← Back to all models

Trinity Mini

trinity-mini

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model, engineered for efficient inference over long contexts with robust function calling and multi-step agent workflows.

Available at 2 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
vercel vercel Input: $0.05 Output: $0.15 Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model, engineered for efficient inference over long contexts with robust function calling and multi-step agent workflows.
openrouter openrouter Input: $0.05 Output: $0.15 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. Context: 131072