Measured on novita
6 runs- Avg Tokens / Second
- 2.77
- Avg Time to First Token (ms)
- 23200.00
- Runs Analysed
- 6
- Last Updated
- Sep 1, 2026, 03:18 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 · shared vertical scale, 0 to 20 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn · 1 samples above the ceiling drawn at it
Every provider serving this model
2 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| novita | R1 | 2.84 | 1.24 | 4.64 | 25100.00 |
| novita | R1 | 2.70 | 2.14 | 3.26 | 21300.00 |
Frequently Asked Questions
How fast is R1?
The latest rolling average throughput is 2.77 tokens per second with an average time to first token of 23200.00 ms across 6 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 03:18 AM.