proomt

Search

Search posts, papers, and topics

All posts

VercelRohan Taneja2 min readrelease notesintermediate

TypeSafe AI's Jev now available on AI Gateway

Read on vercel.com

Summary

Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.

  • Jev evaluates all declared questions in parallel, returning typed answers with confidence scores, avoiding token‑by‑token text generation.
  • TypeSafe AI claims Jev is up to 193.6× faster and 444.6× cheaper than LLMs for workflow evaluations.
  • Use the AI SDK 7 `experimental_evaluate` API: provide model, state, and a map of questions to get structured decisions.
  • Supports Zero Data Retention and No Training per request, with logs, custom reporting, and budget accounting in AI Gateway.

Teams building AI agents or automated decision pipelines need fast, cost‑effective, structured evaluations with built‑in security and observability.

5/10
llmapi designobservabilitysecurityperformanceml infra

Related reading

  2. Jev is the fastest-adopted model in AI Gateway history

    Vercel reports that the Jev decision model was adopted by 13% of paid teams within its first day, outpacing prior model launches. Jev claims to be up to 194× faster and 445× cheaper than general‑purpose LLMs while returning structured, probabilistic decisions.

    Vercelvercel.com1 minHN21

  3. Introducing System One Models and Jev

    TypeSafe AI announced its first “System One” model, Jev, a non‑text‑generating LLM that outputs type‑safe structured decisions with calibrated probabilities. It claims 40‑200× lower latency (70‑500 ms) and 100‑500× lower cost versus frontier LLMs, no hallucinations, and parallel sampling. The post includes a side‑by‑side demo, a custom “workflow” benchmark comparing Jev to GPT‑5.6/6 and other mod…

    Hacker News front pagetypesafe.ai9 minHN1824480lobste.rs26

  5. Reverse-engineered Jev-like model

    Jevlike is an open‑source starter model that scores a list of text options in a single forward pass. It provides a minimal architecture (option queries, shared dot‑product scorer), synthetic data generation, training/evaluation CLI, and examples on Doom and chess. The repo supports a byte‑level encoder or a frozen Hugging‑Face encoder (e.g., Qwen2.5‑0.5B), runs on CPU/MPS/CUDA, and reports benchm…

    Hacker News front pagegithub.com4 minreleaseHN16224

  6. I turned Jev into a (lousy) chatbot

    jevchat is a Python CLI that turns the Typesafe Jev API into a symbol‑level chatbot by repeatedly asking Jev which next character to emit. It offers interchangeable sampling strategies and alphabets, live generation stats, and a benchmark mode that quantifies performance trade‑offs.

    Hacker News front pagegithub.com5 minHN17048