Arcee AI: Trinity Mini (free)
Review
The free tier of Arcee AI's Trinity Mini has no benchmark data available, making it impossible to assess capability; while the zero cost is attractive, businesses should verify performance before relying on it for any meaningful workload.
Assessment date: April 16, 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
Performance Profile
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..
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
How does Arcee AI: Trinity Mini (free) stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
arcee-ai/trinity-mini:free
|
| Provider | arcee-ai |
| Release Date | December 1, 2025 |
| Context Length | 131,072 tokens |
| Status | Active |
