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 (free)
Total usage per day on OpenRouter
Prompt
753M
Reasoning
62M
Completion
16M
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.