Microsoft Phi 4 vs Mistral Ministral 3 8B 2512
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
- Phi 4 is 1.7× cheaper at a typical mix of 3 input tokens per output token.
- Ministral 3 8B 2512 accepts longer prompts: 262K vs 16K tokens.
- Ministral 3 8B 2512 is the newer model (released 2025-12-02).
| Phi 4 | Ministral 3 8B 2512 | |
|---|---|---|
| Vendor | Microsoft | Mistral |
| Released | 2025-01-10 | 2025-12-02 |
| Input / 1M | $0.07 | $0.15 |
| Output / 1M | $0.14 | $0.15 |
| Cached input / 1M | — | $0.015 |
| Blended / 1M (3:1) | $0.088 | $0.15 |
| Context | 16K | 262K |
| Max output | 15K | 210K |
| Accepts | text | text, image |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 3 |
| Cheapest provider, output | $0.14 | $0.15 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | Operational |
Cost calculator
Phi 4
$6.30 per month$0.21 per day
Ministral 3 8B 2512
$11.25 per month$0.38 per day
Phi 4 saves $4.95 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Phi 4 with