Jev from @typesafeai is on AI Gateway. Build agents that decide, route, score, and stop in milliseconds: 𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({ 𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟', 𝚜𝚝𝚊𝚝𝚎, 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜, }); vercel.com/changelog/type…
API & Models
Context window
The 64k-token budget covering state plus all questions, with a 32k sub-budget for state plus the longest question.
- Category
- API & Models
- Also known as
- —
- Related terms
- 4
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Jev ingests the state once and evaluates every question against it in parallel. The 64k budget covers the state plus all questions combined, while 32k applies to the state plus the single longest question.
The two budgets are what make speculative fan-out practical: many questions fit in one request as long as no single question is enormous. Accuracy still falls as state grows with irrelevant detail, so the limit is not a target.
Tagsapilimits
Related terms
Definitions that connect to this one.
StateThe content a request asks Jev to evaluate: a string, a named object, or an array of messages, shared by every question in the request.Core ConceptsSpeculative fan-outAsk every question the system might need in one request — including ones only some branches use — and let code discard the rest.PatternsPrimitive limitsThe hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.PrimitivesContext rotThe accuracy loss that comes from padding state with detail unrelated to the question; filter state before sending it.Core Concepts
From the directory
The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.
Sites & GuidesDocs#official#docs#models
Official
Ask everything the system might need in one request, then let code throw away what it does not use. The ticket-triage example sends a category plus four speculative questions in parallel.
Practices & PatternsDocs#official#patterns#batching
Official
From the community
Posts from builders shipping with Jev right now.
Vercel ships the AI SDK provider for Jev
Computer use at 155× cheaper than Opus 5
i built computer use using @typesafeai ! it is 155x cheaper than opus 5, ~20x faster, and generalizes across OS's more on how it works in the vid & thread below:
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Foreman keeps coding agents on task
I just open sourced Foreman: a software factory foreman built with @typesafeai's Jev. Coding agents work the factory floor. Foreman watches them, continuously assessing progress, completeness, tests, drift, and verification, and intervenes when needed. GitHub: Show more
Unclutter: an ad and slop blocker that runs on Jev
introducing Unclutter: a smart ad + slop blocker with Jev 🤓 it auto cleans up pages from slop elements: ⬖ ads ⬖ cookie banners ⬖ upsells ⬖ bs dialogs BYOK. open source + free, download below 👇
An open-source BS meter for debates and investor calls
🚨 Open Source Jev BS meter you can use this to analyze any debate / investor call / interview / sales pitch / podcast video fact check live , for example this dario interview cost 60 Jev calls / 111K tokens / $0.0047 github.com/ChetasLua/jevm…
🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check
A Jev-shaped model on Cerebras and Qwen
Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b. Similar quality, similar performance, but vastly different cost. TypeSafe was way cheaper, and did beat Qwen on performance. Closest we can get using LLMs I think. Source: github.com/iammrduncan/ty…
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x