Independent guide, not affiliated with or endorsed by TypeSafe AI. “Jev” is TypeSafe’s name for its model, used here only to identify it. Official documentation: docs.typesafe.ai.
Jev AI (TypeSafe): pricing, limits and independent measurements
Jev is a decision model, not a chatbot: you give it some text and typed questions, and it returns answers with probabilities in one pass. It costs $0.042 per million input tokens with output free. Below is what that means in practice, measured over 3,455 historical billed requests to Jev 1.13 via OpenRouter on 23 September 2026; to work out your own bill, use the Jev pricing calculator.
| Made by | TypeSafe AI, San Francisco (founded 2024) |
|---|---|
| Released | 15 September 2026; direct stable alias jev-1.13.0; preview 1.14 |
| Price | $0.042 per 1M input tokens; output free |
| Measured per-request overhead | ~260 tokens on every call |
| Context | Direct default 64k / 32k, opt-in 262k; OpenRouter 262,144 |
| Rate limits | Per organization: check console tokens/s and requests/s |
| Measured latency | 375–734 ms warm (1K–32K tokens) |
| Direct signup | September pause is historical; check console for current status |
What is Jev AI?
Jev is the first of what TypeSafe AI calls System One models, after the fast, intuitive thinking in Kahneman’s work. It was announced on 15 September 2026 alongside a US$40 million seed round led by DCVC. Instead of generating text token by token, it reads your input once and answers every question you ask about it in parallel. At launch it supported these three text primitives; OpenRouter now also documents image/Box support for 1.14:
- Choice returns the selected option, a probability for every option, and a confidence.
- Score returns a position on an ordered rubric (2–10 levels), per-level probabilities, and a confidence.
- Noul returns a yes/no probability between 0 and 1.
TypeSafe reports 40–200× faster and 40–400× cheaper than frontier LLMs on its own workloads; those are its figures, not independent ones. What we measured is below.
Is Jev AI free?
Historical September 2026 report, not a current offer: accounts opened while signup was open got $5 of credit, reported by VentureBeat, which buys about 119M input tokens: about 476K answered questions on a typical support-triage workload. Vercel’s launch offer of free Jev calls ended on 25 September 2026. What the credit covers for your workload.
How much does Jev AI cost per decision?
About $10.50 per million answered questions on a 500-token text with 4 questions per call. Two things decide the bill besides the price: every request bills about 260 tokens on top of your text, and the text is billed once per call however many questions you ask, so batching them is most of the saving.
At 100K items a day that is $126.00 a month. The cheapest LLM in our comparison, GPT-5.6 Luna, would bill $624.00, 5.0x Jev’s bill; GPT-6 Astra $29,700, 236x. Put in your own numbers or see every model ranked.
Comparison LLM base token rates checked against official sources on 17 October 2026; other tiers and long-context rates can differ. Credit was reported in September, not confirmed as a current offer. Company background and launch claims are historical September sources.
How do I get Jev AI API access?
Historically, TypeSafe paused new direct signups on 22 September 2026; current direct signup status is not reverified. Our September 2026 listings recorded access without a TypeSafe account through OpenRouter, Vercel AI Gateway, Netlify AI Gateway, Cloudflare Workers AI. Current availability and prices for gateways other than OpenRouter have not been reverified. OpenRouter documents access without a TypeSafe account and lists 262,144 tokens of context. Our end-to-end OpenRouter test was on 23 September 2026. Every route, with a working call for each.
How fast is Jev AI?
At launch, TypeSafe stated 70–500 ms end to end. Through OpenRouter we measured 375 ms for 1,000 tokens of text and 734 ms for 32,000, on a reused connection; the same small request took 1,630 ms when it had to open a connection first. Latency and rate limits in detail.
What are Jev AI’s limits?
Rate quotas are per organization. Direct default context is 64k total, 32k state plus any question. Explicit long context raises both to 262k with slower, less accurate results. OpenRouter publishes 262,144. Our September Jev 1.13 observations are historical evidence. See context-mode requirements. Estimate your request’s size.
Can Jev AI chat or write text?
No. It returns labels, scores and probabilities, not prose. That makes it a replacement for an LLM wherever software needs a decision (routing a ticket, flagging a comment, checking an answer) and no help for writing, summarising or open questions.
Is Jev AI accurate?
We did not measure accuracy, and TypeSafe’s figures are its own. In one independent test with 128 candidate answers, Jev picked the right one 60% of the time and the open-weight Laya 39%. What we did measure is that its confidence is useful: across 960 paired answers we reworded or translated, the least confident third moved15.6 times as much as the most confident. Route low-confidence answers to a person or a fallback.
Jev AI vs GPT, Claude and Laya
On price per decision, Jev undercuts every LLM we track, from 5.0x against GPT-5.6 Luna to 236x against GPT-6 Astra, but it only answers typed questions. Jev vs GPT-5.6 Luna, all eight LLMs, and Jev vs Laya, the open-weight model you can run yourself, which answered a short question in 7.8 ms on our Mac.
Is Jev AI the same as JEV (Japanese encephalitis virus)?
No. This page is about Jev, the AI model from TypeSafe AI. JEV is also the usual abbreviation for Japanese encephalitis virus, an unrelated medical topic.
Jev AI questions
What is Jev AI?
Jev is a decision model from TypeSafe AI, released on 15 September 2026. Instead of writing text, it takes some input (the "state") and typed questions, and returns answers with probabilities in one pass: Choice picks an option, Score places the input on a rubric, and Noul gives a yes/no probability.
Is Jev AI free?
The current models page publishes token pricing. Jev costs $0.042 per million input tokens, and output is free. A historical September 2026 VentureBeat report described $5 of credit (not reverified as a current offer), which would buy about 119M input tokens.
How much does Jev AI cost per decision?
About $10.50 per million answered questions on a typical support-triage workload (500-token text, 4 questions per call), including the ~260 tokens per request measured on OpenRouter Jev 1.13 on 23 September 2026, not reverified for 1.14 or long context. That workload at 100K items a day costs $126.00 a month.
How do I get Jev AI API access?
OpenRouter documents access without a TypeSafe account and publishes 262,144-token context. The September direct-signup pause is historical; check the console for current availability.
How fast is Jev AI?
At launch TypeSafe stated 70–500 ms. In our historical 23 September 2026 Jev 1.13 test through OpenRouter, a request with 1,000 tokens of text took 375 ms and one with 32,000 tokens took 734 ms on a reused connection; a fresh connection added about a second.
What are Jev AI's limits?
Direct rate quotas are per organization. Default context is 64k total / 32k state plus any question; the explicit long-context header raises both to 262k. OpenRouter publishes 262,144. September measurements do not establish current route limits.
Can Jev AI chat or write text?
No. Jev returns typed decisions with probabilities, not prose, so it replaces an LLM where software needs a label, a score or a yes/no: routing, classification, moderation, checks. For writing, summarising or open-ended answers you still need an LLM.
Is Jev AI the same as JEV, the Japanese encephalitis virus?
No. This page is about Jev, the AI model from TypeSafe AI. JEV is also the abbreviation for Japanese encephalitis virus, an unrelated medical topic.
Get an email when direct signup reopens
TypeSafe gave no date. Leave an address and we will send one email when you can get a key direct again, or if the price changes.
Background from TypeSafe’s announcement and Wikipedia, read 2026-09-27. Price and limits checked against docs.typesafe.ai/models on 2026-10-17. Measurements: jev-fanout-bench, open code and data; the tables are also a Hugging Face dataset. Updated .