Cloudflare's Clairic extracts document data faster and cheaper than LLMs, company says
Cloudflare's Clairic pulls data from documents faster and cheaper than LLMs
- Who
- Cloudflare
- What
- released in preview Clairic, an AI model for extracting data from documents
- Quote
Cloudflare has released an AI model it says pulls data from documents faster and more cheaply than large language models.
What happened
Cloudflare released Clairic in preview on Workers AI, with open weights set to follow soon, saying it extracts document data faster and more cheaply than LLMs. It returns requested fields and confidence scores in a single pass, using null for missing values. Cloudflare reports that a customer complaint workflow combining Clairic, Clef, and GLM-5.3 takes 19.3 seconds versus 61.7 seconds for GLM-5.3 alone at almost twice the cost, but says Clairic cannot yet reliably handle longer calculation chains.
The story so far
Cloudflare released Clairic, a model for extracting data from documents, in preview on Workers AI and said open weights would follow soon. The company says Clairic extracts data faster and more cheaply than large language models. It returns requested fields and confidence scores in a single pass, using null for missing values. Cloudflare reported that a customer complaint workflow combining Clairic, Clef, and GLM-5.3 took 19.3 seconds, compared with 61.7 seconds for GLM-5.3 alone, which cost almost twice as much. That comparison covers the combined workflow. Cloudflare also said Clairic cannot yet reliably handle longer chains of calculations.
Keep reading
Latest daily · Issue 27TorchNeuron brings native PyTorch support for Hugging Face models on AWS TrainiumTrending now
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-20
