ScaleDown

Headlines · 2

1. Oct 13
   ScaleDown's constrained-decoding model family launches on OpenRouter

   OpenRouter said a family of constrained-decoding models from ScaleDown is live, with each model purpose-built for a single task. Summarize turns long text, images and PDFs into short, consistent summaries for context compaction and transcript digests; Extract takes fields described in plain English and returns JSON with confidence scores and source spans; Classify-1 lets users set labels and returns a calibrated probability for each through the Decisions API. Launch pricing is 20% off at $0.04 per million input tokens with output free, and Neal Patel describes the approach as Constrained Decoding Models (CDMs); the capabilities and pricing are vendor claims from OpenRouter's post.

   OpenRouter (X) · 🔥 0
2. Oct 13
   LangChain adds ScaleDown context middleware for long-running agents

   LangChain's blog introduced the langchain-scaledown integration and said ScaleDown's constrained decoding models are now a direct model provider in the LangSmith LLM Gateway. The package ships with three middlewares for summarizing old history, compressing large tool results and extracting structured data, covering ScaleDown's four single-task models: Summarize, Compress, Extract and Classify. LangChain says each model accepts up to 1M tokens of input and that some handle images and scanned PDFs; ScaleDown's own benchmarks claim large speed and cost advantages over frontier models on narrow tasks, without independent verification in the post.

   LangChain Blog · 🔥 0

Experience and discussion from the community

Share my ScaleDown experienceAsk about ScaleDown