DeepSeek-V3.2 vs Nex-N2.5-Pro
Specs, VRAM requirements and download trends — updated 25 October 2026.
deepseek-ai · A · Open weights
Params
685.4 B
Context
163,840
30d
5.6 M
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V3.2 | Nex-N2.5-Pro |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 685.4 B | 396.8 B |
| Architecture | DeepseekV32ForCausalLM | Qwen3_5MoeForConditionalGeneration |
| Context length | 163,840 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 5,571,243 | 1,880 |
| Downloads all time | 30.7 M | 34 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-12-01 | 2026-09-08 |
| API input price / 1M tokens | $0.28 | $0.075 |
| API output price / 1M tokens | $0.42 | $0.25 |
| Est. cost per 1M input + 1M output tokens | $0.70 | $0.33 |
| Cached input / 1M tokens | $0.028 | $0.015 |
| AA Intelligence Index | 21.5 | — |
| AA Coding Index | 44.2 | — |
| AA Agentic Index | — | — |
| Max output tokens | 65,536 | 235,929 |
| API providers | 11 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V3.2
$0.70
Nex-N2.5-Pro
$0.33
Nex-N2.5-Pro is 2.2× cheaper at list price.
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
5.6 M2 K
DeepSeek-V3.2
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-V3.2 · fp16 @ 160K ctx
2,815.1 GB / 24 GB