← ← Back to Rankings
#5 DeepSeek: DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
#5
Rank
1,280K
Context Window
$0.02
Min Input /1M
$0.32
Min Output /1M
Model Info
| Model ID | deepseek-deepseek-v4-flash-0731 |
| Modality | text->text |
| Context Window | 1,280K tokens |
| Platforms | OR |
Usage & Rankings
| Rank | #5 |
| Weekly Usage | 8.2T |
| Trend | ↑ 17% |
Input
$0.021
/ 1M tokens
Output
$0.320
/ 1M tokens
Round Trip
$0.34
/ 1M tokens
Value Rating
🟢
🟢 Economy — great for high volume
About DeepSeek: DeepSeek V4 Flash 0731
DeepSeek: DeepSeek V4 Flash 0731 is a large language model with a 1,280K token context window. It currently ranks #5 on OpenRouter by API token usage.
The best available input price is $0.021/1M tokens and output price is $0.320/1M tokens, with a round-trip cost of $0.34/1M tokens.