Measured over the last 30 days
- Models Tracked
- 22
- Avg Tokens / Second
- 60.15
- Avg Time to First Token (ms)
- 770.45
- Last Updated
- Aug 9, 2026
All bedrock models
22 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| nova-micro | 120.00 | 27.20 | 188.00 | 310.00 |
| llama-4-maverick | 108.00 | 23.10 | 135.00 | 290.00 |
| llama-3.1-8b | 96.00 | 7.07 | 112.00 | 400.00 |
| llama-4-scout | 95.60 | 43.50 | 130.00 | 290.00 |
| nova-lite | 91.00 | 1.05 | 129.00 | 370.00 |
| nova-pro | 90.80 | 10.80 | 132.00 | 390.00 |
| llama-3.3-70b | 85.20 | 4.60 | 122.00 | 370.00 |
| mistral-7b | 82.00 | 25.10 | 87.00 | 190.00 |
| llama-3-8b | 77.80 | 1.05 | 86.70 | 260.00 |
| mixtral-8x7b | 73.10 | 19.30 | 80.60 | 240.00 |
| mistral-small | 56.20 | 23.00 | 60.60 | 210.00 |
| llama-3.1-70b | 52.80 | 2.00 | 73.60 | 480.00 |
| llama-3.2-90b | 46.80 | 36.20 | 49.90 | 350.00 |
| claude-haiku-4.5 | 43.30 | 1.04 | 59.00 | 930.00 |
| mistral-large | 42.10 | 5.75 | 46.60 | 260.00 |
| llama-3-70b | 36.30 | 1.04 | 41.50 | 550.00 |
| claude-opus-4-7 | 27.80 | 1.03 | 38.70 | 1710.00 |
| claude-sonnet-4.6 | 27.00 | 6.36 | 33.10 | 980.00 |
| claude-sonnet-4.5 | 22.00 | 1.00 | 29.30 | 1510.00 |
| claude-opus-4.6 | 21.00 | 3.58 | 24.80 | 1690.00 |
| claude-opus-4.5 | 20.10 | 1.05 | 23.30 | 1660.00 |
| Claude Opus 4.1 | 8.41 | 1.14 | 15.70 | 3510.00 |
Frequently Asked Questions
Which bedrock model is fastest?
Based on recent tests, nova-micro shows the highest average throughput among tracked bedrock models.
How many recent measurements feed this dashboard?
This provider summary aggregates 29005 individual prompts measured across 26464 monitoring runs over the past month.