DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
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...
Modalities
Teks
Harga in / out
₩144 / ₩287
1M
Context
1,05 jt
Dirilis
24 Apr 2026
Providers
Beberapa tempat menghosting model yang sama. Permintaan disebarkan berdasarkan prioritas dan kesehatan, dan local GPU selalu didahulukan jika tersedia.
| Provider | Context | Quantization | Max output | Priority | State |
|---|---|---|---|---|---|
| OpenRouter | 1,05 jt | — | — | 50 | unknown |