Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.
Modalities
Context
131K
Released
Dec 1, 2025
Token volume and request traffic to this model over time.
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.
Trinity Mini has a 131,072 token context window.
Trinity Large Thinking and Virtuoso Large are other text models from Arcee AI.
Trinity Mini was released on December 1, 2025.