{"id":"thx-02","slug":"thx-02","name":"THX-02","orgId":"hal-x","family":"thx-02","releaseDate":null,"availability":"ga","openWeights":true,"license":"Apache-2.0","paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/HAL-X-AI/THX-02","hfRepo":null,"modalities":["text","image"],"aliases":["THX-02","thx-02","THX 02","thx02","HAL-X-AI/THX-02","HAL-X/THX-02","THX-02 decision"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-05","announced":"2026-11-05","blurb":"HAL-X's open-weight multimodal decision model: a 4.5B decision network plus a 60M think adapter that returns calibrated probabilities over options you supply (choice, noul yes/no, and score). Accepts text and up to four images; trained on requests up to 32K tokens. Successor of THX-01 (0.3B). Apache-2.0 weights on Hugging Face (HAL-X-AI/THX-02) and ModelScope (HAL-X/THX-02). Hosted API at api.hal-x.ai (free-tier per IP and keyed); pip package thx02 for the API client and local/Termux runs.","api":"live","openWeights":"yes","params":{"text":"4.5B decision model + 60M think adapter","source":"HAL-X model card (HAL-X-AI/THX-02)"},"facts":[{"label":"Role","value":"Non-autoregressive decision model: answers typed questions over a state with a probability for every supplied option; free-text only when the think adapter writes a short note"},{"label":"Question types","value":"choice (up to 255 options), noul (yes/no), score (ordered scale); up to 64 questions per request"},{"label":"Context","value":"Trained up to 32K tokens per request"},{"label":"Modalities","value":"Text plus up to 4 images per request; post-training and evaluation across more than 20 languages"},{"label":"Thinking","value":"Optional 60M think adapter with self-gate (think=false, auto, or true); auto mixes direct and thought-assisted reads"},{"label":"Checkpoints","value":"HAL-X-AI/THX-02 on Hugging Face and HAL-X/THX-02 on ModelScope (BF16; FP32 on CPU); includes thinker/ adapter for vLLM"},{"label":"API","value":"Hosted at api.hal-x.ai (model id thx-02); free tier without a key (THX-02: 60 decisions/min per IP) and keyed access; docs at api.hal-x.ai/docs/thx-02/"},{"label":"Local","value":"pip install thx02 (API client/CLI) or thx02[local]; Termux path documented on the model card"},{"label":"License","value":"Apache-2.0"},{"label":"Predecessor","value":"THX-01 (0.3B; doofz/THX-01 on Hugging Face) — not a tracked page on isitsota"}],"claims":["Lab claim: on a 6,018-request sample of the Decision Index 0.3 public suite, THX-02 scores 65.06 with think=auto and 63.83 direct (lab-measured on one RTX PRO 6000).","Lab claim: 72.19 on the Decision Vision Index 0.3 public sets run so far (10 of 11; Winoground gated; no thinking).","Lab claim: median latency 50 ms direct and 79 ms with self-gated thinking on one RTX PRO 6000; 129 requests per second on one RTX 4090 (lab-measured)."],"sources":[{"kind":"repo","title":"HAL-X-AI/THX-02 model card (Hugging Face)","url":"https://huggingface.co/HAL-X-AI/THX-02"},{"kind":"repo","title":"HAL-X/THX-02 on ModelScope","url":"https://modelscope.ai/models/HAL-X/THX-02"},{"kind":"lab","title":"THX-02 API reference (HAL-X)","url":"https://api.hal-x.ai/docs/thx-02/","date":"2026-11-05"},{"kind":"lab","title":"HAL-X announcement on X","url":"https://x.com/halx_ai/status/2118377213842379072","date":"2026-11-05"},{"kind":"press","title":"ModelScope announcement on X (host)","url":"https://x.com/ModelScope2022/status/2118372777107599433","date":"2026-11-05"}],"firstBenchmark":null},"organization":{"id":"hal-x","name":"HAL-X","slug":"hal-x","country":null,"url":"https://api.hal-x.ai","color":"#11110F","mark":"H"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 5, 2026; no independent results yet.","lead":"As of Nov 22, 2026, THX-02 is pending benchmarks on isitsota: announced Nov 5, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}