DeepSeek-V4-Flash-0731 vs Hy4-preview
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
tencent · B · Open weights
Params
780.0 B
Context
1,048,576
30d
18 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Hy4-preview |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 304.2 B | 780.0 B |
| Architecture | DeepseekV4ForCausalLM | HYV4ForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,315,560 | 18,369 |
| Downloads all time | 12.1 M | 39 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2026-08-27 |
| API input price / 1M tokens | $0.044 | $0.83 |
| API output price / 1M tokens | $0.13 | $2.50 |
| Est. cost per 1M input + 1M output tokens | $0.18 | $3.34 |
| Cached input / 1M tokens | $0.0014 | $0.042 |
| AA Intelligence Index | 34.3 | — |
| AA Coding Index | 69.1 | — |
| AA Agentic Index | 41 | — |
| Max output tokens | 131,072 | 64,000 |
| API providers | 22 | 5 |
| 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
Hy4-preview
$3.34
DeepSeek-V4-Flash-0731 is 18.8× cheaper at list price.
Download trend
Daily snapshots, last 83 days (4 Aug – 25 Oct)
4.7 M18 K
DeepSeek-V4-Flash-0731
Hy4-preview
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
Hy4-preview · fp16 @ 1024K ctx
16,691.7 GB / 24 GB