Measured over the last 30 days
- Models Tracked
- 6
- Avg Tokens / Second
- 32.88
- Avg Time to First Token (ms)
- 1040.00
- Last Updated
- Oct 14, 2026
All cohere models
6 live · one row per model · fastest first · 1 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Command R7B (12-2024) | 46.20 | 40.20 | 52.20 | 480.00 |
| Command R (08-2024) | 38.40 | 31.50 | 45.30 | 480.00 |
| DeepSeek V4 Flash 0731 | 35.10 | 26.70 | 47.30 | 1370.00 |
| Command A | 35.00 | 34.00 | 36.00 | 520.00 |
| Command A+ | 24.00 | 12.40 | 31.20 | 2710.00 |
| Command R+ (08-2024) | 18.60 | 11.60 | 25.60 | 680.00 |
Frequently Asked Questions
Which cohere model is fastest?
Based on recent tests, Command R7B (12-2024) shows the highest average throughput among tracked cohere models.
How many recent measurements feed this dashboard?
This provider summary aggregates 312 individual prompts measured across 311 monitoring runs over the past month.