Measured over the last 30 days
- Models Tracked
- 8
- Avg Tokens / Second
- 12.45
- Avg Time to First Token (ms)
- 12869.08
- Last Updated
- Sep 1, 2026
All inceptron models
8 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5.2 | 37.20 | 8.37 | 51.60 | 3030.00 |
| Kimi K2.7 Code | 16.50 | 4.72 | 40.20 | 4810.00 |
| Kimi K2.7 Code | 11.80 | 5.44 | 26.70 | 7340.00 |
| MiniMax M2.5 | 10.50 | 5.28 | 17.00 | 6740.00 |
| MiniMax M2.5 | 6.34 | 3.85 | 8.89 | 9990.00 |
| Kimi K2.6 | 6.04 | 3.41 | 9.20 | 11600.00 |
| Kimi K2.6 | 5.40 | 2.40 | 7.50 | 13400.00 |
| DeepSeek V4 Flash 0731 | 2.12 | 1.08 | 4.92 | 42400.00 |
Frequently Asked Questions
Which inceptron model is fastest?
Based on recent tests, GLM 5.2 shows the highest average throughput among tracked inceptron models.
How many recent measurements feed this dashboard?
This provider summary aggregates 904 individual prompts measured across 739 monitoring runs over the past month.