Liquid AI has introduced d1, a decision model built for structured choice tasks rather than open-ended text generation. According to the announcement cited by Techub News, users provide context and a set of typed questions, and the model returns calibrated probabilities for a fixed set of outcomes in a single call. It does not generate any output tokens.
The company said d1 is aimed at use cases such as classification, ticket routing, scoring, review, reranking, and checks where an LLM is used as a judge. The model is already available as a hosted API on Liquid API under the name d1:free.
Liquid’s model library indicates that d1 is API-only and does not support training. That means there are no self-hosted GGUF, MLX, or ONNX weights available for the model. Liquid AI’s migration guide also offers a simple rule for choosing between model types: use a decision model when the answer is one of N known options, and keep an existing LLM when the model needs to compose a new string.
Liquid AI has released d1, a decision model designed for structured choice tasks, according to Techub News, which cited MarkTechPost. Users provide context and a set of typed questions, and the model returns calibrated probabilities for a fixed set of outcomes in a single call. It does not generate any output tokens.
Liquid said the target use cases for d1 include classification, ticket routing, scoring, review, reranking, and checks in which an LLM serves as a judge.
d1 is live as a hosted API
The model is now available as a hosted API on Liquid API under the model name d1:free.
Based on information in Liquid’s model library, d1 is offered only through an API interface and does not support training. As a result, there are no GGUF, MLX, or ONNX weights available for self-hosting.
Migration guide sets a simple rule
Liquid AI’s migration guide gives a straightforward rule: if the answer is one of N known options, use a decision model. If the model needs to compose a new string, keep the existing LLM.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
