Vercel, Cloudflare, and others quickly add Jev, as it makes AI tool selection much faster and cheaper; TypeSafe: Jev matches GPT-5.6 and Sonnet 5 workflow evals
Most of what an AI agent asks a frontier model to do is not writing. It is choosing. Which tool to call next, whether to retry, whether a command is safe to run.
ForbesJosipa Majic Predin
Context & Ripple Effects
TypeSafe introduced Jev on September 16 as a model that returns typed, probabilistic decisions rather than generated prose, positioning it for workflow steps such as routing and classification. Its claimed workflow-evaluation parity with GPT-5.6 and Sonnet 5 gives infrastructure providers a basis to expose it alongside general-purpose models.
The move extends a design already visible in OpenAI's model-routing architecture, where a router selects between efficient and reasoning models. Jev makes that selection layer itself a specialized API product, following its September 16 debut.
First-order effects
Vercel and Cloudflare users can apply Jev to agent tool selection, retries, and safety decisions without assigning those steps to a frontier text model.
TypeSafe gains distribution through two developer-infrastructure platforms while its workflow-evaluation claim is tested in production integrations.
Second-order effects
Agent builders can separate decision calls from text-generation calls, reducing the amount of frontier-model inference used for routine workflow control.
General-purpose model providers face a narrower role in agent stacks when platforms offer specialized decision models for routing and classification.
Third-order effects
If specialized decision models sustain comparable workflow quality, agent architectures may standardize on multi-model pipelines in which generation, reasoning, and control are distinct services.
Developer clouds that make model selection portable across providers gain leverage over the routing layer, rather than competing solely on access to a single model.
The trend: AI agent stacks are moving from one-model workflows toward routed, specialized services that reserve costly generative models for tasks that require them.
Jev is not open-source and only available via API. Here's an open version called Nimble which performs just as well. https://github.com/...
@airesearch12
Florian S on x
JevBench results are in. Jev still in the lead, but it's close.
@venturetwins
Justine Moore on x
Jev can serve as better natural language search on websites. It can scan thousands of Zillow listings and classify properties by things you can't normally filter for - e.g. architecture, renovation status, proximity to freeways. This was done in <20 sec and costs $0.18 👇
@altryne
Alex Volkov on x
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be amazed …
@levie
Aaron Levie on x
Jev will be super helpful for agents to make split second decisions in workflows, data classification, judgment calls, and hundreds of other use-cases in the enterprise. Here's a quick demo with Box and Jev to make that real... This all happens nearly instantly and at almost no …
@rasbt
Sebastian Raschka on x
It's easy to dismiss Jev it as “just a classifier
@ibocodes
Ibo on x
i have jev access and i genuinely can't think of one thing to use it for everyone's jevpilled and i'm sitting here with fomo what are you actually using it for every day not demos, real work
@yuchenj_uw
Yuchen Jin on x
Jev has spoken. It picked which model is AGI. 20-200x faster. 40-400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn't burn through $0.10.)
@aaazzam
Adam Azzam on x
Jev is an incredible model router. Ask Jev which models can solve a user's task, and route it to the cheapest one. We have a new frontier model overnight.
@dabit3
Nader Dabit on x
Absolutely insane how fast the AI space moves.
@rbilgil
Robin Bilgil on x
Made a real-time slop detector with jev as you scroll [video]
@minchoi
Min Choi on x
ChatGPT co-inventor just shipped a different kind of AI. It doesn't chat. It decides. 20-200x faster decisions. People are already running it on Doom, Minecraft, browser agents, LLM judging + more. 10 wild examples: 1. Jev plays doom
@alexatallah
Alex Atallah on x
“Isn't Jev not a frontier model? how could it be *more* useful then?” We put together a clear video and playground with multiple mini demos to visually demonstrate. https://openrouter.ai/...
@vercel
@vercel on x
Jev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
@layton_gott
Layton Gott on x
Yesterday I said Jev would open a ton of doors... 24 hours later, this exists. Cua built a 2.8MB model that scored 99.7% on their form-filling eval. Hosted Jev scored 83.6%. Not to mention it's FREE and only 706K parameters. Small enough to run locally with not even 1gb or ram. F…
@deryatr_
Derya Unutmaz on x
After trying out Jev, I'm going to go out on a limb & say this could become as big as ChatGPT, if not bigger, from one of the co-inventors of ChatGPT! The potential of Jev is almost beyond imagination to accelerate AI implementation & I'm incredibly excited to see how it evolves
@andrewchen
Andrew Chen on x
Jev is going to change the prosumer/consumer AI landscape by unlocking a specific thing: Ad-supported + free AI native apps this is going to usher in a generation of new AI-native marketplaces, social networks, photo apps, messaging, calendars, email, collab tools, and much more.…
@moongotchi
@moongotchi on x
Jev is INSANE. I built this in an evening and morning. A real-time trading bot ingesting onchain+offchain data to make rapid decisions about trades. Fully autonomous. So far it has lost me $31,680.
@jarrodwatts
Jarrod Watts on x
I built a trading bot with Jev! Jev decides if it should “buy” or “sell”, given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → https://jev-trader.vercel.app/
@iam_zachi
Zachi on x
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 [video]
@kunchenguid
Kun Chen on x
poor guy claim to have built Jev a year ago but no one cared, and now Jev stole all the thunder many people are saying “you gotta tell your story” or “marketing is important
@nathanflurry
Nathan Flurry on x
hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by new, …
@nailthy62
Nailthy Tang on x
jev is insane 🫣 it makes realtime virtual try-on hauls possible. built this experiment for Drape with @typesafeai > i talk > jev reads transcript + what i'm wearing > picks from my closet > changes my outfit in realtime cost: $0.0011 per decision time: ~620ms per decision imagine…
Roman Pinchuk
Roman Pinchuk on linkedin
Everyone's buzzing about Jev, the new AI model from a ChatGPT inventor, promising cheaper and faster intelligence. …