Measured over the last 30 days
- Models Tracked
- 9
- Avg Tokens / Second
- 20.57
- Avg Time to First Token (ms)
- 8381.11
- Last Updated
- Sep 1, 2026
| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Sonar Pro Search | 34.60 | 16.40 | 52.00 | 1300.00 |
| Sonar Pro Search | 32.70 | 26.30 | 37.90 | 1200.00 |
| Sonar | 26.90 | 18.00 | 36.10 | 1840.00 |
| Sonar Pro | 24.90 | 12.90 | 40.40 | 2090.00 |
| Sonar Pro | 23.90 | 15.00 | 30.50 | 2130.00 |
| Sonar | 23.50 | 12.70 | 37.60 | 2210.00 |
| Sonar Reasoning Pro | 9.16 | 5.94 | 14.30 | 6930.00 |
| Sonar Reasoning Pro | 8.16 | 5.04 | 15.00 | 7530.00 |
| Sonar Deep Research | 1.28 | 1.10 | 1.63 | 50200.00 |
Frequently Asked Questions
Which perplexity model is fastest?
Based on recent tests, Sonar Pro Search shows the highest average throughput among tracked perplexity models.
How many recent measurements feed this dashboard?
This provider summary aggregates 168 individual prompts measured across 137 monitoring runs over the past month.