DeepSeek V4 Flash
DeepSeek · Released Apr 24, 2026
$0.09
Input price / MTok
#2 of 27$0.18
Output price / MTok
#1 of 271M
Context window
#16 of 28113
Tokens / sec
#10 of 2188.1
GPQA Diamond
#9 of 1979
SWE-bench Verified
#5 of 1291.6
LiveCodeBench
#3 of 8Summary
DeepSeek V4 Flash is a open-source language model from DeepSeek, released on Apr 24, 2026.
At $0.09 input and $0.18 output per million tokens, it ranks #2 of 27 for input price, placing it among the most affordable options.
Its context window of 1M tokens ranks #16 of 28 for context depth in this dataset.
It targets budget, coding workloads.
Throughput is measured at 113 tokens per second (ranked #10 of 21 for throughput).
284B total params / 13B active; the deepseek-reasoner API alias now routes here.
Benchmarks
| Benchmark | Score | Max | % | Rank | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 88.1 | 100 | 88.1% | #9/19 | DeepSeek (self-reported in technical rep... |
| SWE-bench Verified | 79 | 100 | 79.0% | #5/12 | DeepSeek (self-reported in technical rep... |
| LiveCodeBench | 91.6 | 100 | 91.6% | #3/8 | DeepSeek (self-reported in technical rep... |
Similar Models
Compare all 6 modelsModels with the most shared benchmark coverage and closest scores to DeepSeek V4 Flash.
Compare DeepSeek V4 Flash side by side
Pre-filled with 5 similar models
Speed source: https://artificialanalysis.ai/models/deepseek-v4-flash