返回全部动态

Cloudflare 推出 System One 提取模型 Clairic

原标题:Introducing Clairic, a new System One class of extraction models

Cloudflare AI Blog一手来源模型发布质量 70

AI 摘要

Cloudflare 发布 System One 类提取模型 Clairic 预览版,托管于 Workers AI(@cf/cloudflare/clairic),并计划近期开源权重。该模型可从非结构化输入中提取、计算、估计和预测数值,相比传统 LLM 准确率更高、延迟更低、成本更省。它单次前向处理输入、不生成 token,输出带置信度的类型化值(span、数字、日期、分布等),与决策模型 Clef、Jev 及 System Two 的 LLM 形成互补。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Today, we're announcing a preview of a new class of System One-style models: extraction models. Our first one, Clairic, is available hosted on Workers AI as @cf/cloudflare/clairic.We intend to release the model open-weights soon. Clairic is an extraction model that is able to extract, compute, estimate, and forecast values from unstructured inputs — all at a significantly higher accuracy, faster latency, and cheaper cost than traditional LLMs. Context When System One models were announced by Typ


发布时间:2026-10-20 01:48
抓取时间:2026-10-20 01:59
来源机构:Cloudflare
阅读原文blog.cloudflare.com