Sakhanda Wire
NVDA $152.58 -2.28% MSFT $506.11 -2.29% GOOGL $279.81 -1.38% META $619.07 -1.17% AMZN $256.55 -0.47%
← Back to the news

Liquid AI releases d1 decision model for calibrated probabilistic outputs

Liquid AI has released d1, a model designed for structured decisions rather than text generation. Given a state—plain text or a JSON object—and typed questions, it returns probabilities over predefined outcomes in one API request. The response contains zero generated output tokens. The hosted model is available through the Liquid API as d1:free; it is listed as API-only and not trainable, with no GGUF, MLX or ONNX weights for self-hosting.

The model offers three question types. Noul produces a probability for a yes-or-no question, Choice selects from named alternatives while returning the distribution and confidence, and Score evaluates an ordered scale with a probability-weighted result. These types can be combined in one call. Liquid positions d1 for classification, routing, moderation, scoring, reranking and LLM-as-judge checks.

According to Liquid’s migration guidance, the approach avoids billed output tokens, decoding delays and schema-format errors, while exposing probabilities that can support thresholds and human-review bands. The company recommends retaining conventional LLMs for summarization, drafting, conversation, code generation and complex multi-step reasoning. Calls use the Liquid API, with Python and TypeScript clients provided by TypeSafe AI.

Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.

Originally published by MarkTechPost on

Read the original on MarkTechPost ↗

The reporting and the image belong to MarkTechPost and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news