minimax/minimax-m2.5 vs minimax/minimax-m3.1-flash
For 100,000 calls of 2,000 in and 500 out, minimax/minimax-m3.1-flash is cheaper: $60.00 a month at Together AI, against $120.00 for minimax/minimax-m2.5 at Novita AI — 2.0× the cost.
Cheapest on each
minimax/minimax-m2.5
$120.00/mo
cheapest, at Novita AI — $0.3 in, $1.2 out per million
minimax/minimax-m3.1-flash
$60.00/mo
cheapest, at Together AI — $0.15 in, $0.6 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | minimax/minimax-m2.5 | minimax/minimax-m3.1-flash |
|---|---|---|
| Context window | 205K | 1M |
| Accepts | Aa | Aa · IMG · VID |
| Sellers | 3 | 2 |
| Cheapest input rate | $0.3 / M | $0.15 / M |
| Cached input rate | $0.03 / M | $0.015 / M |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | minimax/minimax-m2.5 /mo | minimax/minimax-m3.1-flash /mo |
|---|---|---|
| OpenRouter | $120.002026-10-27 | $60.002026-10-27 |
| Novita AI | $120.002026-10-22 | ○ no answer |
| FriendliAI | $120.002026-10-21 | ○ no answer |
| Together AI | ○ no answer | $60.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.