Liquid AI releases d1, a decision model with zero output tokens

Liquid AI has released d1, a decision model that returns calibrated probabilities over predefined options instead of generating text. It runs on the Liquid API as d1:free with usage.output_tokens always at 0, and no self-hosted weights are available.

• d1 returns calibrated probabilities over typed options with zero output tokens
• Three primitives: Noul (yes/no), Choice (pick from a set), Score (ordered rubric)
• Available only via Liquid API as d1:free; no GGUF, MLX or ONNX weights
• Targets routing, moderation, triage, reranking and LLM-as-judge tasks