{"version":1,"type":"story","url":"https://digestai.news/story/liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou","json":"https://digestai.news/story/liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou.json","markdown":"https://digestai.news/story/liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou.md","slug":"liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou","headline":"Liquid AI launches d1 decision model for structured tasks with zero output tokens","summary":"Liquid AI released **d1**, a decision model designed for structured choices like classification, ticket routing, and moderation. Unlike text-generating models, d1 returns calibrated probabilities across predefined outcomes in a single API call, with no generated tokens billed. It supports three primitives—**Noul** (yes/no with probability), **Choice** (top pick from a set), and **Score** (ordered rubric ratings)—and evaluates all questions against the same input state in one round trip.\n\nThe model is available today via Liquid’s hosted API under **d1:free**, with no self-hosting options. Liquid’s migration guide advises using d1 for tasks with fixed answer sets (e.g., spam detection, urgency triage) and reserving LLMs for generation or multi-step reasoning. A demo shows d1 powering a real-time road-decision game, outperforming a competitor model in consistency. The company highlights benefits like predictable latency, no schema errors, and reduced round trips compared to LLMs.","keyPoints":["d1 returns typed decisions with calibrated probabilities and zero output tokens, billed only for input","Supports three primitives: Noul (yes/no), Choice (top pick), and Score (ordered ratings) in one call","Deployable now via Liquid’s API as **d1:free**; no self-hosted weights or training options"],"whyItMatters":"Decision models like d1 cut costs and latency for structured tasks, replacing LLMs in classification, routing, and moderation without generation overhead. This could reduce operational costs for teams handling high-volume, rule-bound workflows.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Liquid AI","MarkTechPost","TypeSafe AI"],"models":["d1","d1:free","jev-1.13"],"people":["Asif Razzaq"]},"firstPublishedAt":"2026-09-29T21:47:09Z","updatedAt":"2026-09-29T21:47:09Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Liquid AI Releases d1: A Decision Model That Returns Calibrated Probabilities With Zero Output Tokens","url":"https://marktechpost.com/2026/09/29/liquid-ai-releases-d1-a-decision-model-that-returns-calibrated-probabilities-with-zero-output-tokens","publishedAt":"2026-09-29T21:47:09Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Liquid AI launches d1 decision model for structured tasks with zero output tokens\", 29 September 2026, https://digestai.news/story/liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou","publisher":"Digest AI","title":"Liquid AI launches d1 decision model for structured tasks with zero output tokens","datePublished":"2026-09-29T21:47:09Z","url":"https://digestai.news/story/liquid-ai-launches-d1-decision-model-for-structured-tasks-with-zero-ou"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}