Arcee-aitext->text
Arcee AI: Trinity Mini
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.
Context Window
131K
Input Price
$0.0500/M tokens
Output Price
$0.1500/M tokens
Modality
text->text
Pricing Breakdown
Cost per million tokens for input and output
Input$0.0500/M tokens
Output$0.1500/M tokens
Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.000650
Context Window Size
Maximum tokens the model can process in a single request
Context Window131K tokens
13% of 1M max
~98K
Words Equivalent
~66
Pages of Text
~1311
Code Functions
Best Use Cases
What this model excels at
MathReasoningAnalysis
Related Categories:
More from Arcee-ai
Ready to Test Arcee AI: Trinity Mini?
Use our free AI Models Tester to compare Arcee AI: Trinity Mini with other models side-by-side using your own prompts. See real results instantly.