ScaleDown 发布 Classify、Extract、Summarize 三款约束解码小模型，1M 上下文输出免费
ScaleDown 出了三个专门做分类、抽取、摘要的小模型，1M token 上下文，输出免费，$0.05 每百万 token，agent 里的杂活不用再烧大模型的钱了。
ScaleDown 发布了 Classify、Extract、Summarize 三款小模型，专供智能体里原本交给昂贵 LLM 的分类、抽取、摘要类重复任务。模型支持最长 1M token 的文本和图像输入，采用约束解码，只做一次 prefill，直接从输入中选出标签、带偏移量的片段或摘要段落，不逐 token 生成，因此输出免费。价格方面输入为 $0.05 每百万 token，官方称相比前沿 LLM API 快 200 倍、便宜 467 倍。
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.
https://t.co/AHsLsn6GBf
