@typesafeai (and System One models in general) have a lot of uses, and fun to play with. New paradigm open to public now. This is a self-driving sim I spun up to test Jev today. Structured sensor state in, typed driving decisions out, steer, brake, overtake, pedestrians, speed Show more
CommunitySites & Guides
TypeSafe Jev: the First Decision-Only Model Class, Benchmarked and Priced
A release guide with eval tables, pricing, curl and Python examples, and fit boundaries for Jev's early access.
- Category
- Sites & Guides
- Format
- Article
- Published by
- Community
- Author
- Developers Digest
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- Lists POST /v1/systemone with model jev-latest at $0.042 per million input tokens and free output.
- Eval table: Jev 76.0% at $0.0001 and 0.4 s against GPT-6 Sol 79.1% at $0.2152 and 34.3 s.
- Cites the parallel-questions cookbook at 12.2x cheaper and 10.0x faster than per-question calls.
- Notes the Choice cap of 255 options and that no OpenCode provider exists yet.
Watch out
Aggregates TypeSafe first-party sources and repeats the vendor's own caveat that its multipliers are the high end of real-world gains.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
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 like this
A heavily footnoted claims audit that separates documented Jev facts from marketing, including the seed round, third-party tests, and missing transparency.
Sites & GuidesArticle#community#article#analysis
Community
DataCamp's explainer walks the eval tables behind System One models, from 67.8% workflow accuracy and 0% structured-output errors to the $0.042 per million token price and how to call the API.
Sites & GuidesArticle#community#article#evaluation
Community
Latent Space's AINews roundup of launch day: the Jev thread atop Hacker News, the RLCD decision-model framing, and community readings that compare it to DSPy-style typed signatures for routing and scoring.
Sites & GuidesArticle#community#article#models
Community
From the community
Posts from builders shipping with Jev right now.
Jev Driving Lab: a playground for System One models
200 rows, 32 template families, and traps, judged in one call
First test with Jev (TypeSafe System One): 200 rows, 32 template families, traps — 'yes' rows with "we'll pass", 'no' rows with 'absolutely, happy to meet'. The single Jev question scored 100%. My 12 dimensions scored 98%. I had designed a task my own question could ace.
jev(): Postgres WHERE clauses in plain language
I think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1s Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
A real-time ad blocker that classifies every DOM element
I build an undetectable realtime adblocker extension with typesafe It checks every dom element and classifies as ad/non-ad and removes it if true Extremely fun to work with, expecting an incredible shift in how AI is being used in the future
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Jev plus Astra beats the Ender Dragon for under a dollar
Harness: I made Jev control the player, has access to WASD, space, click, and mouse movements. Astra is the planner that sends instructions to Jev async. Learning: Each time the agent would fail, Astra would add skills as mjs files, that it can draw upon in different scenarios, Show more
Tool calling as classify plus action, back to twelve-factor agents
jev is the best excuse you could possibly have to go re-read 12 factor agents. Tool calling itself can be decomposed into classify+action, if you learn to design ai programs as pipelines that switch breathlessly between classification, structuring data, deterministic code, AND Show more
@dillon_mulroy
i think jev is resonating with devs so well b/c it unlocks so many opportunities for composing ai into systems and products rather than ai _becoming_ the product/system really does feel like it was a missing primitive