An ultra-sparse MoE with 400B total and 13B active parameters, trained by an American company. They also released a tech report and two base models, one "true" base model pre-annealing and the base model after the pre-training phase. Many more insights, including technical details and their motivation, can be found in our interview with the founders and pre-training lead:
Relative Adoption Metric contextualizes downloads against the model's size bucket.
OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Trinity-Large-Preview fell below that cutoff — not zero usage. OpenRouter logs usage separately per dated model version and per variant (like ":free"); the hub combines provider variants while keeping separately cataloged releases distinct.
