Liquid AI Releases d1: A Decision Model That Returns Calibrated Probabilities With Zero Output Tokens
Liquid AI's d1 does structured decisions in a single call—no token generation tax. A faster, cheaper way to route work that doesn't need text.
Why it matters
A new model class optimized for classification and decision tasks returns calibrated probabilities without token overhead. Relevant to teams running high-volume routing, triage, and choice tasks where latency and cost matter more than explanation.
The key facts
11 to knowd1 is a decision model, not a text-generation model
Returns calibrated probabilities across fixed outcome sets
Zero generated tokens (no token consumption for output)
Single API call for structured choice tasks
Target use case: work currently sent to general-purpose LLMs for classification/routing
d1 is a specialized decision model, not a general-purpose LLM
Returns calibrated probabilities across fixed outcome sets in single call
Zero generated output tokens—direct probability output only
Target use case: structured classification work currently sent to general-purpose models
Product launch from Liquid AI, a model vendor
Positioning against token-inefficient use of general LLMs for classification tasks
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Liquid AI has released d1, a decision model built for structured choices instead of text generation. You give it context and a set of typed questions. It returns calibrated probabilities across a fixed set of outcomes in a single call, with zero generated tokens. The target is the work many teams…