← All models

arcee-ai

Arcee AI: Trinity Mini

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.

Try in playgroundAPI reference
131,072 context
Modalities:text->text
Released:12/1/2025

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.

Weekly tokens

353.6M

Tokens generated this week (network-wide)

Usage by period

No ranking data yet for this model.