DeepSeek V4 Pro 0424: Release Intelligence, Performance & Price
Available providers
Artificial Analysis Intelligence Index
Output speed
Per Intelligence Index Task
The DeepSeek V4 Pro 0424 release offers 3 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across the 3 models.
- For intelligence, the top model of DeepSeek V4 Pro 0424 is DeepSeek V4 Pro (Reasoning, Max Effort) at 31.
- For output speed, the fastest model is DeepSeek V4 Pro (Non-reasoning) at 93 t/s.
- For latency, DeepSeek V4 Pro (Non-reasoning) at 1.56s offers the lowest time to first answer token.
- For pricing, DeepSeek V4 Pro (Reasoning, Max Effort) at $0.12 offers the lowest cost per task.
| Input modality | Supports: text |
|---|---|
| Output modality | Supports: text |
| Context window | 1M ~1500 A4 pages of size 12 Arial font |
| Total parameters | 1.6T |
| Active parameters | 49B Number of parameters active per token during inference |
| Model weights | Hugging Face |
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench v4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
More from DeepSeek
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro (Reasoning, Max Effort) |  DeepSeek | 31 | 1.6T 49B active at inference time | 1M | $0.2 | 86 |    +6 | ||
| DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 30 | 1.6T 49B active at inference time | 1M | $0.2 | 92 | +5 | ||
| DeepSeek V4 Pro (Non-reasoning) | DeepSeek | 21 | 1.6T 49B active at inference time | 1M | $0.2 | 93 |   +2 |