Skip to content

Clef-omni

News that Cloudflare's Clef-omni decision model takes text, images, audio and video in one request, with a Clef-flash price cut.

Articlediscussion

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

A RuntimeWire article reporting that Cloudflare's decision model line gained Clef-omni, which takes text, images, audio and video in one request, and that the cheaper Clef-flash tier had its price cut at the same time.

The listing frames it as a competitor update relative to Jev, which accepts text only.

What the decision model decides

TypeQuestionAnswers
OtherTyped decisions over multimodal state (covered by the article)(inferred)—

How it works

  1. Client sends text, image, audio or video state
  2. Adds typed questions to the same request
  3. Clef-omni returns typed probabilities

Strengths

  • Adds audio and video input to decision models

Caveats

  • News coverage only
  • Only list summary available

At a glance

Type
Article
Status
discussion
Has code
no
Has tests
no

Use cases and integrations

How curated lists describe it

  • Competitor update: Cloudflare's decision model now takes text, images, audio and video in one request, and the cheaper Clef-flash tier had its price cut at the same time.

    yibie/awesome-jev

Frequently asked questions

What is new in Clef-omni?

It accepts text, images, audio and video in one request.

What changed for Clef-flash?

Its price was cut, per the article.

Where is it?

https://runtimewire.com/article/cloudflare-clef-omni-multimodal-decision-model

Related projects

  • openvons (open-Jev): finite-choice decision layer for text, images and Japanese voice, with a none option and execute/confirm/reject.

    ProjectresearchPython
  • RoboKrunch's curated Jev resource list with official links, news and its own measured experiments marked separately.

    Projectproduction
  • Long-form analysis of what Jev is, why it is fast, how much of the hype holds up, and how hard it is to reproduce.

    Projectdiscussion
  • Japanese research deck, article and source ledger tracking TypeSafe's Jev and System One models over time.

    ProjectdiscussionMarkdown
  • Unofficial Jev information hub site with access guide, pricing comparison, a BYOK playground and an auto-updated news timeline.

    AppproductionPython
  • Chinese-run aggregator of X long posts and demo videos about Jev, keeping original links and authors rather than rehosting.

    Serviceproduction