Inference provider
Cohere
7 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
7
Median output speed
50 t/s
Median latency
398ms
Median price / 1M
$0.262
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- V4 Flash 0731DeepSeek34.3
- Command A+Cohere13.1
- North Mini Code (free)Cohere9.9
- Command ACohere7.0
View as table
| Model | Intelligence |
|---|---|
| V4 Flash 0731 (DeepSeek) | 34.3 |
| Command A+ (Cohere) | 13.1 |
| North Mini Code (free) (Cohere) | 9.9 |
| Command A (Cohere) | 7.0 |
Fastest output
Median tokens per second
- V4 Flash 0731DeepSeek223 t/s
- Command A+Cohere157 t/s
- Command R7B (12-2024)Cohere56 t/s
- North Mini Code (free)Cohere50 t/s
- Command ACohere44 t/s
- Command R (08-2024)Cohere34 t/s
- Command R+ (08-2024)Cohere10 t/s
View as table
| Model | Tokens/s |
|---|---|
| V4 Flash 0731 (DeepSeek) | 223 |
| Command A+ (Cohere) | 157 |
| Command R7B (12-2024) (Cohere) | 56 |
| North Mini Code (free) (Cohere) | 50 |
| Command A (Cohere) | 44 |
| Command R (08-2024) (Cohere) | 34 |
| Command R+ (08-2024) (Cohere) | 10 |
Full catalogue
All 7 models on Cohere
Filter by creator
7 of 7 models| V4 Flash 0731 DeepSeekopen | 34.3 | $0.05 |
| Command A+ Cohere | 13.1 | $0.14 |
| North Mini Code (free) Cohereopen | 9.9 | Free |
| Command A Cohereopen | 7.0 | $0.38 |
| Command R7B (12-2024) Cohere | — | $0.006 |
| Command R (08-2024) Cohere | — | $0.02 |
| Command R+ (08-2024) Cohere | — | $0.38 |