OpenRouter (@OpenRouter) · 10/13/2026, 20:49:00
Scaledown Team Launches Constrained Decoding Models: Skipping Generative Loops for Fast, Task-Specific Inference
The Scaledown team has launched a family of 'Constrained Decoding Models' (CDMs) on OpenRouter, purpose-built for single tasks like summarization, extraction, and classification. By reading inputs once and skipping the traditional LLM's token-by-token generative loop, this architecture significantly reduces latency and cost while providing structured JSON outputs with confidence scores. A launch promotion offers input tokens at $0.04/M, with 50M free credits available for the first 50 hours.
SOURCE COVERAGEFull Original Report
A family of constrained-decoding models from @scaledown_team is live on OpenRouter, each one purpose-built for a single task:
• Summarize: turns long text, images, and PDFs into short, consistent summaries for context compaction and transcript digests • Extract: describe the fields you want in plain English and get clean JSON back, with confidence scores and source spans • Classify-1: set your own labels and get a calibrated probability for each, via our Decisions API
20% off for launch: $0.04/M input tokens, output free.
↳ 引用 @neal_k_patel (Neal 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 👀
