# OpenJev 21 Hacker News commenters recommended OpenJev and 26 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months. **Verdict:** 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. ## Why people recommend it - Fast, inexpensive answers (4 comments): "the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens" ([source](https://news.ycombinator.com/item?id=49754851)) "Because Jev answers so quickly and inexpensively, it's a likely replacement for complex, best-effort functions" ([source](https://news.ycombinator.com/item?id=49763193)) "What’s novel is how fast and cheap Jev is while maintaining quality." ([source](https://news.ycombinator.com/item?id=49753156)) - Very low cost per answer (4 comments): "In Jev output tokens are straight up free because it's not doing text token generations." ([source](https://news.ycombinator.com/item?id=49770972)) "their demos are pretty good, their prices are extremely low compared to alternatives" ([source](https://news.ycombinator.com/item?id=49752989)) "Anything you can do in Jev can be done with an LLM at much greater cost and latency." ([source](https://news.ycombinator.com/item?id=49753354)) - Output limited to allowed tokens (3 comments): "the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens" ([source](https://news.ycombinator.com/item?id=49754851)) "This is a great evolution in the right direction compared to LLM + pydantic and temperature 0." ([source](https://news.ycombinator.com/item?id=49763829)) "it's faster, cheaper, smart structured output." ([source](https://news.ycombinator.com/item?id=49752533)) - Clear site with no clutter (2 comments): "Clear and to the point. Not even a cookie popup" ([source](https://news.ycombinator.com/item?id=49752471)) "This site is several levels above that." ([source](https://news.ycombinator.com/item?id=49752640)) ## What people warn about - Confusing Jev naming and copies (4 comments): "I think the "Jev" naming is confusing (and it could be legally dangerous)." ([source](https://news.ycombinator.com/item?id=49752860)) "These jev-copy projects are all vibecoded, and only mimic the shape of output." ([source](https://news.ycombinator.com/item?id=49753019)) "This has no relation to Jev, other than that it makes fun of Jev" ([source](https://news.ycombinator.com/item?id=49753806)) - Unclear difference from other LLMs (4 comments): "I am not really convinced on how it's different than any other llm that execute small context within 100ms." ([source](https://news.ycombinator.com/item?id=49755073)) "So I don't see the advantage to their approach until you're up beyond 6 or 7 questions?" ([source](https://news.ycombinator.com/item?id=49758328)) "it's an AI generated webpage that uses small LLM models to produce structured output" ([source](https://news.ycombinator.com/item?id=49754786)) - Wrong answers in some tests (3 comments): "It picked always the third with an 80% confidence, while the answer should have been 1." ([source](https://news.ycombinator.com/item?id=49752414)) "Weird, I tried it and Jev gave me 16-18% for each face of the die." ([source](https://news.ycombinator.com/item?id=49753642)) "it scored "Foo" at 98% percent. Why not 0% for both?" ([source](https://news.ycombinator.com/item?id=49752346)) - Slow or broken in some browsers (2 comments): "Works in Firefox for me, but much much slower than Chrome." ([source](https://news.ycombinator.com/item?id=49766027)) "Doesn't work for me on iPad Pro: Loading… or it is just incredible slow" ([source](https://news.ycombinator.com/item?id=49753181)) ## Alternatives hackers recommend - [Jev by Typesafe AI](https://hackerapproved.com/p/jev.md): 392 recommend - [Laya](https://hackerapproved.com/p/laya.md): 44 recommend - [Cloudflare Clef](https://hackerapproved.com/p/clef.md): 21 recommend - [Typesafe AI](https://hackerapproved.com/p/typesafe-ai.md): 16 recommend - [Strands Decider 2B](https://hackerapproved.com/p/strands-decider-2b.md): 7 recommend ## Cite as Hacker Approved, "OpenJev", https://hackerapproved.com/p/openjev/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).