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.
Recent activity on Trinity Mini
Total usage per day on OpenRouter
Reasoning
5.88M
Prompt
2.69M
Completion
-43,900
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.