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.
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | Microsoft Phi-4 Mini | Qwen3.5 397B A17b Fp8 |
|---|---|---|
| Provider | microsoft | qwen |
| Input price / 1M tokens | Free | Free |
| Output price / 1M tokens | — | — |
| Context window | 128k tokens | 262k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | Yes | No |
Microsoft Phi-4 Mini is a 3.8B parameter compact model from Microsoft. Delivers impressive reasoning capabilities for edge and mobile deployment scenarios, with strong performance on math and coding tasks relative to its size.
Qwen3.5 397B A17b Fp8 — Alibaba's Qwen series language model with strong multilingual and coding capabilities.
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.