OpenJev
Shares rank 3 of 6 decision models by recommenders
Fast, cheap structured-output model that cannot emit tokens outside a given set. Critics doubt it differs from other small LLMs, and the naming is confusing.
Fast, cheap structured-output model that cannot emit tokens outside a given set. Critics doubt it differs from other small LLMs, and the naming is confusing.
47 people gave an opinion
- recommend it
- 21
- criticize it
- 26
- approval share
- 45%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 21 people recommend itNeeds 10 or more, met.
- 0.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Fast, inexpensive answers
“the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens”
Comment from 18 Sep 2026 in “OpenJev” “Because Jev answers so quickly and inexpensively, it's a likely replacement for complex, best-effort functions”
Comment from 19 Sep 2026 in “OpenJev” “What’s novel is how fast and cheap Jev is while maintaining quality.”
Comment from 18 Sep 2026 in “OpenJev” - Comment from 18 Sep 2026 in “OpenJev”
Very low cost per answer
“In Jev output tokens are straight up free because it's not doing text token generations.”
Comment from 19 Sep 2026 in “OpenJev” “their demos are pretty good, their prices are extremely low compared to alternatives”
Comment from 18 Sep 2026 in “OpenJev” “Anything you can do in Jev can be done with an LLM at much greater cost and latency.”
Comment from 18 Sep 2026 in “OpenJev” - Comment from 18 Sep 2026 in “OpenJev”
Output limited to allowed tokens
“the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens”
Comment from 18 Sep 2026 in “OpenJev” “This is a great evolution in the right direction compared to LLM + pydantic and temperature 0.”
Comment from 19 Sep 2026 in “OpenJev” “it's faster, cheaper, smart structured output.”
Comment from 18 Sep 2026 in “OpenJev” Clear site with no clutter
“Clear and to the point. Not even a cookie popup”
Comment from 18 Sep 2026 in “OpenJev” “This site is several levels above that.”
Comment from 18 Sep 2026 in “OpenJev”
What people warn about
Each mark is one comment
Confusing Jev naming and copies
“I think the "Jev" naming is confusing (and it could be legally dangerous).”
Comment from 18 Sep 2026 in “OpenJev” “These jev-copy projects are all vibecoded, and only mimic the shape of output.”
Comment from 18 Sep 2026 in “OpenJev” “This has no relation to Jev, other than that it makes fun of Jev”
Comment from 18 Sep 2026 in “OpenJev” - Comment from 18 Sep 2026 in “OpenJev”
Unclear difference from other LLMs
“I am not really convinced on how it's different than any other llm that execute small context within 100ms.”
Comment from 18 Sep 2026 in “OpenJev” “So I don't see the advantage to their approach until you're up beyond 6 or 7 questions?”
Comment from 18 Sep 2026 in “OpenJev” “it's an AI generated webpage that uses small LLM models to produce structured output”
Comment from 18 Sep 2026 in “OpenJev” - Comment from 18 Sep 2026 in “OpenJev”
Wrong answers in some tests
“It picked always the third with an 80% confidence, while the answer should have been 1.”
Comment from 18 Sep 2026 in “OpenJev” “Weird, I tried it and Jev gave me 16-18% for each face of the die.”
Comment from 18 Sep 2026 in “OpenJev” “it scored "Foo" at 98% percent. Why not 0% for both?”
Comment from 18 Sep 2026 in “OpenJev” Slow or broken in some browsers
“Works in Firefox for me, but much much slower than Chrome.”
Comment from 19 Sep 2026 in “OpenJev” “Doesn't work for me on iPad Pro: Loading… or it is just incredible slow”
Comment from 18 Sep 2026 in “OpenJev”
Other decision models people recommend
The four most recommended other decision models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Jev by Typesafe AI | 392 | 170 | 70% | 2 | — | — |
| Laya | 44 | 26 | 63% | 2 | — | — |
| OpenJevThis page | 21 | 26 | 45% | 1 | — | — |
| Cloudflare Clef | 21 | 13 | 62% | 2 | — | — |
| Typesafe AI | 16 | 13 | 55% | 2 | — | — |
What people said
40 of the 51 comments that mention it, newest first. Each links to the original comment.
“see these links for better/more complete open implementations of Jev”
“In Jev output tokens are straight up free because it's not doing text token generations.”
“you come up with crap that goes the opposite direction”
“the most interesting to me so far is razorback16/openjev using DiffusionGemma”
“Works in Firefox for me, but much much slower than Chrome.”
“This is a great evolution in the right direction compared to LLM + pydantic and temperature 0.”
“Because Jev answers so quickly and inexpensively, it's a likely replacement for complex, best-effort functions”
“There is an "Unsloppify site" button which makes it a bit better.”
“So I don't see the advantage to their approach until you're up beyond 6 or 7 questions?”
“messes with the layout enough that you can't actually toggle it without scrolling”
“limited to specific types of use cases”
“the unsloppified version looks exactly as vibe coded as the regular one”
“Nasty little site, between that and pretending LLMs are the same as Jev.”
“I am not really convinced on how it's different than any other llm that execute small context within 100ms.”
“the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens”
“it's an AI generated webpage that uses small LLM models to produce structured output”
“This isn't the same thing, and just riding on its name”
“I'm using it and find their claims credible but they deserve broader scrutiny.”
“It's working, providing results and not ugly code.”
“This has no relation to Jev, other than that it makes fun of Jev”
“Weird, I tried it and Jev gave me 16-18% for each face of the die.”
“a bit of a hack (a good one though)”
“ran a test involving ~250M tokens, something we measure went from ~60% to >80% success (with almost no tuning)”
“there’s an “un-slop site” button that does absolutely nothing to un-sloppify the site”
“Anything you can do in Jev can be done with an LLM at much greater cost and latency.”
“Doesn't work for me on iPad Pro: Loading… or it is just incredible slow”
“What’s novel is how fast and cheap Jev is while maintaining quality.”
“These jev-copy projects are all vibecoded, and only mimic the shape of output.”
“their demos are pretty good, their prices are extremely low compared to alternatives”
“I think the "Jev" naming is confusing (and it could be legally dangerous).”
“OpenJev then classifies it as 100% legitimate.”
“This site is several levels above that.”
“it's faster, cheaper, smart structured output.”
“It's overly automated and repetitive in its styling.”
“Clear and to the point. Not even a cookie popup”
“I don't understand how this is different from oai "structured output"”
“It picked always the third with an 80% confidence, while the answer should have been 1.”
“it scored "Foo" at 98% percent. Why not 0% for both?”
“I think that's not proper to have Jev on the name”
“there will be so many usecases, applications and even new jobs out of this”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.