Briefs

BriefsNewsPreview1 min read

Cloudflare puts Clairic, a new AI extraction model, in preview on Workers AI

Clairic reads text and images and returns typed values, estimates and forecasts. It runs on Workers AI as a preview, with open weights promised.

Cloudflare puts Clairic, a new AI extraction model, in preview on Workers AI — image from Cloudflare
Image: Cloudflare

Summary

Cloudflare has put Clairic, an AI extraction model, in preview on Workers AI. It takes text and up to four optional images plus a map of typed fields, and it charges only for input. Cloudflare calls the endpoint an early checkpoint and says it intends to release open weights soon.

What changed

  • Clairic runs on Workers AI as @cf/cloudflare/clairic, in preview.
  • It pulls typed values like names, dates and lists, and gives numbers with an 80% range.
  • A request is the text to read, up to four optional images, and a map of typed fields.
  • In Cloudflare's test, the cascaded pipeline took 19.3 seconds against 61.7 for the all-LLM one, and cost 49% less.
  • Cloudflare says it intends to release the model open-weights soon.

Availability

Preview

“Today, we're announcing a preview of a new class of System One-style models: extraction models.”

Founder takeaway

If an LLM currently handles your extraction work, try Clairic on a small sample and compare speed and cost. For now, let it predict the value and do the math in your own code, as Cloudflare advises.

Source

CloudflareIntroducing Clairic, a new System One class of extraction models

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS logo on a FounderHeist card

    NewsAvailable now

    Amazon Quick adds smart approvals for agentic AI actions

    Amazon Quick introduces smart approvals to automate routine agentic tasks while keeping human oversight for high-impact actions.

    AWS1 min read

  2. ElevenLabs introduces Cue forced alignment AI model — image from ElevenLabs

    NewsAvailable now

    ElevenLabs introduces Cue forced alignment AI model

    ElevenLabs releases Cue, an AI forced alignment model that places every character in an audio file on a precise timeline and powers its Scribe model family.

    ElevenLabs1 min read

  3. GitHub makes Copilot Memory generally available on paid Copilot plans — image from GitHub

    NewsAvailable now

    GitHub makes Copilot Memory generally available on paid Copilot plans

    GitHub introduces new AI intelligence capabilities including Copilot Memory, dreaming, and multi-repository code search.

    GitHub1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.