Article
CommunityJev Media & Talks
TypeSafe Opens Experimental Jev Access
Tech & Business newswire item on TypeSafe opening experimental API access to image inputs and longer context for Jev, alongside the Jev 1.14.0 release through jev-preview and a new box output type.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Tech & Business
- Last verified
- Oct 2026
Highlights
- TypeSafe opened experimental image and longer-context access alongside the release of Jev 1.14.0 through jev-preview.
- Developers enable the experimental features through API headers; image inputs can sit in state, instructions or criteria.
- A new box output type returns a single bounding box.
- TypeSafe expects the largest improvement to be multilingual support and plans to move jev-latest to 1.14.0 in a week.
- The company warns the experimental features are too unreliable for it to endorse production use.
Watch out
A short newswire item published October 14, 2026 and tiered Notable, drawn from TypeSafe's own blog post, with no independent testing and no licence or pricing details for the model. It does not quantify how much image inputs or longer context reduce reliability.
Questions about this entry
Short answers drawn from the linked project or page.
Image inputs and longer context, alongside the Jev 1.14.0 release through jev-preview. Developers enable them through API headers rather than a separate endpoint, and the company warns they are too unreliable to endorse for production.
In the model's state, instructions or criteria, per the newswire item. Access is gated behind headers that callers opt into per request, which keeps the experimental features off by default.
A single bounding box for a question about an image. It arrives with the Jev 1.14.0 release distributed through jev-preview, and the same release opens the experimental image inputs and longer context.
The largest expected improvement is multilingual support. TypeSafe also plans to move the jev-latest alias to 1.14.0 about a week after the October 14, 2026 release.
The company's own warning is that the experimental features are too unreliable for it to endorse production use, and that image inputs and longer context reduce reliability compared with text decisions at the default limits.
It cites TypeSafe's own blog post at typesafe.ai/blog/jev-1-14, so the claims are the vendor's announcement rather than an independent evaluation. It was published Wednesday, October 14, 2026 at 7:18 PM EDT.
No. It covers the experimental feature access, the box output type and the plan to move jev-latest to 1.14.0 in a week; pricing and token-limit details are not part of this item and live on TypeSafe's own pages.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: A doorbell camera on Jev 1.14
More Jev resources like this
MarkTechPost's write-up of the Jev 1.14 release: images, a box question type and 262k long context as experimental danger-zone features, unchanged $0.042 per million input token pricing, and TypeSafe's own note that none are production-ready.
Jev Media & TalksArticle#community#news#images
Community
RSS.bz's compilation of TypeSafe's launch posts for Jev 1.14, released October 14 at 1:14pm PT with experimental preview features: image support, a new box type and longer context, plus internal benchmark guesses.
Jev Media & TalksArticle#community#news#model-release
Community
A three-week timeline of the Jev clone war: the September 15 stealth launch, reported $10B valuation talks, an Amazon engineer's own build, and the $870M round, alongside OpenAI, Amazon, and Cloudflare shipping rivals.
Jev Media & TalksArticle#community#news#funding
Community
Per WSJ's search excerpt, the three-week-old Jev has set Silicon Valley abuzz with talk of alternatives to large language models and is already sparking copycats. It classifies inputs to predetermined outputs: yes or no, a numerical score, or answers on a list.
Jev Media & TalksArticle#community#press#competition
Community
SiliconANGLE reports TypeSafe closed $870M at a $7.5B valuation and explains the model's pitch: three request types, yes/no answers, picking from a list, or a score, return structured output and a confidence number instead of text.
Jev Media & TalksArticle#community#press#funding
Community
The Economic Times profiles Diogo Almeida, who left OpenAI in 2024 and spent about two years developing the idea behind TypeSafe AI. It cites WSJ on the roughly 25% Fortune 500 adoption and a $40 million DCVC raise.
Jev Media & TalksArticle#community#press#explainer
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.