Measured on inception
1 runs- Avg Tokens / Second
- 13.30
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 5590.00
- Runs Analysed
- 1
- Last Updated
- Oct 11, 2026, 07:18 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 14 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples
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 |
|---|---|---|---|---|---|---|
| inception | direct · disabled | 13.30 | 13.30 | 13.30 | 5590.00 | 1 |
| inception | via OpenRouter · disabled | 20.00 | 20.00 | 20.00 | 5740.00 | 1 |
Frequently Asked Questions
How fast is Mercury 2.5 Preview?
The latest rolling average throughput is 13.30 tokens per second with an average time to first token of 5590.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 11, 2026, 07:18 PM.