Play the video in the post belowPost on X
- Views
- 295,658
- Likes
- 3,877
- Reposts
- 98
Read from X on . Counts change daily.
Reported by the author
- Cost
- 3.5 cents
it costed 3.5 cents
x.com
A video demo shows Jev classifying 500 emails in a few seconds for a total cost of 3.5 cents.
Play the video in the post belowRead from X on . Counts change daily.
it costed 3.5 centsx.com

Cloudflare's launch post for Clef and Clef-flash, two decision models on Workers AI that accept the Jev request format and open weights under Apache 2.0. It covers the architecture, Cloudflare's own benchmark tables against Jev, Kev and Laya, and a new reinforcement learning service.
Fine-tunes Sentence Transformer embeddings plus a lightweight head for high-accuracy classification from a handful of labeled examples, with no prompting. The standard cheap alternative to an LLM classification call when the label set is fixed. Star count is GitHub's rounded display figure.

Open-weights 340M-parameter decision model from Fastino Labs. It jointly decodes typed classification questions and, per Fastino's own internal benchmark, leads 9 of 17 datasets against JevK5, SemIf and Laya.
2.2k starsCPU latency 167 msGPU latency 38-47 ms
Modernized BERT encoder used as the backbone for fast fine-tuned classifiers and rerankers. The non-generative baseline Jev's cost and latency claims are usually measured against. Star count is GitHub's rounded display figure.
PostgreSQL extension that lets you filter, rank and classify rows with plain-language conditions, such as WHERE jev(tickets, 'the customer is angry'). Adds jev_prob, jev_choice and jev_score functions that compose with joins, GROUP BY and ORDER BY, with no index or embeddings. Published on PGXN.
329 stars2k rows, cold ~3.5s, $0.0122k rows, cached ~50ms

Agent-ergonomic CLI for Jev with pick, rate, check, rank, triage and guard subcommands, meant for agents offloading snap judgments from the shell.