Microsoft Phi 4 vs Mistral Small 3
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Mistral Small 3 is 1.5× cheaper at a typical mix of 3 input tokens per output token.
- Mistral Small 3 accepts longer prompts: 33K vs 16K tokens.
| Phi 4 | Mistral Small 3 | |
|---|---|---|
| Vendor | Microsoft | Mistral |
| Released | 2025-01-10 | 2025-01-30 |
| Input / 1M | $0.07 | $0.05 |
| Output / 1M | $0.14 | $0.08 |
| Cached input / 1M | — | — |
| Blended / 1M (3:1) | $0.088 | $0.058 |
| Context | 16K | 33K |
| Max output | 15K | 16K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 1 |
| Cheapest provider, output | $0.14 | $0.08 |
| Best provider uptime, 24 h | 99.77% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | Operational |
Cost calculator
Phi 4
$6.30 per month$0.21 per day
Mistral Small 3
$4.20 per month$0.14 per day
Mistral Small 3 saves $2.10 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Phi 4 with
Compare Mistral Small 3 with