Cloudflare 的 Clairic 以比大语言模型更快更便宜的方式从文档抽取数据
Cloudflare's Clairic pulls data from documents faster and cheaper than LLMs
The Decoder
以下为原文逐段中文翻译,保留图表与说明。AI 翻译并经 AI 对照复核,仍可能存在错误;核对数据和引用时请同时查看原文。译文发布:2026年10月20日 22:50(北京时间)。
Cloudflare 发布了一款 AI 模型,称其从文档中抽取数据的速度比大语言模型更快、成本更低。Clairic 已在 Workers AI 上以预览形式上线,开源权重也即将推出。
用户指定所需字段,例如订单号或发票总额,Clairic 便会以正确格式返回匹配的值,并附上置信度评分。与大语言模型不同,Clairic 不会逐令牌(token)生成文本。它一次性回答所有字段。若某个值缺失,该模型会返回「null」。除抽取外,它还能处理简单的计算、估算与预测。

Cloudflare 希望 Clairic 与 LLM 及其他「System One」类模型(如 Jev)在链路中协同运行。以投诉邮件为例,Clairic 抽取出订单号、金额和损坏情况,然后估算维修成本。决策模型 Clef 应用公司规则,在退款与维修之间做出选择,而 GLM-5.3 负责撰写给客户的回复。
Cloudflare 称,这一链路耗时 19.3 秒。仅靠 GLM-5.3 完成全部三步则需要 61.7 秒,成本差不多是两倍。
据 Cloudflare 表示,Clairic 目前尚不能可靠地处理更长的计算链路。眼下,开发者应将这些计算放在自己的代码中运行。
拒绝炒作的 AI 资讯——由人工精选
展开英文原文 · 与中文逐段对应
Cloudflare's Clairic pulls data from documents faster and cheaper than LLMs
Cloudflare has released an AI model it says pulls data from documents faster and more cheaply than large language models. Clairic is available in preview on Workers AI , and open weights are set to follow soon.
Users name the fields they want, like an order number or invoice total, and Clairic returns matching values in the right format along with a confidence score. Unlike language models, Clairic doesn't generate text token by token. It answers every field in a single pass. If a value is missing, the model returns "null." Beyond extraction, it can handle simple calculations, estimates, and forecasts.

Cloudflare wants Clairic to run in chains alongside LLMs and other "System One" models like Jev . With a complaint email, for example, Clairic pulls out the order number, amount, and damage, then estimates the repair cost. The decision model Clef applies company rules to choose between a refund and a repair, and GLM-5.3 writes the reply to the customer.
Cloudflare says this chain takes 19.3 seconds. GLM-5.3 on its own needs 61.7 seconds for all three steps and costs almost twice as much.
According to Cloudflare, Clairic can't yet reliably handle longer chains of calculations. For now, developers should run those in their own code.
AI News Without the Hype – Curated by Humans
查看本期独立摘要
中文独立摘要 · AI 整理
这件事
Cloudflare发布AI模型Clairic,从文档抽取结构化数据的速度比大语言模型更快、成本更低,已在Workers AI预览并即将开源权重。用户指定字段后,Clairic一次性返回匹配值与置信度评分,不逐token生成。Cloudflare称其与LLM协同的链路耗时19.3秒,仅为纯LLM方案的三分之一。
本页概括所列来源的重点,属于独立摘要;完整报道请阅读原站。整理时间:2026年10月20日 22:57(北京时间)。
信息从哪里来
据The Decoder报道,引述Cloudflare发布信息。
- The Decoder 报道正文