ScaleDown 发布 3 个小模型：分类、抽取、摘要比前沿 LLM API 便宜 467 倍

AI 导读

ScaleDown 发布 3 个小模型（Classify、Extract、Summarize），用于处理 Agent 通常交给昂贵 LLM 的简单重复任务，宣称比前沿 LLM API 快 200 倍、便宜 467 倍，输入价格为 $0.05 per million input tokens，输出免费。

正文 · 原文

Pulling a due date out of a 300-page PDF shouldn’t need a model that writes.

Decision models now get a 1M-token window, and they take images too.

ScaleDown released 3 small models (Classify, Extract, Summarize) for the simple, repetitive jobs that agents usually hand to an expensive LLM.

200x faster and 467x cheaper than frontier LLM APIs. $0.05 per million input tokens, and output is free.

The bigger change is that the same design now covers classify, extract and summarize.

The difference with regular LLMs is that these models don’t write their answer token by token. They read up to 1M tokens of text and images once and pick the answer straight from the input, so output is free, results stay inside your labels or source text

ScaleDown’s Constrained Decoding Models make one prefill pass over your input and select the answer from it: a label, a span with its source offset, or the passages that belong in a summary.