Model specification · DeepSeek

DeepSeek V4 Pro

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
PriceStandard
Input$0.435 / M
Output$0.870 / M
Benchmark indexesReported indexes
Intelligence
44.3
Coding
59.4
Agentic
36.4
Design Arena Elo
1181
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00522
Long analysis100K / 4K × 150%$0.025
Workday20K / 2K × 1,00030%$7.85
More from DeepSeekAll DeepSeek models
ModelContextInput / MOutput / MIntel.
DeepSeek V4 Flash 07311.0M$0.090$0.18049.9
DeepSeek V3.2164K$0.269$0.40032
DeepSeek V3.1 Terminus164K$0.270$1.0030.4
R1164K$0.700$2.5018.5
DeepSeek V3 0324164K$0.270$1.1215.4