Hal X

THX-01 is a 322M multilingual decision model from HAL-X AI, trained with reinforcement learning on a strictly proper scoring rule so its probabilities are calibrated. Send a state and typed questions (noul / choice / score) and get an answer with probabilities for each question in one forward pass of about 10 ms — not generated chat text. Post-trained in 18 languages, 100+ supported. Apache 2.0. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).