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
Input Price
$0.045per 1M
Output Price
$0.15per 1M
Context
131K
Weekly Tokens
670M
Released
Dec 1, 2025