- Avg Tokens / Second
- 38.80
- Avg Time to First Token (ms)
- 940.00
- Runs Analysed
- 639
- Last Updated
- Sep 1, 2026, 03:14 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 42 tok/s (99th percentile) · dashed rule is the model's own mean · 2 further providers not drawn · 1 samples above the ceiling drawn at it
Every provider serving this model
1 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| azure | Claude Haiku 4.5 | 38.80 | 31.80 | 45.60 | 940.00 |
Frequently Asked Questions
How fast is Claude Haiku 4.5?
The latest rolling average throughput is 38.80 tokens per second with an average time to first token of 940.00 ms across 639 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, 03:14 AM.