deepseek-v4.1-flash
763.2B parameters
FP8
1,048,576 token context
completionthinkingtoolsvision
74.7
output tokens / second
160 tokens · 2.14s server · 2.28s request
Performance statistics
Calculated live from valid twenty-minute RRDtool samples.
| Range | Latest | Average | Lowest | Median P50 | P05 | Highest | Std dev | Variability CV | Trend | Data coverage |
|---|---|---|---|---|---|---|---|---|---|---|
| Last 24 hours | 78.6 | 177.1 | 63.6 | 176.7 | 106.6 | 238.0 | 40.7 | 23.0% | -3.3% | 72 samples 100.0% |
| Last 7 days | 78.6 | 157.7 | 9.1 | 166.3 | 36.1 | 254.1 | 56.3 | 35.7% | -2.3% | 345 samples 68.5% |
| Last 30 days | 78.6 | 157.7 | 9.1 | 166.3 | 36.1 | 254.1 | 56.3 | 35.7% | -2.3% | 345 samples 16.0% |
P05: 5% of twenty-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 twenty-minute slots in the selected range.
Last 24 hours
Last 7 days
Last 30 days
