deepseek-v4-flash
304.2B parameters
FP8
1,048,576 token context
completiontoolsthinking
106.7
output tokens / second
160 tokens · 1.50s server · 1.66s request
Performance statistics
Calculated live from valid five-minute RRDtool samples.
| Range | Latest | Average | Lowest | Median P50 | P05 | Highest | Std dev | Variability CV | Trend | Data coverage |
|---|---|---|---|---|---|---|---|---|---|---|
| Last 24 hours | 108.7 | 109.6 | 7.1 | 113.3 | 55.8 | 165.9 | 27.2 | 24.8% | +1.6% | 288 samples 100.0% |
| Last 7 days | 108.7 | 101.5 | 7.1 | 110.5 | 25.2 | 172.4 | 36.1 | 35.6% | +13.5% | 469 samples 23.3% |
| Last 30 days | 108.7 | 101.5 | 7.1 | 110.5 | 25.2 | 172.4 | 36.1 | 35.6% | +13.5% | 469 samples 5.4% |
P05: 5% of five-minute throughput samples are at or below this value; it represents lower-tail performance. CV: standard deviation ÷ average; lower is more stable. Trend: second-half average versus first-half average. Data coverage: valid samples versus all expected five-minute slots in the selected range.
Last 24 hours
Last 7 days
Last 30 days
