DeepSeek: DeepSeek V4 Pro
Input per million tokens
$0.70
Unchanged since November 16, 2026
- November 16, 2026: $0.70
Output per million tokens
$2.80
Unchanged since November 16, 2026
- November 16, 2026: $2.80
Alias deepseek-v4-pro > deepseek-v4-pro-1
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, and agentic workloads.
We are inviting early-access interest while we develop the platform.
| Model version | Status | Released | Retires | Hugging Face revision |
|---|---|---|---|---|
| deepseek-v4-pro-1CURRENT | Live |
Per million tokens
Batch is not offered for this model.
| Input | Cached input | Output | |
|---|---|---|---|
| On demand | $0.70 | Billed as input | $2.80 |
| Batch | Batch is not offered for this model. | ||
In every pool, every input token is billed at the input rate today.
Input per million tokens
$0.70
Unchanged since November 16, 2026
Output per million tokens
$2.80
Unchanged since November 16, 2026