MiniMax-M2.5 vs DeepSeek-V4-Flash-0731
Specs, VRAM requirements and download trends — updated 10 November 2026.
deepseek-ai · B · Open weights
Params
304.2 B
Context
1,048,576
30d
2.7 M
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MiniMax-M2.5 | DeepSeek-V4-Flash-0731 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 228.7 B | 304.2 B |
| Architecture | MiniMaxM2ForCausalLM | DeepseekV4ForCausalLM |
| Context length | 196,608 | 1,048,576 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 1,202,828 | 2,697,621 |
| Downloads all time | 6.7 M | 13.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-12 | 2026-07-31 |
| API input price / 1M tokens | $0.30 | $0.043 |
| API output price / 1M tokens | $1.20 | $0.30 |
| Est. cost per 1M input + 1M output tokens | $1.50 | $0.34 |
| Cached input / 1M tokens | $0.06 | $0.035 |
| AA Intelligence Index | — | — |
| AA Coding Index | — | 69.1 |
| AA Agentic Index | — | 41 |
| Max output tokens | 58,982 | 943,718 |
| API providers | 5 | 24 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiniMax-M2.5
$1.50
DeepSeek-V4-Flash-0731
$0.34
DeepSeek-V4-Flash-0731 is 4.4× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.7 M272 K
MiniMax-M2.5
DeepSeek-V4-Flash-0731
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
MiniMax-M2.5 · fp16 @ 192K ctx
1,076.9 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB