llm-benchmarks
githubdrose.io

DeepSeek V4 Pro 0813 Benchmarks


Measured on alibaba

19 runs
Avg Tokens / Second
0.14
Avg Time to First Token (ms)
50400.00
Runs Analysed
19
Last Updated
Sep 2, 2026, 06:07 AM

Throughput distribution

Throughput over time

DeepSeek V4 Pro 0813sail-research1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 44 tok/s (99th percentile) · dashed rule is the model's own mean · 8 further providers not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
alibabaDeepSeek V4 Pro 08130.140.140.1450400.00

Frequently Asked Questions

How fast is DeepSeek V4 Pro 0813?
The latest rolling average throughput is 0.14 tokens per second with an average time to first token of 50400.00 ms across 19 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 2, 2026, 06:07 AM.

Related models