Mistral Devstral 2 2512 vs OpenAI GPT-4.1 Mini
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
- GPT-4.1 Mini is 1.1× cheaper at a typical mix of 3 input tokens per output token.
- GPT-4.1 Mini accepts longer prompts: 1M vs 262K tokens.
- Devstral 2 2512 is the newer model (released 2025-12-09).
| Devstral 2 2512 | GPT-4.1 Mini | |
|---|---|---|
| Vendor | Mistral | OpenAI |
| Released | 2025-12-09 | 2025-04-14 |
| Input / 1M | $0.40 | $0.40 |
| Output / 1M | $2.00 | $1.60 |
| Cached input / 1M | $0.04 | $0.10 |
| Blended / 1M (3:1) | $0.80 | $0.70 |
| Context | 262K | 1M |
| Max output | 210K | 33K |
| Accepts | text, file | text, image, file |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 3 |
| Cheapest provider, output | $2.00 | $1.60 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Devstral 2 2512
$54.00 per month$1.80 per day
GPT-4.1 Mini
$48.00 per month$1.60 per day
GPT-4.1 Mini saves $6.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Devstral 2 2512 with