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.
function_calling| Provider | Input | Output | Since launch |
|---|---|---|---|
| Vercel AI Gatewaycheapest | $0.43 | $0.87 | ↓75% |
| OpenRouter | $1.17 | $2.34 | ↓33% |
| Novita AI | $1.6 | $3.2 | ↓5% |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash (free) | 1.0M | 384K | |
| DeepSeek: DeepSeek V4 Flash 0423 | 1.0M | 384K | $0.06$0.12 |
| DeepSeek V4 Flash Latest | 1.0M | 384K | $0.07$0.13 |
| Nex AGI: DeepSeek V3.1 Nex N1 | 131K | 164K | $0.14$0.5 |
| DeepSeek: DeepSeek V4 Flash 0731 | 1.0M | 393K | $0.14$0.28 |
| DeepSeek: DeepSeek V3.2 | 164K | 66K | $0.27$0.4 |
| DeepSeek: DeepSeek V3.1 Terminus | 164K | 33K | $0.27$0.95 |
| DeepSeek: DeepSeek V3.2 Exp | 164K | 66K | $0.27$0.41 |
| DeepSeek: DeepSeek V3.2 Speciale | 164K | 164K | $0.29$0.43 |
| DeepSeek: DeepSeek V4 Pro 0813 | 1.0M | 384K | $0.44$0.87 |
| DeepSeek: DeepSeek V4 Pro | 1.0M | 393K | $1.17$2.34 |
/v1/models/openrouter/deepseek/deepseek-v4-proDeepSeek 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.