Measured on relace
9 runs- Avg Tokens / Second
- 1.25
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 60800.00
- Runs Analysed
- 9
- Last Updated
- Sep 21, 2026, 01:10 AM
Throughput distribution
Throughput over time
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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 60 tok/s (99th percentile) · dashed rule is the model's own mean
Every lane measuring this model
2 measured · live first · a lane is a provider, a catalogue id and a transport| Provider | Lane | Avg Toks/Sec | Min | Max | Avg TTF (ms) | n |
|---|---|---|---|---|---|---|
| relace | direct | 1.25 | 0.63 | 3.03 | 60800.00 | 9 |
| relace | via OpenRouter | 2.49 | 2.49 | 2.49 | 25200.00 | 1 |
Frequently Asked Questions
How fast is DeepSeek V4.1 Flash?
The latest rolling average throughput is 1.25 tokens per second with an average time to first token of 60800.00 ms across 9 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 21, 2026, 01:10 AM.