09-19, 2 posts)
- Episode 15: JevBench Launches: Jev 1.13 Holds Narrow Lead as Open-Source Rivals Close In(2026-09-19, 8 posts)
- Episode 16: TypeSafe AI's Decision Model Jev Explodes in Popularity, Setting Vercel AI Gateway Adoption Record(2026-09-19, 14 posts)
- Episode 17: omarsar0 Tests Jev as a New Primitive: Cheap Verifiers for Long-Running Agents(2026-09-19, 10 posts)
- Episode 18: Dev Tests 16 Models on Calibration: Jev Fast and Honest but Only 10th in Accuracy(2026-09-19, 8 posts)
- Episode 19: Independent Tests Confirm Jev Classifier's Accuracy at Fractional Cost(2026-09-19, 4 posts)
Primary sources
- TypesafeAI ships Jev, a zero-shot classifier that cuts chat-data labeling costs — yenkel · 2026-09-17
- Jev Debate: Engineers Forget Encoder-Only Classifiers Have Existed for Years — brandon_galang · 2026-09-17
- typesafeai's Jev classifier lands on AI Gateway with zero-data retention — cramforce · 2026-09-17
- Typesafe AI's Jev lands on Vercel AI Gateway for millisecond agent decisions — cramforce · 2026-09-17
- [source] New Model Jev Runs Security Pipelines 5x Cheaper and Faster, Devs Say — zeeg · 2026-09-17
- Hands-on with Jev: a classifier model to replace LLM-as-a-judge and route agents — doesdatmaksense · 2026-09-17
- Jev buzz reveals many don't know encoder-only classifiers have existed for years — RichmanRonald · 2026-09-17
- Dev says Jev classifies tweets 6X faster and ~40X cheaper than fastest LLM — altryne · 2026-09-17
- Switching tweet classification to Jev: 6x faster, ~40x cheaper than fastest LLMs — altryne · 2026-09-17
- [source] Jev evaluation model now available to everyone via Vercel AI Gateway at $0.04/1M tokens — jarrodwatts · 2026-09-17
- Six real-world uses for TypeSafe's Jev judgment model, 4x faster than Gemini in evals — HamelHusain · 2026-09-18
- Six Real Uses for Jev, the Judgment Model: From Fact-Checking Scripts to Debugging Agents — HamelHusain · 2026-09-18
- Self-Proclaimed ChatGPT Co-Inventor Launches Jev, Claims 200x Speed at 1/400 Cost — iamrobotbear · 2026-09-18
- Jev hype reveals two things: weak builder skills and the case for renting inference — edgarpavlovsky · 2026-09-18
- TypeSafe, founded by a ChatGPT researcher, launches Jev — a decision engine that can't write — Scobleizer · 2026-09-18
- TypeSafe's structured evaluation model Jev goes live on Cloudflare AI Gateway — michellechen · 2026-09-18
- 48 hours old, 724 ads broken down in 40 seconds: Jev sweeps the dev world — Scobleizer · 2026-09-18
- ChatGPT co-inventor launches Jev model with AI detector API 100x cheaper than Pangram — gaganghotra_ · 2026-09-18
- Jev Ditches Autoregression: A Model That Only Outputs Structured Decisions — karminski3 · 2026-09-18
- Jev: A Non-Autoregressive Decision Model That Outputs Structured JSON in 70ms — karminski3 · 2026-09-18
- Jev, the non-chatbot model, returns decisions in 70-500ms at $0.042/M input tokens, free output — adrianscottcom · 2026-09-18
- Jev and System One Models: fast decision-only AI that outputs typed answers, not text — blaizedsouza · 2026-09-18
- Jev, a 'System One' model by Typesafe, launches on OpenRouter with typed decisions instead of text — majidmanzarpour · 2026-09-18
- Dev: Jev could run cheaply in browsers — classification tasks were shoehorned into LLMs — GabGarrett · 2026-09-18
- TypeSafe launches Jev, a "System One" model that answers typed judgments in ~100ms — aronchick · 2026-09-18
- ChatGPT co-inventor launches Jev model claiming 20-200x speed and 40-400x cost cuts — multiply_matrix · 2026-09-18
- Jev, a new 'decision' model from a ChatGPT co-creator, plays Subway Surfers in real time — Cagnazzo82 · 2026-09-18
- ThursdAI Podcast Dives Into Jev Real-Time Models and Computer-Use Agents — altryne · 2026-09-18
- ThursdAI: TypeSafe's non-LLM Jev hailed as a ChatGPT moment, Dario proposes three ways to pace frontier AI — altryne · 2026-09-18
- A day with Jev: a fast classifier, best suited for Computer Use and game AI — jiayuan_jy · 2026-09-18
- After a day with Jev: a blazing-fast classifier, not a GPT replacement — jiayuan_jy · 2026-09-18
- Jev Launches as a Decision-Only Model: 20-200x Faster, 40-400x Cheaper Than LLMs — thisiskp_ · 2026-09-18
- [source] TypeSafe Jev returns typed decisions, not text: 70ms latency, free output tokens — mostly_idempotent · 2026-09-18
- Stop using LLM prose for routing: Jev returns structured decisions at $0.042 per million tokens — mikegiannulis · 2026-09-18
- A 20-cent AI that can't write a sentence caught 13 requests our classifier missed — mikegiannulis · 2026-09-18
- Replaying 3,300 Real Production Decisions to Test Small Model Jev — mikegiannulis · 2026-09-18
- Offline replay of 3,300 production decisions validated Jev routing in an afternoon for 20 cents — mikegiannulis · 2026-09-18
- Before buying a smarter model, check you asked the wrong job: Jev test wrap-up and rollout rules — mikegiannulis · 2026-09-18
- Same Material, Better Order: Reranking Lifts Correct-Passage Hit Rate to 90% — mikegiannulis · 2026-09-18
- 13 'Please Text Me, No Calls' Messages Misrouted — Small Model Caught All of Them — mikegiannulis · 2026-09-18
10 near-duplicate retellings: threepointone · hardimanjames · HankYeomans · multiply_matrix · multiply_matrix · multiply_matrix · multiply_matrix · GabGarrett · multiply_matrix · hardimanjames