Jev

Jev

Jev by TypeSafe AI is a model API that takes state plus typed questions and returns Choice, Score and true/false answers with calibrated probabilities instead of generated text.

0.0 (0)
Visit Website
Founder
TypeSafe AI
Active
PlanUsage-based - $42 per billion input tokens ($0.042 per million); output tokens free · Enterprise - contact sales
BusinessB2B

About Jev

What is Jev?

Jev is TypeSafe AI's first System One model: an API that takes unstructured state plus typed questions and returns typed decisions with calibrated probabilities, rather than text your code has to parse.

Three primitives

  • Choice picks one option from a list and returns per-option probabilities and a confidence value.
  • Score rates the state against a rubric and returns a score distribution.
  • Noul answers whether a statement is true, as a value between 0 and 1.

All three can be mixed in one call and are evaluated in parallel.

Where it fits

Intent routing, confidence-gated routing to an LLM, classification, re-ranking, RAG passage filtering, citation checks, LLM guardrails and function-call selection.

Pricing

Usage-based: $42 per billion input tokens, output tokens free. Python and JavaScript SDKs plus an HTTP API.

About TypeSafe AI

Founded in 2024 and based in San Francisco, TypeSafe AI emerged from stealth in September 2026 with a $40M seed round led by DCVC.

Value & Audience

Value Proposition

Replaces slow, expensive LLM calls for yes/no, pick-one and scoring decisions with a single typed API call that returns calibrated probabilities in milliseconds, with no output parsing.

Problem Solved

Automations that use an LLM for small decisions pay for generated text, wait seconds per call and then have to parse and trust free-form output. Jev returns typed answers with confidence values so software can act on them or route low-confidence cases elsewhere.

Share this product

Product founder?

Get Badge

Tech Stack

Social & Links

Loading ratings...

Loading comments...

Gallery

Jev screenshot 1

Feedback & Roadmap

Loading feedback…

Jev FAQ

Common questions about Jev's features, pricing, and use cases

What does Jev do?

Typed, calibrated AI decisions for software automation Replaces slow, expensive LLM calls for yes/no, pick-one and scoring decisions with a single typed API call that returns calibrated probabilities in milliseconds, with no output parsing.

Is Jev free to use?

Jev is a paid product, starting at Usage-based - $42 per billion input tokens ($0.042 per million); output tokens free. Full pricing details are listed on the Jev product page on TechLogHub.

What problem does Jev solve?

Automations that use an LLM for small decisions pay for generated text, wait seconds per call and then have to parse and trust free-form output. Jev returns typed answers with confidence values so software can act on them or route low-confidence cases elsewhere.

Who is Jev built for?

Jev is built for Developers, Backend Developers, Data Scientists & ML Engineers, Startups, Enterprises.

What tech stack does Jev use?

Jev is built with Framer, Mintlify, Python, TypeScript.

What category is Jev listed under?

Jev is listed in the AI Tools & Platforms category on TechLogHub, alongside curated alternatives with community ratings and pricing comparisons.

Jev appears in

Newsletter

One email a week

TechLogHub tracks 515 tools and 471 open-source projects. Get the week's new launches, release roundups and open-source picks — nothing else.

Get the TechLogHub digest

One email a week: new and trending developer tools, fresh comparisons, and what shipped. Unsubscribe in one click.