Did OmniaKey actually benchmark it, or just confirm it answers?

Only connectivity. The authors sent one live request and got HTTP 200 from jev-1.13.0, and say plainly that this is not a latency, calibration or quality benchmark. The 70 to 500 ms figure is TypeSafe's own claim.

Can I chain questions so one answer conditions the next?

Not within one request. Multiple questions are evaluated independently and in parallel against the same state, so one answer does not automatically condition another. If question B depends on A, your code has to make that explicit.

Do I need early-access approval to use it through OmniaKey?

No. The post says no TypeSafe early-access application or waitlist approval is required, and lists jev-1.13.0 plus the jev-latest alias. Their route is POST https://api.omniakey.com/v1/alpha/search, not TypeSafe's own endpoint.

What are the limits on Choice options and Score levels?

A Choice can hold up to 255 options and a Score accepts 2 to 10 descriptive levels. Noul has no separate confidence field, because its zero-to-one value is already the probability of yes.

What context and throughput limits does Jev have?

64K tokens per request, with 32K reserved for state plus the longest question, and published default limits of 250,000 input tokens per second and 1,200 requests per minute, subject to change.

How is the Jev API priced?

The direct API price is $0.042 per 1M input tokens and output is currently free, with a vendor latency claim of 70 to 500 ms end to end. Prices, limits and capability claims come from TypeSafe's own release post and documentation.

Why is the model called Jev, and what is the System One label?

TypeSafe named it after economist William Stanley Jevons, and the System One label draws on the fast, intuitive System 1 from Kahneman's Thinking, Fast and Slow. The official spelling is Jev, not an acronym.

CommunityJev Guides & Articles

Jev model explained

OmniaKey's fact-checked table for jev-1.13.0, limits, and pricing, plus a live connectivity check through OmniaKey's alpha search endpoint.

See highlights

Open omniakey.com

Format: Article
Published by: Community
Author: OmniaKey
Last verified: Sep 2026

Tagscommunity article explainer pricing

Works forJev for Classification Jev for Routing

Used inJev for Software & DevTools

Highlights

Fact-checked 20 September 2026. Values come from TypeSafe docs, not a private briefing.
Lists jev-1.13.0, jev-latest, and POST https://api.typesafe.ai/v1/systemone.
OmniaKey route: POST https://api.omniakey.com/v1/alpha/search.
64K context; 32K for state plus the longest question. Published limits 250k tokens/s and 1,200 req/min.
Authors sent one live request and got HTTP 200 from jev-1.13.0; not a quality benchmark.

Watch out

OmniaKey's own gateway article. The connectivity check is not latency or accuracy testing.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: New signups no longer get free credits.

Hacker News: Simon Willison's overview of Noul, Choice, and Score, and where a decision model fits.

benwerd53 pointsJev introduces a new shape of LLMRead the thread on Hacker News

Hacker News: swyx posts the Latent Space interview with Diogo Almeida.

swyx4 pointsJev: System One Models for Prod, Not God – With Diogo Almeida, CEO, TypeSafe AIRead the thread on Hacker News

X: Diogo Almeida in five minutes

Related terms

Glossary definitions related to this entry.

Token pricing

More Jev resources like this

TypeSafe Jev explained

Requesty's September 2026 guide to Jev as a System One model: state, Choice, Score, and Noul, plus how Requesty routes typesafe/jev-1.13.0.