新模型专攻文档引用问答，输入价格低至 $0.01/百万 token
做合同、发票、邮件问答的工具党可以留意：答案直接附上源文档原句，出处可追溯，比传统 RAG 自己拼引用省事。输入 $0.01/百万 token、输出免费，批量跑文档成本几乎可以忽略，想搭文档问答流水线的朋友值得试一下。
一款新模型针对文档问答场景训练：回答问题时直接返回源文档中支持答案的原文段落，而不是只给结论。这意味着合同、发票、邮件等文档的处理结果天然带有出处，方便人工核对和合规审计。
定价方面，输入 token 为 $0.01/百万，输出免费，对需要大批量处理文档的团队来说成本极低。
对检索增强（RAG）类应用开发者而言，可引用原文的输出方式能减少幻觉回答的风险。
This new model is a big deal:
It was trained to return the exact passages from the source document that answer a question.
Think about applications that work with contracts, invoices, emails, or other documents. You always want to answer questions with direct traceability back to the source.
$0.01 per 1M input tokens with free output. Awesome price for processing documents at scale!
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include RAG, 文档问答, 引用溯源.
Source attribution: curated from Ate-a-Pi (@svpino).
