Minimax M2 vs Codestral Latest: cost comparison
Prices updated 2026-11-06 · computed from live provider data
Short answer: Codestral Latest is cheaper on a
3:1 input/output blend — $0.450 per million tokens versus
$0.525, a 14% difference.
Minimax M2 offers the larger context window at 200,000 tokens, against 128,000 for Codestral Latest.
Head to head
| Minimax M2 | Codestral Latest | |
|---|---|---|
| Input, per 1M tokens | $0.300 | $0.300 |
| Output, per 1M tokens | $1.20 | $0.900 |
| Blended 3:1, per 1M | $0.525 | $0.450 |
| Context window | 200,000 | 128,000 |
| Vendor | minimax | mistral |
Monthly cost at real volumes
| Workload (input / output) | Minimax M2 | Codestral Latest |
|---|---|---|
| 1M in / 250K out | $0.600 | $0.525 |
| 10M in / 2.5M out | $6.00 | $5.25 |
| 100M in / 25M out | $60.00 | $52.50 |
Which should you pick?
Pick Minimax M2 when you need the longer context window (200,000 vs 128,000 tokens). Pick Codestral Latest when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.