Measured on aionlabs
8 runs- Avg Tokens / Second
- 7.65
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 8220.00
- Runs Analysed
- 8
- Last Updated
- Sep 26, 2026, 05:02 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 55 tok/s (99th percentile) · dashed rule is the model's own mean
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 |
|---|---|---|---|---|---|---|
| aionlabs | via OpenRouter | 7.65 | 4.30 | 11.20 | 8220.00 | 8 |
| aionlabs | direct | 11.10 | 11.10 | 11.10 | 4660.00 | 1 |
Frequently Asked Questions
How fast is Aion 3.5?
The latest rolling average throughput is 7.65 tokens per second with an average time to first token of 8220.00 ms across 8 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 26, 2026, 05:02 AM.