Jev Day 2026 · Independent report
Jev long context on Jev Day: 262k tokens with TypeSafe-Danger-Zone-Long-Context
Default context stays 64k / 32k on 1.13 and 1.14. The long-context header raises both limits to 262k and is slower and less accurate. Peter Banda posted a 128K screenshot.
Compiled by jevmodel.ai. We read the cited posts and documentation. The measurements stay with their authors. We have not rerun them.
64k / 32k unless the header is set
A Jev request has two context limits. Per-request context is the state plus all questions combined. Per-question context is the state plus any one question. There is no separate cap on the number of questions beyond those two limits. On both jev-1.13.0 and jev-1.14.0 the defaults are 64k per request and 32k per question.
Long context is off by default and works on both versions. TypeSafe-Danger-Zone-Long-Context: true raises both limits to 262k tokens. Requests without the header keep the table values. Almeida writes that Jev already supported longer contexts than TypeSafe allowed, and that the earlier cap was a product choice because the uses TypeSafe prefers should manage state more carefully.
Sources:[34] TypeSafe AI[154] TypeSafe AI[150] Diogo Almeida
Same token price, slower and less accurate
Long context costs the same per token as any other request. The models page says it is slower and less accurate than staying within the default limits, and to turn it on only for requests that need it. The blog says Jev, like other models, is less reliable on longer contexts, and that the default cap encourages tighter state in production.
Image tokens also count toward context length. A long document plus images can hit max_tokens_exceeded even when the header is on. The long-context curl example on the models page still sends model jev-latest, which on 15 October 2026 resolves to jev-1.13.0.
Sources:[154] TypeSafe AI[153] TypeSafe AI[155] TypeSafe AI[34] TypeSafe AI
A 128K field note
Peter Banda posted “Happy JevDay! Tested the danger zone today - up to 128K tokens” with a screenshot. The post names no model id, no question list, no latency, and no accuracy. 128K sits between the default 64k per-request limit and the 262k header limit. Treat it as one author’s screenshot, not a measured 262k run.
Questions
Does jev-1.14.0 default to 262k context?
Both 1.13.0 and 1.14.0 default to 64k per request and 32k per question. 262k needs TypeSafe-Danger-Zone-Long-Context: true on that request.
Does long context work on jev-1.13.0?
Yes. The models page says long context is off by default and works on Jev 1.14 and Jev 1.13.
Sources:[154] TypeSafe AI
Does 262k cost more per token?
The models page says long context costs the same per token as any other request, and that it is slower and less accurate than the default limits.
Sources:[154] TypeSafe AI
Sources and reading notes
The summaries below are paraphrases. Each link opens the original source, including its surrounding context.
TypeSafe AI
Source checked:
[34] Jev 1.14 and 1.13 model card: price, context and aliases
The models page lists jev-1.14.0 and jev-1.13.0 at $42 per billion / $0.042 per million input tokens, with output free. Default context is 64k tokens per request and 32k per question. The table lists Input as Text for both. Jev 1.14 is dated as available from 14 October 2026. Both jev-latest and jev-preview point at jev-1.14.0. A warning on the page says there is no preview build. jev-1.13.0 stays available as a versioned id.
Canonical model card as accessed 26 October 2026. On 15 October 2026 the same page pointed jev-latest at jev-1.13.0 and jev-preview at jev-1.14.0. Audio and video are excluded here; convert those to text or structured fields first. Image files and 262k context are documented under danger-zone headers on this page and on the Images page. Rate limits are per organization in the developer console.
TypeSafe AI
Source checked:
[154] Long context: 262k behind TypeSafe-Danger-Zone-Long-Context
Long context is off by default and works on Jev 1.14 and Jev 1.13. The header TypeSafe-Danger-Zone-Long-Context: true raises both the per-request and per-question limits to 262k tokens. Requests without the header keep 64k / 32k. The same per-token price applies. The page says long context is slower and less accurate than the default limits.
Official models documentation as accessed 15 October 2026. There is no separate cap on the number of questions beyond those two context limits.
Diogo Almeida (@CompleteSkeptic)
Published:
Source checked:
[150] Almeida: context lengths should be up to 262k
Almeida writes that Jev already supported longer contexts than TypeSafe allowed in production. He says the earlier cap was a product choice, and that context lengths should be up to 262k. The opt-in header is TypeSafe-Danger-Zone-Long-Context: true.
Fourth post in the JevDay thread. The models page documents 262k as both the per-request and per-question limit when the header is set, on jev-1.13.0 and jev-1.14.0. Default limits stay 64k / 32k.
TypeSafe AI
Published:
Source checked:
[153] Jev: For the builders AND dreamers
The Jev Day blog ships jev-1.14.0 under jev-preview, with experimental images, a Box type, and longer context behind danger-zone headers. TypeSafe says jev-latest will move to jev-1.14.0 in a week, jev-1.13.0 will stay available, and it intends 60 days of warning before deprecating 1.13.0 and 30 days for 1.14.0. Images are composable through an assets map. TypeSafe says models, including Jev, perform worse on multimodality than on pure text.
Company blog, metadata timestamp 15 October 2026 00:22 UTC; the models page dates Jev 1.14 as available from 14 October 2026. The Measuring Intelligence section describes an internal ranking of open-weight models and asks readers not to treat it as settled. The text we opened does not print those scores, so this site does not repeat a table we could not read as numbers.
TypeSafe AI
Source checked:
[155] Images: assets map, size limits, and the images header
Images and Box questions are off until the request sends TypeSafe-Danger-Zone-Images: true. Each image is listed once in assets and referenced in state, instructions, or criteria. Jev 1.13 and Jev 1.14 both accept images. Formats are PNG or JPEG stills, 16 MiB per file, 256 to 1568 pixels on each side, with a 32 MiB request-body limit. The API strips EXIF and does not apply EXIF orientation. Image tokens are billed as input at the same per-token price as text.
Official Images page as accessed 15 October 2026. The page labels images and Box as dreamer-ready, below TypeSafe’s production bar, and says the format, answers, and limits can change between releases. A 256×256 image is below the minimum pixel area. The page does not publish a token-count formula for images.
Peter Banda (@0xbnd)
Published:
Source checked:
[159] Peter Banda: a 128K-token danger-zone test
Banda posted “Happy JevDay! Tested the danger zone today - up to 128K tokens” with a screenshot.
A single field note on 14 October 2026. The post names no model id, no question count, no latency, and no accuracy. 128K is below the documented 262k header limit.