Measured over the last 30 days
- Models Tracked
- 2
- Avg Tokens / Second
- 10.71
- Avg Time to First Token (ms)
- 5195.00
- Last Updated
- Oct 17, 2026
All openinference models
2 live · one row per model · fastest first · 2 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 13.00 | 4.52 | 38.30 | 2870.00 |
| DeepSeek V4 Flash 0423 | 8.43 | 0.62 | 25.60 | 7520.00 |
Frequently Asked Questions
Which openinference model is fastest?
Based on recent tests, DeepSeek V4 Flash 0731 shows the highest average throughput among tracked openinference models.
How many recent measurements feed this dashboard?
This provider summary aggregates 692 individual prompts measured across 667 monitoring runs over the past month.