Jev Day 2026: Jev 1.14.0, images, Box, and 262k context
On 14 October 2026 TypeSafe posted a Discord town hall with Diogo Almeida and Allie at 1:14 PM, then shipped Jev 1.14.0. Images, a Box question type, and 262k context sit behind danger-zone headers. The models page, accessed 26 October 2026, points both jev-latest and jev-preview at jev-1.14.0.
Compiled by jevmodel.ai. Independent notes on TypeSafe’s 14 October 2026 release. Measurements stay with their authors. We have not rerun them.
- TypeSafe-Danger-Zone-Images
- Turns on image files and Box questions. jev-1.13.0 and jev-1.14.0 both accept images. Box needs jev-1.14.0 or jev-preview.
- TypeSafe-Danger-Zone-Long-Context
- Raises per-request and per-question context to 262k tokens on both versions. Default stays 64k / 32k.
- Aliases on 26 October 2026
- jev-latest and jev-preview both point at jev-1.14.0. jev-1.13.0 stays a versioned id. Price $0.042 per million input tokens, output free.
The town hall and the thread
TypeSafe posted a teaser, “what’s this? Jev is evolving!”, and asked people to join a town hall with Diogo Almeida (@CompleteSkeptic) and Allie (@allietheicon) at 1:14 PM. A follow-up in the same thread says the session is streamed live from Discord. The opening post does not name a timezone. This page repeats the clock time as TypeSafe wrote it. We do not have a transcript of the call.
Almeida then posted a JevDay thread. TypeSafe published the blog “Jev: For the builders AND dreamers.” The models page dates Jev 1.14 as available from 14 October 2026. The blog’s metadata timestamp is 15 October 2026, 00:22 UTC.
Sources:[146] TypeSafe AI[147] Diogo Almeida[153] TypeSafe AI[34] TypeSafe AI
Danger-zone headers
Almeida splits early adopters from production infrastructure. He writes that the first public Jev release favored stable infrastructure, and that this release is for tinkerers, with a gate so people can opt into the danger zone. TypeSafe CTO Erik Gafni linked the same blog and named image inputs, a new output type, and longer context.
The documented headers are TypeSafe-Danger-Zone-Images: true and TypeSafe-Danger-Zone-Long-Context: true. The blog calls those features better than what exists elsewhere in TypeSafe’s view, still too jagged to vouch for production, and here to stay for later models. Almeida also mentions an opt-in so users can help find jaggedness, and says TypeSafe still will not train on that data. The post does not name that flag.
Sources:[147] Diogo Almeida[157] Erik Gafni[153] TypeSafe AI[151] Diogo Almeida[155] TypeSafe AI[154] TypeSafe AI
jev-latest, jev-preview, and the one-week cutover
jev-1.14.0 is the newest release. Almeida calls it better overall, mostly a drop-in replacement, with the largest gain on multilingual support. Price stays $0.042 per million input tokens, output free, on both 1.13.0 and 1.14.0. Default context stays 64k tokens per request and 32k per question. The models table lists Input as Text for both rows.
The Jev Day blog said jev-latest would move to jev-1.14.0 in a week from that post. The models page, accessed 26 October 2026, points both jev-latest and jev-preview at jev-1.14.0, and says there is no preview build. jev-1.13.0 stays available as a versioned id and is not deprecated. TypeSafe intends 60 days of warning before formally deprecating 1.13.0, and 30 days for 1.14.0, and says it will publish a deprecation policy before those dates. If you have tuned confidence thresholds on one version, the models page says to send that versioned id and switch when you are ready.
Sources:[152] Diogo Almeida[153] TypeSafe AI[34] TypeSafe AI
Field notes from 14 and 15 October
OpenRouter posted that Jev 1.14 is on OpenRouter, with small overall gains, multilingual as the largest upgrade, experimental image input, and the same $0.042 per million input price. The post does not print an OpenRouter model id. openrouter.ai/typesafe/jev-1.14 returned not found on 15 October 2026.
Peter Banda posted that he tested the danger zone up to 128K tokens, with a screenshot. The post names no model id, no question count, no latency, and no accuracy. 128K is below the documented 262k header limit.
Jev Day articles
Four reports unpack the model cutover, native images, the Box type, and the 262k header. Each page keeps the official limits next to the field notes.
Jev 1.14.0: jev-latest cutover, jev-preview, and OpenRouter
jev-1.14.0 is the current jev-latest and jev-preview target. Price is unchanged. OpenRouter posted that 1.14 is listed, without printing a model id.
Read the articleJev Day images: TypeSafe-Danger-Zone-Images and the assets map
Image files need TypeSafe-Danger-Zone-Images: true. jev-1.13.0 and jev-1.14.0 both accept them. TypeSafe calls the path dreamer-ready.
Read the articleJev Box: a bounding-box question type on jev-1.14.0
Box returns four edges as fractions of the image, plus confidence. It needs jev-1.14.0, an image, and the images header. A missing target still returns a box.
Read the articleJev 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.
Read the articleQuestions about Jev Day 2026
What was Jev Day 2026?
On 14 October 2026 TypeSafe held a Discord town hall at 1:14 PM with Diogo Almeida and Allie, then published Jev 1.14.0 as jev-preview, with image input, a Box type, and 262k context behind danger-zone headers.
Which model does jev-latest call after Jev Day?
The models page, accessed 26 October 2026, points both jev-latest and jev-preview at jev-1.14.0. The Jev Day blog said that cutover would happen a week after 14 October. jev-1.13.0 stays available as a versioned id.
Are images on for every Jev request now?
Images stay off until the request sends TypeSafe-Danger-Zone-Images: true. Jev 1.13 and Jev 1.14 both accept images once that header is set. Box questions also need jev-1.14.0 or jev-preview.
Is 262k the new default context length?
Default context stays 64k per request and 32k per question on both versions. TypeSafe-Danger-Zone-Long-Context: true raises both limits to 262k. The models page says that path is slower and less accurate than the default limits.
Sources and reading notes
The summaries below are paraphrases. Each link opens the original source, including its surrounding context.
Diogo Almeida (@CompleteSkeptic)
Published:
Source checked:
[147] Almeida’s JevDay thread: danger-zone opt-in
Almeida opened a JevDay thread by separating early adopters from production infrastructure. He writes that the first Jev release favored stable infrastructure, and that this release is for tinkerers, with a gate so people can opt into the danger zone.
Opening post of the 14 October 2026 announcement thread. Product details sit in later posts in the same thread and in the TypeSafe blog.
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:
[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.
Erik Gafni (@EGafni)
Published:
Source checked:
[157] Gafni posts the Jev 1.14 blog with a Danger Zone line
TypeSafe CTO Erik Gafni linked the Jev 1.14 blog and named image inputs, a new output type, and longer context, with the line “Highway to... the Danger Zone.”
Posted two minutes after Almeida’s thread. The post is a pointer to the blog. It adds no extra measurements.
Diogo Almeida (@CompleteSkeptic)
Published:
Source checked:
[151] Almeida: an opt-in to help find jaggedness
Almeida says TypeSafe added an opt-in flag so users can help find model jaggedness. He writes that TypeSafe still will not train on that data.
Fifth post in the JevDay thread. The post does not name the header.
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.
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:
[152] Almeida: jev-1.14.0 ships as jev-preview
Almeida lists jev-1.14.0 as jev-preview. He calls it better overall, mostly a drop-in replacement, and strongest on multilingual support. jev-1.13.0 stays available and is not deprecated.
Sixth post in the JevDay thread. The blog adds the one-week jev-latest cutover and the 60-day / 30-day deprecation warnings.
OpenRouter (@OpenRouter)
Published:
Source checked:
[158] OpenRouter says Jev 1.14 is on OpenRouter
OpenRouter posted that Jev 1.14 is on OpenRouter. The post lists small overall gains, multilingual as the largest upgrade, experimental image input, and an unchanged price of $0.042 per million input tokens with output free.
Posted 15 October 2026 at 00:16 UTC. The post does not print an OpenRouter model id. openrouter.ai/typesafe/jev-1.14 returned not found on 15 October 2026.
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.
TypeSafe AI
Source checked:
[156] Box: four edges as fractions of the image
A Box question returns top, bottom, left, and right as fractions from 0 to 1, measured from the top-left of the image, plus a confidence value. Box needs an image in the request, the images header, and jev-preview or jev-1.14.0. The type takes no criteria. A Box answer is always a box, so the page pairs it with a Noul that asks whether the target is present. On 36 test crops of paintings with a known cut, four edge questions caught 30 of the cuts, a single all-inside question caught 26, and an outline on the full image caught 20.
Official Box documentation as accessed 15 October 2026. The 36-crop check is TypeSafe’s. There is no recommended confidence threshold; the 0.6 figure in the padding example is labelled as an example to tune.