ScaleDown 推出 Constrained Decoding Models 并接入 LangChain 生态
ScaleDown 发了三个不逐 token 生成的决策模型，分类、抽取、摘要各管一个，速度和价格都比通用 LLM API 好一大截，做 agent 的话可以试试接进 LangChain。
ScaleDown 发布三类受限决策模型：Classify、Extract、Summarize，跳过逐 token 生成循环，直接输出校准概率、带引用的 JSON 或 1000 token 内摘要。在 DecisionBench 上得 77.2%，高于 Jev 的 72%。官方称比前沿 LLM API 快 200 倍、便宜 467 倍，输入定价 0.05 美元/百万 token 且输出免费。现已通过 langchain-scaledown 开源包和 LangSmith LLM Gateway 接入 LangChain，并上线 OpenRouter、LiteLLM 等平台。
Excited to partner with @scaledown_team 🤝 Their constrained decision models now plug into your agents via: ✅ langchain-scaledown, an OSS package with prebuilt scaledown middlewares ✅ Support in the LangSmith LLM Gateway, with tracing, spend limits, and rate limits Neal Patel @neal_k_patel 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 👀 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 2 👀 1345 📊 1 ⚡
