ScaleDown 发布 Classify、Extract、Summarize 三款小模型
ScaleDown has launched 3 small AI models for routine in-app jobs: Classify, Extract, and Summarize.
ScaleDown 推出 Classify、Extract、Summarize 三款面向应用内常规任务的小模型，均支持 100 万 token 输入、文本或图像，并可通过 ScaleDown API、OpenRouter、Vercel AI Gateway、LiteLLM 和 LangChain 调用。Classify 按用户提供的标签路由文本并给出每个标签的概率；Extract 读取文件、抽取数据并以 JSON 字段输出并附高置信度分数；Summarize 可读取长转录或报告，生成最多 1000 token 的摘要。
查看原帖You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models (CDMs) LLMs were built to write. Most production workloads just need an answer: fast, consistent, and affordable. CDMs are purpose-built for 1 task each. They read your input once and skip the token-by-token…
展开完整原文
You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models (CDMs) LLMs were built to write. Most production workloads just need an answer: fast, consistent, and affordable. CDMs are purpose-built for 1 task each. They read your input once and skip the token-by-token generative loop that makes LLMs slow and expensive. Not just a decision model, but a family of 3 CDMs live today: • Classify: define your labels and get back a calibrated probability + reason for each. Used for routing, tagging, and intent detection. • Extract: describe the entities in natural language and get back well-formed JSON with confidence scores + citations. Used for web scraping, document processing, and PII redaction. • Summarize: pass in long text, images, or PDFs and get back a consistent summary under 1,000 tokens. Used for context compaction, metadata generation, and transcript digests. Built for production: • 1M tokens of multimodal (text + image) input, 31x larger than Jev • 77.2% on DecisionBench vs Jev's 72% • 200x faster, 467x cheaper than frontier LLM APIs • $0.05/M input tokens. Output is free (yes, even for summarize) Live on your favorite platforms today: @OpenRouter @vercel_dev @LiteLLM @LangChain @TrustedRouter @itsArthurAI @useRouterPlus Get 50M input tokens for free (for the first 50 hours) at link below 👀
正文
当前显示原文，中文全文译文尚未就绪。
ScaleDown has launched 3 small AI models for routine in-app jobs: Classify, Extract, and Summarize.
All 3 models have a 1M-token input limit, support text or images, and are accessible through ScaleDown's API, as well as OpenRouter, Vercel AI Gateway, LiteLLM, and LangChain.
> Classify - routes text by assigning user-provided labels, including a probability for each label.
> Extract - can read files, collect the desired data, and output it as JSON fields with a high confidence score.
> Summarize - can read long transcripts or reports and generate a short summary of up to 1,000 tokens.