Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰Arcee AI: Trinity Mini is 25% cheaper than Amazon Nova Lite
⚡Amazon Nova Lite is 250ms faster than Arcee AI: Trinity Mini
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Arcee AI: Trinity Mini is 33% cheaper
| Spec | Amazon Nova Lite | Arcee AI: Trinity Mini |
|---|---|---|
| Provider | amazon | arcee-ai |
| Input price / 1M tokens | $0.06 | $0.04 |
| Output price / 1M tokens | $0.24 | $0.15 |
| Context window | 300k tokens | 131k tokens |
| Latency (p50) | — | 250ms |
| Best benchmark score | — | — |
| Open source | No | No |
Amazon Nova Lite is a very low-cost multimodal model that can process image, video, and text inputs. Fast and accurate for a wide range of tasks requiring visual and language understanding.
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...
Want to swap in a different model or estimate monthly costs?