by arcee-ai
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.
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Recency2026-03-03T20:24:48.565Z | 100 | 15% | +15.0 |
| Capabilities2026-03-03T20:24:48.565Z | 57 | 25% | +14.3 |
| Context Window2026-03-03T20:24:48.565Z | 81 | 15% | +12.2 |
| Output Capacity2026-03-03T20:24:48.565Z | 85 | 10% | +8.5 |
| Versatility2026-03-03T20:24:48.565Z | 33 | 10% | +3.3 |
| Pricing Tier2026-03-03T20:24:48.565Z | 0 | 25% | +0.0 |
Cost Estimator
You save $40.02/month vs category average