ScaleDown 发布 Classify、Extract、Summarize 三个约束解码模型
ScaleDown 发布 3 个 Constrained Decoding Models：Classify、Extract 和 Summarize
ScaleDown 发布 Classify、Extract、Summarize 三个小型约束解码模型，面向智能体通常交给昂贵 LLM 的简单重复任务。这些模型不逐 token 生成答案，而是一次读取最多 1M token 的文本和图像，直接从输入中选出标签、带源偏移的片段或摘要段落，因此输出免费，定价为每百万输入 token 0.05 美元。
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://x.com/neal_k_patel/status/2109978626124898587/video/1
来源：Rohan Paul · x.com