VerdictPal
Join

Models / TypeSafe

Jev

Jev · Released 2026-09-15

TypeSafe's 15 Sep 2026 System One model. Early access. Text-only state in; typed Noul, Choice, and Score decisions out — no generated prose. 64K request budget (32K for state plus the longest question). List $0.042 per 1M input tokens; output free. No AA Intelligence Index or Vals Index row as of 19 Sep 2026.

Current TypeSafe System One workhorse for software-native classify, route, and score calls — not a chat or coding model.

Composite—
Context64K
Input / 1M$0.04
Output / 1MFree
Knowledge cutoffunpublished
Statussolid
Not enough families covered yet.Add more benchmark rows for Jev to see the family profile.
Editor's note
Recorded from TypeSafe models docs and the 15 Sep 2026 launch post (64K request budget, 32K for state plus the longest question, $0.042 / MTok input, output free) plus Vercel AI Gateway listing on 16 Sep. TypeSafe does not publish a standard public-benchmark table; vendor workflow-eval charts stay off the ledger. Jaggedness notes last reviewed 17 Sep 2026. Privacy policy (updated 19 Nov 2025) says TypeSafe will not train or fine-tune models on customer Input. No independent AA Intelligence Index or Vals Index row as of 19 Sep 2026.
Benchmark placements

Where Jev places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

No benchmark rows yet for Jev.

Family context

The three highest-scoring models with pages in each capability family. Where Jev shows up, it's highlighted.

Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

No family coverage yet.
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Jev. Scores link to the original source; gaps mean no public row exists yet.

0 sourced rows

0 of 37 catalog benchmarks have a sourced row for Jev.

Changelog
  1. Early access on the TypeSafe API and Vercel AI Gateway.
Sources

Questions this model page answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

What is Jev?

Jev is a TypeSafe model: TypeSafe's 15 Sep 2026 System One model. Early access. Text-only state in; typed Noul, Choice, and Score decisions out — no generated prose. 64K request budget (32K for state plus the longest question). List $0.042 per 1M input tokens; output free. No AA Intelligence Index or Vals Index row as of 19 Sep 2026.

What is Jev for?

Current TypeSafe System One workhorse for software-native classify, route, and score calls — not a chat or coding model.

What does Jev cost?

Jev lists $0.04 input and Free output per 1M tokens. Pricing last checked 2026-09-19.

How large is the Jev context window?

Jev publishes a 64K token context window.

What is the VerdictPal status of Jev?

Jev carries Solid status on the model atlas.

The Pack · Editorial newsletter

New tools in your inbox. Free.

One short email when a tool ships or changes status. No tracking, no third-party analytics. Unsubscribe in one click.