We Open-Sourced a 322M Decision Model. Now Its API Is Free

Description and use

HAL‑X AI released the open‑source decision model THX‑01, running in ~10 ms and available via a free API without a key. It outperforms Jev 1.13 in accuracy and latency, supports 18 languages, and can run on a smartphone.

Problem

Developers need fast, low‑cost decision‑making models for tasks like spam detection, ticket routing, and numeric extraction, but large LLMs add unnecessary latency and cost.

Outcome

THX‑01 outperforms Jev 1.13 with 98.4 % accuracy, 0.003 calibration error, and ~10 ms latency, while being 33× faster and fully open‑source.

Workflow

• 1. Send a JSON request with state and questions to https://api.hal-x.ai/v1/systemone
• 2. THX‑01 processes the input and returns structured answers with calibrated probabilities
• 3. Consume the API response in your application or pipeline

Evidence

We benchmarked THX‑01 against TypeSafe Jev 1.13 using 2,843 multilingual support tickets across four languages.

Source

Accuracy 98.4% vs 97.4%

Source

Measured latency ~10 ms vs 331 ms

Source

No API key, no sign‑up, and no payment required.

Source