Measured on relace
7 runs- Avg Tokens / Second
- 10.10
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 9040.00
- Runs Analysed
- 7
- Last Updated
- Nov 4, 2026, 06:01 PM
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 524 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 | via OpenRouter | 10.10 | 2.58 | 19.60 | 9040.00 | 7 |
| relace | direct | 4.07 | 2.02 | 9.13 | 20200.00 | 11 |
Frequently Asked Questions
How fast is DeepSeek V4.1 Flash?
The latest rolling average throughput is 10.10 tokens per second with an average time to first token of 9040.00 ms across 7 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 4, 2026, 06:01 PM.