Released Dec 1, 2025131,072 context$0/M input tokens$0/M output tokens
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
1.93B
Reasoning
122M
Completion
43.9M
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.