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.
💰Amazon Nova Lite is 98% cheaper than Magnum v4 72B
⚡Amazon Nova Lite is 18ms faster than Magnum v4 72B
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Amazon Nova Lite is 4900% cheaper
| Spec | Amazon Nova Lite | Magnum v4 72B |
|---|---|---|
| Provider | amazon | anthracite-org |
| Input price / 1M tokens | $0.06 | $3.00 |
| Output price / 1M tokens | $0.24 | $5.00 |
| Context window | 300k tokens | 33k tokens |
| Latency (p50) | — | 18ms |
| 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.
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
Want to swap in a different model or estimate monthly costs?