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...
| Type | Model |
| Section | Models & platforms / text->text |
| Pricing | paid (от $0.09/mo) |
| Platform | Self-hosted |
| Systems | api, python, self-hosted |
| Hosting | cloud |
| Site language | en |
| Vendor | Deepseek |
| Launched | 2026-04-24 |