Measured on claudeonaws
3 runs- Avg Tokens / Second
- 20.70
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 2540.00
- Runs Analysed
- 3
- Last Updated
- Oct 31, 2026, 06:48 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 24 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples
Every lane measuring this model
1 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 |
|---|---|---|---|---|---|---|
| claudeonaws | direct | 20.70 | 17.00 | 22.90 | 2540.00 | 3 |
Frequently Asked Questions
How fast is Claude Haiku Latest?
The latest rolling average throughput is 20.70 tokens per second with an average time to first token of 2540.00 ms across 3 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 31, 2026, 06:48 PM.