Model specification · DeepSeek
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro
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,...
SpecificationsReported values
- Context window
- 1.0M
- Maximum output
- 384K
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.955 / M |
| Output | $1.91 / M |
Benchmark indexesReported indexes
- Intelligence
- 12.6
- Coding
- —
- Agentic
- —
- Design Arena Elo
- 1148
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.011 |
| Long analysis | 100K / 4K × 1 | 50% | $0.059 |
| Workday | 20K / 2K × 1,000 | 30% | $17.67 |
More from DeepSeekAll DeepSeek models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 1.0M | $0.0060 | $0.500 | 28.6 |
| DeepSeek V4 Pro 0813 | 1.0M | $0.111 | $4.44 | 23.1 |