DeepSeek: DeepSeek V4 Pro 0423deepseek
DeepSeek: DeepSeek V4 Pro 0423: $0.48/1M input, $0.96/1M output, 1.0M context, CPS grade A. DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
API Pricing (per 1M tokens)
| Input | $0.48 |
| Output | $0.96 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.60 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 384K |
| Intelligence | 36 |
| Coding | 69 |
| Math | — |
| Speed | 84 tok/s |
| TTFT | 1.09s |
| 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 Pro 0423 API cost?
DeepSeek: DeepSeek V4 Pro 0423 costs $0.48/1M input tokens and $0.96/1M output tokens. Blended cost at a 3:1 ratio is about $0.60/1M tokens.
What is the context window of DeepSeek: DeepSeek V4 Pro 0423?
DeepSeek: DeepSeek V4 Pro 0423 supports a 1.0M token context window with up to 384K output tokens.
Is DeepSeek: DeepSeek V4 Pro 0423 worth it?
DeepSeek: DeepSeek V4 Pro 0423 has a CPS grade of A (score 69), intelligence index 36, coding index 69. Use the compare page to benchmark against rivals.