DeepSeek-V4-Flash vs DeepSeek-V4-Flash-0731
Specs, VRAM requirements and download trends — updated 10 November 2026.
deepseek-ai · A · Open weights
Params
158.1 B
Context
1,048,576
30d
1.2 M
mit · commercial OK
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 | DeepSeek-V4-Flash | DeepSeek-V4-Flash-0731 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 158.1 B | 304.2 B |
| Architecture | DeepseekV4ForCausalLM | DeepseekV4ForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 1,151,336 | 2,697,621 |
| Downloads all time | 13.7 M | 13.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-22 | 2026-07-31 |
| API input price / 1M tokens | $0.091 | $0.043 |
| API output price / 1M tokens | $0.18 | $0.30 |
| Est. cost per 1M input + 1M output tokens | $0.27 | $0.34 |
| Cached input / 1M tokens | $0.018 | $0.035 |
| AA Intelligence Index | — | — |
| AA Coding Index | 56.2 | 69.1 |
| AA Agentic Index | 22.2 | 41 |
| Max output tokens | 943,717 | 943,718 |
| API providers | 13 | 24 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash
$0.27
DeepSeek-V4-Flash-0731
$0.34
DeepSeek-V4-Flash is 1.3× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.7 M799 K
DeepSeek-V4-Flash
DeepSeek-V4-Flash-0731
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash · fp16 @ 1024K ctx
3,211.0 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB