TypeSafe's Jev hits 13% of Vercel paid teams in 24 hours
TL;DR
- Jev reached roughly 13% of Vercel AI Gateway paid teams within 24 hours, 2x the GPT-5.6 family and 6x Fable 5.1 at the same mark.
- Jev is a decision model, not a chatbot: state goes in, typed Choice/Score/Boolean answers come out with attached probabilities.
- Vercel, Cloudflare, LangChain and Langfuse all wired Jev into their stacks within three days of its September 15 launch.
TypeSafe's decision model Jev reached roughly 13% of Vercel's AI Gateway paid teams within 24 hours of going live, making it the fastest-adopted model in the gateway's history, Forbes reports. At the same 24-hour mark, that was 2x the GPT-5.6 family and 6x Fable 5.1.
Jev, launched September 15, is not a chatbot. It takes program state in and returns typed answers: a Choice, a Score, or a Boolean, each with a probability attached. TypeSafe calls it a 'System One' model, named after the economist William Stanley Jevons.
Vercel's own team put it flatly 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." Within three days, Cloudflare, LangChain and Langfuse had all wired it into their stacks; LangChain exposes it as a TypeSafeClassifier integration.
The pricing is unusual for a hosted model: $0.042 per million input tokens with free output, returning decisions in under half a second. TypeSafe's own numbers put Jev at up to 193.6x faster and 444.6x cheaper than frontier LLMs on its workflow evaluations. Those are the company's in-house peak figures, not independent benchmarks.
Shared on Bluesky by 1 AI expert
Originally reported by forbes.com
Read the original article →Original headline: TypeSafe's Jev Hits 13% of Vercel Paid Teams in 24 Hours, 2x GPT-5.6 Family and 6x Fable 5.1