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
AI builders have been moving from a single-model approach toward systems that select among models and steps: OpenAI described GPT-5 as using a router between efficient and reasoning models, while coverage of agents highlighted their growing inference-compute demands. Jev applies that division of labor to the frequent, narrow decisions inside an agent workflow rather than to text generation.
Vercel and Cloudflare adding Jev gives TypeSafe distribution through two developer infrastructure platforms. TypeSafe says Jev matches GPT-5.6 and Sonnet 5 on workflow evaluations; that is a vendor-reported evaluation result, not a general capability comparison.
First-order effects
Vercel and Cloudflare users gain Jev as a dedicated layer for tool selection, retry decisions, and safety checks within AI-agent workflows.
TypeSafe gains immediate placement in developer platforms, while Jev’s claimed workflow-evaluation parity positions it against using frontier models for those decisions.
Second-order effects
Frontier-model providers face pressure to justify using general-purpose models for repetitive routing and judging tasks when a specialized decision model is available through major gateways.
Agent-platform teams can separate decision latency and cost from generation quality, making routing and evaluation design a more visible part of workflow performance.
Third-order effects
If specialized decision models perform reliably across production workflows, agent stacks may decompose into distinct generation, routing, and evaluation layers rather than relying on one frontier model for every step.
That decomposition would shift differentiation toward the platforms that can observe, route, and swap components across workloads, reinforcing the infrastructure demands of AI agents.
The trend: AI-agent infrastructure is unbundling the general-purpose model into specialized components for generation, routing, and workflow evaluation.
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. The demo pulls an incident report from Box, asks wheth…
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.)
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
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.
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 …
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.
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/
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]
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.…
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
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
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, …
“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/...
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
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.
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…
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…
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 👇