Docs
CommunityJev Guides & Articles
Jev News
A desk recording news, benchmarks, and listed API prices for TypeSafe's Jev and other decision models, with each figure linked to the page that printed it. Updated October 15, 2026, and not affiliated with TypeSafe.
- Format
- Docs
- Reading time
- 2 min
- Published by
- Community
- Author
- Jev News
- Last verified
- Oct 2026
Highlights
- Keeps Banking77, JevBench, and Decision Index results on separate rows rather than blending them into one score.
- Hosted-call table lists jev-1.13.0 at $0.042 per million input tokens with free output, and OpenAI's Decisions API guide price at $0.10 per million.
- Open checkpoints table spans Apache 2.0 releases including Clef, PurpleMIST-Flash, Laya, Bespoke Nimble, imajev-4b, and PolicyLM-1.7B.
- Archive runs through October 14, 2026, with 191 stories; figures are labelled as claims from the pages that published them.
Watch out
A desk run by an unaffiliated publisher, not TypeSafe; it states plainly that it is not affiliated and that figures are claims from public posts and official writing which can go stale. Prices and benchmark cells reflect listings at capture time, and no licence is stated for its text.
Questions about this entry
Short answers drawn from the linked project or page.
A desk that records news, benchmarks, and listed API prices for TypeSafe's hosted System One call and for other hosted APIs and open checkpoints that return a choice, a score, or a yes or no. It states explicitly that it is not affiliated with TypeSafe.
The desk says Banking77, JevBench, and Decision Index stay on their own rows. Each article ends with Verify, Compare, and Terms sections, and the story names who measured each figure.
The hosted table shows jev-1.13.0 at $0.042 per million input tokens with free output, still returned by jev-latest on October 15, 2026; jev-1.14.0 opened that day with OpenRouter listing typesafe/jev-1.14 at the same price.
Yes. The catalog includes OpenAI's Decisions API, Cloudflare's Clef models, Subquadratic's subq-snap-preview, Perplexity's pplx-decider, and Databricks' ai_decide, plus open checkpoints such as Laya, Nimble, imajev-4b, and PolicyLM.
Box on jev-1.14.0 returned edges near left 0.40, right 0.79, top 0.16, bottom 0.71 at confidence 0.91 on a drawn red square, and an empty field still returned a box at confidence 0.05; the same request on 1.13.0 returned HTTP 400.
The homepage was updated October 15, 2026, and the archive of stories runs through October 14, 2026. The desk says figures can go stale and links the write-up that printed each one.
An unaffiliated desk. The page states it is not affiliated with TypeSafe and credits primary sources including the official System One launch post, TypeSafe's docs, and the Awesome Jev directory.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: New signups no longer get free credits.
YouTube: Gary Explains the catch: Jev understands natural language but answers with structured values and confidence.
YouTube: David Ondrej explains the architecture behind Jev and how to build a business on it.
More Jev resources like this
A release guide with eval tables, pricing, curl and Python examples, and fit boundaries for Jev's early access.
Jev Guides & ArticlesArticle#community#article#pricing
Community
A community directory of projects, tools, SDKs, demos and resources built around Cloudflare Clef, the open-weight decision models that answer typed noul, choice and score questions with probabilities. Includes a searchable site at awesomeclef.com.
Jev Guides & Articles#community#github#awesome-list
Community
rohinrohin/awesome-clefJavaScript
rohinrohin/awesome-clefJavaScriptDeepInfra's survey of the decision-model category: pointer-head architecture, RLCD calibration, latency and cost figures for Jev and its rivals, and a landscape table spanning TypeSafe, AWS, Convai, Kev, OpenAI, and Ollaya.
Jev Guides & ArticlesArticle#community#analysis#architecture
Community
czmilo's long guide to TypeSafe's System One model: the 193.6x/444.6x benchmark claims, RLCD training, Cloudflare, OpenRouter, and LangChain availability, a 32K context window, and vendor caveats.
Jev Guides & ArticlesArticle#community#article#guide
Community
Kervin Hu's Neo4j Developer Blog experiment runs Jev Noul over 1,822 blocker-filtered candidate pairs from 703 synthetic contact records: F1 0.943 at a 0.5 threshold, about two cents per thousand pairs, and a hybrid reaching 0.972.
Jev Guides & ArticlesArticle#community#article#entity-resolution
Community
Jev News's desk for TypeSafe's October 14, 2026 Jev Day: Jev 1.14.0 shipped as jev-preview with opt-in images, a Box type and 262k context, plus the desk's dated API checks and what they returned.
Jev Guides & ArticlesDocs#community#news#danger-zone
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.