DeepSeek-V4-Flash-0731 vs MiMo-V2.5-Pro
Specs, VRAM requirements and download trends — updated 24 October 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
4.3 M
mit · commercial OK
XiaomiMiMo · B · Open weights
Params
1,023.2 B
Context
1,048,576
30d
13 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | MiMo-V2.5-Pro |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 1,023.2 B |
| Architecture | DeepseekV4ForCausalLM | MiMoV2ForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 4,348,313 | 13,381 |
| Downloads all time | 11.9 M | 351 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2026-04-27 |
| API input price / 1M tokens | $0.044 | $0.30 |
| API output price / 1M tokens | $0.13 | $0.61 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $0.91 |
| Cached input / 1M tokens | $0.0014 | $0.0028 |
| AA Intelligence Index | 34.3 | 26 |
| AA Coding Index | 69.1 | 60.2 |
| AA Agentic Index | 41 | 21.3 |
| Max output tokens | 131,072 | 945,000 |
| API providers | 22 | 3 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash-0731
$0.18
MiMo-V2.5-Pro
$0.91
DeepSeek-V4-Flash-0731 is 5.1× cheaper at list price.
Download trend
Daily snapshots, last 82 days (4 Aug – 24 Oct)
4.7 M14 K
DeepSeek-V4-Flash-0731
MiMo-V2.5-Pro
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB
MiMo-V2.5-Pro · fp16 @ 1024K ctx
20,782.3 GB / 24 GB