DeepSeek
DeepSeek V4 Pro (Non-reasoning)
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,...
DeepSeek release notesModel Snapshot
ReleaseApr 24, 2026
Context1,048,576
Overall
Rank #122 across 566
31.2
Coding
Rank #50 across 222
59.4
Blended Price
Rank #125 across 371
$0.544/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed53.5 tok/s
First Token1.06s
Max Output384,000
Pricing
Blended$0.544/M
Input$0.435/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 31.2 | #122 |
| Artificial Analysis Coding Index | coding | 59.4 | #50 |
| GPQA | reasoning | 71.7% | #238 |
| Humanity's Last Exam | reasoning | 7.7% | #244 |
| SciCode |