All news

Hugging Face introduces shared decision-model interface with probabilities instead of generated text

Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .

Agents no longer need to compose text for classification and routing: an application can receive a typed decision and its probability directly, faster and in a consistent format across different models.

Hugging Face has standardized support for decision models, which evaluate permitted decisions directly rather than writing a response token by token. A request consists of context and typed questions: choice selects an option and returns a probability distribution, score calculates an expected value on an ordered scale, and noul gives the probability of a yes-or-no answer. This allows one call to route a request, assess urgency and check a condition without parsing potentially malformed JSON or paying to generate an explanation; the API example returns zero output tokens. Transformers has gained DecisionPipeline, AutoModelForDecision and DecisionConfig, while Transformers and llama.cpp support the shared /v1/systemone endpoint. The compatible interface works with purpose-trained models and with ordinary autoregressive LLMs, whose option logits are normalized without text generation. The Hub has added a dedicated tag for finding such models, and the Trainer API already supports fine-tuning them.

History

Models that answer with a choice or a probability, not text

10 events
  1. Google releases Gemini Decision 1 for fast answers to closed sets of questions
  2. Hugging Face introduces shared decision-model interface with probabilities instead of generated textOpen now
  3. Baseten released joey-1, an open 2-billion-parameter model that delivers decisions for $0.01 per million tokens
  4. OpenAI opens the Decisions API to all customers: the model quickly picks from given options, answering in 100–180 milliseconds instead of 1–3 seconds
  5. Subquadratic releases SubQ Snap, a decision model for agents that processes 100 thousand tokens in about a second
  6. Cloudflare releases open model Clef-omni that picks an answer from audio, video, images and text in one pass
  7. Microsoft releases Decision-1: a model that answers with the probability of a choice rather than text, priced at $0.042 per million input tokens
  8. Liquid AI releases open d1 models that answer without text, in a single pass
  9. OpenAI opens Decisions API: the model answers with a probability, a choice or a score instead of text
  10. Amazon and Cloudflare release open "decision models": fast SIs that choose an option rather than write text