DeepSeek-V4-Flash-0731 vs Nex-N2.5-Pro
Specs, VRAM requirements and download trends — updated 25 October 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
4.3 M
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Nex-N2.5-Pro |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 396.8 B |
| Architecture | DeepseekV4ForCausalLM | Qwen3_5MoeForConditionalGeneration |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,315,560 | 1,880 |
| Downloads all time | 12.1 M | 34 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2026-09-08 |
| API input price / 1M tokens | $0.044 | $0.075 |
| API output price / 1M tokens | $0.13 | $0.25 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $0.33 |
| Cached input / 1M tokens | $0.0014 | $0.015 |
| AA Intelligence Index | 34.3 | — |
| AA Coding Index | 69.1 | — |
| AA Agentic Index | 41 | — |
| Max output tokens | 131,072 | 235,929 |
| API providers | 22 | 1 |
| 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
Nex-N2.5-Pro
$0.33
DeepSeek-V4-Flash-0731 is 1.8× cheaper at list price.
Download trend
Daily snapshots, last 83 days (4 Aug – 25 Oct)
4.7 M2 K
DeepSeek-V4-Flash-0731
Nex-N2.5-Pro
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Nex-N2.5-Pro · fp16
507.9 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB