DeepSeek V4 Flash 0423
DeepSeek · Released Apr 2026
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Input / 1M
$0.14
Output / 1M
$0.28
Cached input / 1M
$0.028
Context window
1.05M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 4 Aug 2026 | $0.14 | $0.28 | $0.028 | Imported from OpenRouter | openrouter.ai |