DeepSeek: DeepSeek V4 Pro 0813deepseek
Bottom Line
DeepSeek: DeepSeek V4 Pro 0813: $0.66/1M input, $1.98/1M output, 1.0M context. DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
API Pricing (per 1M tokens)
| Input | $0.66 |
| Output | $1.98 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.99 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 393K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| 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 0813 API cost?
DeepSeek: DeepSeek V4 Pro 0813 costs $0.66/1M input tokens and $1.98/1M output tokens. Blended cost at a 3:1 ratio is about $0.99/1M tokens.
What is the context window of DeepSeek: DeepSeek V4 Pro 0813?
DeepSeek: DeepSeek V4 Pro 0813 supports a 1.0M token context window with up to 393K output tokens.
Is DeepSeek: DeepSeek V4 Pro 0813 worth it?
DeepSeek: DeepSeek V4 Pro 0813 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.