Arcee AI: Trinity Mini (free)
The free variant of Arcee AI's Trinity Mini carries no benchmark data, making capability assessment impossible. Tool use and function calling are supported, but without performance evidence this model is only suitable for low-stakes experimentation.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
Model Information
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
