DeepSeek-V4-Flash-0731 vs NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Specs, VRAM requirements and download trends — updated 10 November 2026.
deepseek-ai · A · Open weights
Params
304.2 B
Context
1,048,576
30d
2.7 M
mit · commercial OK
nvidia · B · Open weights
Params
560.5 B
Context
262,144
30d
1.1 M
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 560.5 B |
| Architecture | DeepseekV4ForCausalLM | NemotronHForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 12 |
| Downloads 30d | 2,697,621 | 1,067,799 |
| Downloads all time | 13.2 M | 2.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2026-06-03 |
| API input price / 1M tokens | $0.043 | $0.60 |
| API output price / 1M tokens | $0.30 | $2.40 |
| Est. cost per 1M input + 1M output tokens | $0.34 | $3.00 |
| Cached input / 1M tokens | $0.035 | $0.12 |
| AA Intelligence Index | — | 11.8 |
| AA Coding Index | 69.1 | 49.3 |
| AA Agentic Index | 41 | 20.1 |
| Max output tokens | 943,718 | 182,520 |
| API providers | 24 | 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
$0.34
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$3.00
DeepSeek-V4-Flash-0731 is 8.7× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.7 M213 K
DeepSeek-V4-Flash-0731
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · fp16 @ 256K ctx
3,924.2 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB