DeepSeek: DeepSeek V4 Flash 0423deepseek
DeepSeek: DeepSeek V4 Flash 0423: $0.09/1M input, $0.18/1M output, 1.0M context, CPS grade A. 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...
API Pricing (per 1M tokens)
| Input | $0.09 |
| Output | $0.18 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.11 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 944K |
| Intelligence | 34 |
| Coding | 69 |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | A |
| Input / Output Modalities | text → text |
More from deepseek
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the DeepSeek: DeepSeek V4 Flash 0423 API cost?
DeepSeek: DeepSeek V4 Flash 0423 costs $0.09/1M input tokens and $0.18/1M output tokens. Blended cost at a 3:1 ratio is about $0.11/1M tokens.
What is the context window of DeepSeek: DeepSeek V4 Flash 0423?
DeepSeek: DeepSeek V4 Flash 0423 supports a 1.0M token context window with up to 944K output tokens.
Is DeepSeek: DeepSeek V4 Flash 0423 worth it?
DeepSeek: DeepSeek V4 Flash 0423 has a CPS grade of A (score 68), intelligence index 34, coding index 69. Use the compare page to benchmark against rivals.