--- id: "2026-09-15-typesafe-jev-system-one-model" url: "https://postcutoff.com/e/2026-09-15-typesafe-jev-system-one-model/" as_of: "2026-11-19T22:11:00+01:00" date: "2026-09-15" date_precision: day category: model-release importance: 3 confidence: high status: [Confirmed] sources: 21 editor: human editor human_review: null version: "2026-10-17" --- As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-15-typesafe-jev-system-one-model/ # TypeSafe AI releases Jev, a 'System One' decision model that returns typed probabilities instead of text On Sept 15, 2026 TypeSafe AI, founded by ex-OpenAI researcher Diogo Almeida, released Jev, which it calls the first "System One model": it takes text or JSON plus typed questions and returns only structured values (yes/no probabilities, choice distributions, scores), in 70–500 ms at $0.042 per million input tokens with free output. Vercel's AI Gateway and Cloudflare added it within days. ## Key facts - Oct 9, 2026 (Bloomberg): TypeSafe raised ~$870M at a $7.5B valuation led by Andreessen Horowitz, with Sequoia and angels; company says Jev passed 1M users within days and is used by about a third of the Fortune 500 (see [2026-10-09-typesafe-ai-870m-a16z-7-5b](https://postcutoff.com/e/2026-10-09-typesafe-ai-870m-a16z-7-5b/index.md)) - Oct 2 (WSJ): CEO Diogo Almeida says Jev is in use by about 25% of Fortune 500 companies and 'we were at a trillion tokens per day about a week ago', traffic driven by servers rather than people; company figures, not independently verified, and 'in use' is undefined - Released Sept 15, 2026 (TypeSafe blog), early access at launch - Question types: Boolean (probability 0–1), Choice (distribution over options), Score (numeric rating) - Latency 70–500 ms; TypeSafe claims up to 193.6x faster and 444.6x cheaper than LLMs on its workflow evals, with intelligence similar to GPT-5.6 Terra on 'System One tasks' - Pricing: $0.042 per 1M input tokens; output free - TypeSafe: 'unstructured state in, typed probabilistic decisions out'; claims no hallucinated or mistyped outputs - Available through TypeSafe's API (jev-latest), Vercel AI Gateway (typesafe-ai/jev) and Cloudflare (typesafe/jev) - Simon Willison proposed the name 'decision models' and warned the numbers 'could conceal all manner of unseen bias' - Reported $40M seed led by DCVC (not confirmed from TypeSafe's own post) - Founder Diogo Almeida's launch post on X drew ~40M views by Sept 29; Vercel said Jev reached ~13% of AI Gateway teams on day one, '2x the GPT-5.6 family and 6x Fable 5.1', its fastest adoption ever - Fast followers: Cua open-sourced CUA-S1-FORMS, a 706K-parameter 'System One' model for form filling (99.7% vs hosted Jev's 83.6% on Cua's own eval); Bespoke Labs' open Nimble was pitched as an alternative - AWS follower (Oct 1, 2026): Strands Labs, AWS's experimental agent project, released Strands Decider 2B (Apache 2.0), a Qwen3.5-2B-Base LoRA with a pointer/readout head that scores supplied options instead of generating text. Model card: JevBench public (231 tasks) 0.723, ContractNLI 0.872, MuSiQue 0.884. VentureBeat: 106 ms median and 296 ms p95 latency on an RTX 3090; #2 among public ~2B models on JevBench and #1 with a full training recipe - Cloudflare follower (Oct 1, 2026): Clef (Qwen3.8-27B) and Clef-flash (Qwen3.5-9B), Apache-2.0 multimodal decision models, fully Jev-API compatible, 64k context; Cloudflare reports 209 ms (Clef) and 39 ms (Clef-flash) median latency vs Jev's 524 ms; $0.24 per 1M input tokens on Workers AI (see [2026-10-01-cloudflare-clef-decision-models](https://postcutoff.com/e/2026-10-01-cloudflare-clef-decision-models/index.md)) - Perplexity follower (Oct 1, 2026): open pplx-decider-v1-27b behind a Decisions API at $0.04 per 1M input tokens; 85.71% vs Jev 84.51% on Perplexity's 11-benchmark panel (see [2026-10-01-perplexity-decisions-api-pplx-decider](https://postcutoff.com/e/2026-10-01-perplexity-decisions-api-pplx-decider/index.md)) - Open follower (HF, created Sept 18, 2026): Convai Innovations' Laya, an Apache-2.0 non-autoregressive 'System 1' decision model (421M-parameter ModernBERT-large English checkpoint; 322M mmBERT-base multilingual one) trained with 'RLCD' (RL with strictly proper scoring rules as rewards). Model card claims 0.766 vs Jev's 0.727 on its typed-decisions benchmark and 7.8x lower latency (32.8 ms on a T4); ~5k Hugging Face likes by Oct 2 (self-reported numbers, not independently checked) - Small open follower (HF, Sept 23, 2026): Supersonic Labs' Julia 1, a 144.3M-parameter Apache-2.0 decision model fine-tuned from mmBERT-small; on its own tests 73.15% typed-decision accuracy vs 72.70% for a Jev reference (but 64% vs 87% on a Banking77 pilot); trending on Hugging Face in early Oct (huggingface.co/SupersonicLabs/Julia-1) - Distilled open copies (HF, Sept 23–Oct 5, 2026): AutoTrust's JEV-9B, JEV-27B (Qwen3.8-27B adapter, described as a 'student of TypeSafe Jev 1.13' trained largely on Jev output distributions), JEV-27B-VL (adds image input, 'System 1' API at POST /v1/decide; Oct 3 robot-arm and computer-use demos) and GEV-26B-Decide (Gemma 4 26B-A4B base). All Apache-2.0. AutoTrust's own six-benchmark run puts JEV-27B 0.22 points above hosted Jev 1.13. By Oct 7, JEV-27B-VL had ~1.5M downloads and GEV-26B-Decide ~855k, among the most-trending models on Hugging Face (self-reported benchmarks; download counts may include automated pulls) - Jev 1.14 (TypeSafe blog, Oct 14, 2026): jev-1.14.0 released under jev-preview (jev-latest to follow a week later), with small broad gains, mostly multilingual; opt-in experimental 'danger zone' flags for image input, a new single bounding-box `box` type and longer context than production allows (no limit stated). jev-1.13.0 gets 60 days' notice before deprecation. No pricing or benchmark numbers in the post - AutoTrust JEV-35B (Hugging Face, Oct 11, 2026): Apache-2.0 decision model fine-tuned from Qwen3.5-35B-A3B (~3B active), up to 256 options per pass; self-scored 59.73 on the public Decision Index 0.3 suite vs 53.64 for JEV-27B-VL, median latency 204 ms on one B200; NVFP4 version fits 32–48 GB GPUs. ~28k downloads and 771 likes by Oct 15, among Hugging Face's top trending models (self-reported scores) - OpenAI follower (Oct 6, 2026): OpenAI's Decisions API entered public beta with gpt-6-luna at $0.10 per 1M input tokens (see [2026-10-06-openai-decisions-api-public-beta](https://postcutoff.com/e/2026-10-06-openai-decisions-api-public-beta/index.md)) - Microsoft follower (Oct 9, 2026): Microsoft-Decision-1, a post-trained Qwen3.5-9B, at the same $0.042 per 1M input tokens with free output, in Microsoft Foundry (see [2026-10-09-microsoft-decision-1](https://postcutoff.com/e/2026-10-09-microsoft-decision-1/index.md)) - Category spreads (TechCrunch, Oct 6): moderation startup Musubi released PolicyLM-1.7B, an open-weights decision model that applies plain-English content policies to messages in under 50 ms without retraining when policies change; TechCrunch lists Jev, OpenAI's and Amazon's decision models as the wave it joins. Musubi's Filip Jankovic: 'Product teams just want a better understanding of what's happening on their platform' - TechCrunch (Oct 16, 2026), on Vercel's AI Gateway data: within two weeks 35% of paid teams on the gateway used Jev, nearly double the reach of the second model, Sonnet 5.5, the fastest two-week adoption Vercel has seen; Vercel itself replaced GPT-6 Luna with Jev for classifying harmful commands. TechCrunch notes the gateway undercounts labs with their own APIs ## What happened Jev is aimed at the many small judgments inside software (classifying, ranking, routing, reranking search results) where developers currently call a chat model and parse its text. It returns calibrated numbers in a fixed schema instead. Developers adopted it quickly: within days there were integrations, playful hacks (a 2048 player, a left-pad) and an open-source imitation built on Qwen. ## Why it matters It is a new product shape for language models, a cheap, fast "function call" for judgments, and it was widely discussed as a complement to frontier agents in the same week as Claude Opus 5.5 and GPT-6 Sol. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 107 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 77 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 168 days after its cutoff - Grok 4.7 (training cutoff May 2026): 107 days after its cutoff ## Sources 1. [TypeSafe blog: Jev 1.14 (Oct 14, 2026)](https://typesafe.ai/blog/jev-1-14) (typesafe.ai, official) 2. [Hugging Face: autotrust/JEV-35B model card](https://huggingface.co/autotrust/JEV-35B) (huggingface.co, code) 3. [Strands Agents blog: Introducing Strands Decider (Oct 1; Hacker News front page Oct 7, ~281 pts)](https://strandsagents.com/blog/introducing-strands-decider/) (strandsagents.com, official) 4. [TypeSafe AI: Introducing System One Models & Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev) (typesafe.ai, official) 5. [Vercel: TypeSafe AI's Jev now available on AI Gateway](https://vercel.com/changelog/typesafe-ai-jev-now-available-on-ai-gateway) (vercel.com, docs) 6. [Diogo Almeida on X: launching Jev](https://x.com/CompleteSkeptic/status/2099925682726002904) (x.com, official) 7. [Vercel on X: Jev adopted faster than any model in AI Gateway history](https://x.com/vercel/status/2101077346203971900) (x.com, official) 8. [Hugging Face: StrandsAgents/strands-decider-2B-hobson-v19](https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19) (huggingface.co, code) 9. [Cloudflare blog: Clef decision models](https://blog.cloudflare.com/clef-decision-models/) (blog.cloudflare.com, official) 10. [Hugging Face: convaiinnovations/laya (Laya decision model)](https://huggingface.co/convaiinnovations/laya) (huggingface.co, code) 11. [Hugging Face: autotrust/JEV-27B-VL (open distilled Jev student with vision)](https://huggingface.co/autotrust/JEV-27B-VL) (huggingface.co, code) 12. [TechCrunch: Jev is Vercel's fastest-adopted AI model ever (Oct 16)](https://techcrunch.com/2026/10/16/jev-is-vercels-fastest-adopted-ai-model-ever/) (techcrunch.com, press) 13. [TechCrunch: How AI decision models could change content moderation (Oct 6)](https://techcrunch.com/2026/10/06/how-ai-decision-models-could-change-content-moderation/) (techcrunch.com, press) 14. [WSJ: Startup TypeSafe AI's Jev model sparks copycats, talk of LLM alternatives](https://www.wsj.com/tech/ai/startup-typesafe-ais-jev-model-sparks-copycats-talk-of-llm-alternatives-e39ff57d) (wsj.com, press) 15. [AI Weekly: TypeSafe says Jev reaches 25% of Fortune 500, trillion tokens daily](https://aiweekly.co/alerts/typesafe-says-jev-reaches-25-of-fortune-500-trillion-tokens-daily) (aiweekly.co, press) 16. [Forbes: Jev cuts AI decision costs 100x and Vercel, Cloudflare rushed to add it](https://www.forbes.com/sites/josipamajic/2026/09/19/jev-cuts-ai-decision-costs-100x-and-vercel-cloudflare-rushed-to-add-it/) (forbes.com, press) 17. [VentureBeat: Amazon unveils Strands Decider 2B, a free open-source Jev competitor](https://venturebeat.com/technology/amazon-unveils-a-free-fast-open-source-jev-killer-strands-decider-2b-makes-decisions-in-fractions-of-a-second) (venturebeat.com, press) 18. [The New Stack: AWS launches a local answer to TypeSafe's Jev decision model](https://thenewstack.io/aws-strands-decider-model/) (thenewstack.io, press) 19. [Nathan Flurry on X: hype-free explanation of Jev (670K views)](https://x.com/NathanFlurry/status/2100036101809619314) (x.com, discussion) 20. [Jarrod Watts on X: trading bot built with Jev (1.28M views)](https://x.com/jarrodwatts/status/2100356151468585346) (x.com, discussion) 21. [Simon Willison: Jev introduces a new shape of LLM - System One, aka Decision Models](https://simonwillison.net/2026/Sep/21/jev/) (simonwillison.net, discussion) ## Changes - 2026-10-17: TechCrunch on Jev's adoption on Vercel's AI Gateway - 2026-10-15: Added Jev 1.14 (preview, experimental image, bounding-box and long-context flags) and AutoTrust's JEV-35B open student - 2026-10-10: Added Microsoft-Decision-1 as a follower - 2026-10-09: Added the $870M a16z round - 2026-10-08: Linked the Strands Decider blog post (HN front page Oct 7, ~281 pts) - 2026-10-07: Added TechCrunch on Musubi's PolicyLM-1.7B as part of the decision-model wave - 2026-10-07: Added AutoTrust's distilled open Jev students (JEV-27B/-VL, GEV-26B-Decide; trending on Hugging Face) and OpenAI's Decisions API beta - 2026-10-04: Added Supersonic Labs Julia 1 (144M open decision model) as a further follower - 2026-10-03: Added Perplexity pplx-decider as a further follower - 2026-10-03: Added the WSJ interview (25% of Fortune 500, 1T tokens/day; company figures) - 2026-10-02: Added Convai Innovations' open Laya decision model - 2026-10-02: Added Cloudflare Clef/Clef-flash as an open-weight, Jev-compatible follower - 2026-10-01: Added AWS Strands Decider 2B as an open-source follower - 2026-09-30: Linked the highest-reach community Jev posts - 2026-09-29: Added launch-post reach, Vercel adoption data and open follow-ons; 16 related X posts archived - 2026-09-29 (filed): Created ## Related - 2026-10-09: [TypeSafe AI, maker of the Jev decision model, raises ~$870M led by a16z at a $7.5B valuation](https://postcutoff.com/e/2026-10-09-typesafe-ai-870m-a16z-7-5b/index.md) - 2026-10-09: [Microsoft-Decision-1 decision model](https://postcutoff.com/e/2026-10-09-microsoft-decision-1/index.md) - 2026-10-06: [OpenAI opens the Decisions API to all developers in public beta](https://postcutoff.com/e/2026-10-06-openai-decisions-api-public-beta/index.md) - 2026-10-01: [Cloudflare releases Clef and Clef-flash, open-weight multimodal decision models that are Jev-API compatible](https://postcutoff.com/e/2026-10-01-cloudflare-clef-decision-models/index.md) - 2026-10-01: [Perplexity launches a Decisions API and open-sources pplx-decider-v1-27b, a decision model it says edges Jev (85.71% vs 84.51%)](https://postcutoff.com/e/2026-10-01-perplexity-decisions-api-pplx-decider/index.md) - People: [Simon Willison](https://postcutoff.com/person/simon-willison/) - Models: [Strands Decider 2B](https://postcutoff.com/m/strands-decider-2b/) (`strands-decider-2b`) - Archived: 20 posts and 3 videos, listed in https://postcutoff.com/e/2026-09-15-typesafe-jev-system-one-model/index.json