Side-by-side pricing, context window, and capabilities — try both on ChatLima.
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,...
General conversations and content creation
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...
General conversations and content creation
| Feature | DeepSeek: DeepSeek V4 Pro | DeepSeek: DeepSeek V4 Flash |
|---|---|---|
| Provider | OpenRouter | OpenRouter |
| Context Length | 1,048,576 tokens | 1,048,576 tokens |
| Input Price | $0.435/M | $0.077/M |
| Output Price | $0.870/M | $0.154/M |
| Vision Support | No | No |
| Higher cost | No | No |
| Capabilities | Text | TextFast |