Arcee AI: Trinity Mini

arcee-ai/trinity-mini

Created Dec 1, 2025131,072 context

$0.045/M input tokens$0.15/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.

Arcee AI: Trinity Mini

arcee-ai/trinity-mini

Created Dec 1, 2025131,072 context

$0.045/M input tokens$0.15/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

Total usage per day on OpenRouter

Reasoning

2.35M

Prompt

975K

Completion

514K

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.