Measured on chutes
6 runs- Avg Tokens / Second
- 3.82
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 17700.00
- Runs Analysed
- 6
- Last Updated
- Oct 15, 2026, 06:26 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 62 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 |
|---|---|---|---|---|---|---|
| chutes | direct | 3.82 | 2.26 | 5.55 | 17700.00 | 6 |
| chutes | via OpenRouter | 7.58 | 6.93 | 8.24 | 7540.00 | 2 |
Frequently Asked Questions
How fast is Kimi K2.6?
The latest rolling average throughput is 3.82 tokens per second with an average time to first token of 17700.00 ms across 6 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 15, 2026, 06:26 AM.