Trinity Mini
by Arcee AiReleased 1 December 2025
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...
Reads about 130 pages · writes up to 130 pages
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstoplogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceOther
Also accepted by this model.
max_completion_tokensQuestions about Trinity Mini
Is Trinity Mini still on sale?
No. Arcee Ai has retired it. Other Arcee Ai models are on sale.
What is Trinity Mini best for?
The lab has not said.
Does Trinity Mini work in Arabic, French or Darja?
Arcee Ai names no languages for Trinity Mini. Arabic, French and Darja: not stated.
Can it read PDFs, images or a whole book?
It reads text. Up to 131K tokens in one request, about 130 pages. It writes up to 98 000 words at once.
Is Trinity Mini open source?
Yes, its weights are public. Open weights on Hugging Face
Who makes Trinity Mini, and when was it released?
Arcee Ai. Released 1 December 2025.
