Cloudflare Unveils Clairic, a Fast, Low‑Cost AI for Structured Data Extraction
Current overview (not historical)
Cloudflare has announced Clairic, an AI model designed to pull structured data from documents more quickly and cheaply than large language models (LLMs). The model is available in the Workers AI preview, where users specify the fields they want—such as order numbers or invoice totals—and Clairic returns the matched values along with confidence scores in a single pass, without generating text token‑by‑token. Cloudflare plans to release the model’s weights later, but for now it is offered as a proprietary service. Clairic’s approach focuses on efficiency: it bypasses the token‑generation overhead typical of LLMs, aiming to reduce latency and cost for document‑processing tasks. While the company claims superior speed and affordability, independent evaluations and broader adoption will determine how it stacks up against existing extraction solutions.
Written with AI from the reporting · updated 10/20/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 20, 00:00recorded Oct 20, 20:38single sourcerevised
Cloudflare发布Clairic AI模型
Read original source ↗ The DecoderReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- cloudflare
- Action：
- 发布Clairic模型
- Object：
- 从文档中提取数据
- Occurred (fact side)：
- Oct 20, 00:00
- Published (valid side)：
- Oct 20, 20:04
- First seen (known side)：
- Oct 20, 20:38
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- The DecoderRelated fact: single sourceSource report revisedCloudflare releases Clairic AI model for faster, cheaper document data extraction
Report first recorded Oct 20, 20:38
Cloudflare has released Clairic, an AI model available in preview on Workers AI that extracts specific data fields from documents faster and more cheaply than large language models. Unlike LLMs, Clairic returns all requested values in a single pass with confidence scores, returning 'null' for missing data. It also handles simple calculations and estimates, and is designed to work alongside LLMs in agent chains to automate tasks like processing complaint emails.
Read original source ↗
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.