Arcee AI: Trinity Mini
Arcee AI's Trinity Mini has no benchmark data available, making it difficult to assess its real-world capability — it scores conservatively as a result. Tool use and function calling support are positives, and pricing is reasonable, but without evidence of performance it suits only exploratory or low-stakes use cases.
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
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000045 |
| Output | $0.15 | $0.000150 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
