Cloudflare previews Clairic, a single-pass document extraction model
Original title: Cloudflare's Clairic pulls data from documents faster and cheaper than LLMs
Clairic is in preview on Workers AI, with open weights planned, and returns named fields plus a confidence score.
Cloudflare released Clairic, a model it says extracts structured values from documents faster and more cheaply than large language models. Users name fields such as an order number or invoice total; Clairic returns formatted values, or null if missing, in one pass rather than token by token. It can also do simple calculations, estimates, and forecasts, and is meant to sit in agent chains with other models. Cloudflare says a sample chain with Clef and GLM-5.3 took 19.3 seconds versus 61.7 seconds for GLM-5.3 alone.
Unconfirmed: Speed, cost, and reliability claims are Cloudflare's own and are not independently verified.
- Open weights are planned to follow the Workers AI preview.
- Cloudflare says the sample chain cost almost half of GLM-5.3 alone.
- Cloudflare says Clairic is not yet reliable for longer calculation chains.
- Developers are told to run those longer calculations in their own code.
- Vendors
- Cloudflare
- Products
- Workers AI
From the original article
1 min read at the-decoder.com
Cloudflare has released an AI model it says pulls data from documents faster and more cheaply than large language models. The article Cloudflare's Clairic pulls data from documents faster and cheaper than LLMs appeared first on The Decoder.
By Maximilian Schreiner · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.