- Avg Tokens / Second
- 41.90
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 1140.00
- Runs Analysed
- 2
- Last Updated
- Oct 13, 2026, 02:00 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 45 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 |
|---|---|---|---|---|---|---|
| anthropic | direct · disabled | 41.90 | 41.30 | 42.60 | 1140.00 | 2 |
Frequently Asked Questions
How fast is claude-opus-4.8-fast?
The latest rolling average throughput is 41.90 tokens per second with an average time to first token of 1140.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 13, 2026, 02:00 AM.