DeepSeek
DeepSeek V4 Flash (Non-reasoning)
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
DeepSeek release notesModel Snapshot
ReleaseApr 24, 2026
Context1,048,575
Overall
Rank #146 across 566
28.7
Coding
Rank #61 across 222
56.2
Blended Price
Rank #48 across 371
$0.175/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 Speed90.1 tok/s
First Token0.91s
Max Outputn/a
Pricing
Blended$0.175/M
Input$0.140/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 28.7 | #146 |
| Artificial Analysis Coding Index | coding | 56.2 | #61 |
| GPQA | reasoning | 71.6% | #239 |
| Humanity's Last Exam | reasoning | 7.0% | #262 |
| SciCode |