Inference provider
Cohere
5 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
5
Median output speed
26 t/s
Median latency
631ms
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
- North Mini Code (free)Cohere20.2
- Command ACohere7.5
View as table
| Model | Intelligence |
|---|---|
| North Mini Code (free) (Cohere) | 20.2 |
| Command A (Cohere) | 7.5 |
Fastest output
Median tokens per second
- Command R7B (12-2024)Cohere74 t/s
- Command ACohere32 t/s
- North Mini Code (free)Cohere26 t/s
- Command R (08-2024)Cohere17 t/s
- Command R+ (08-2024)Cohere15 t/s
View as table
| Model | Tokens/s |
|---|---|
| Command R7B (12-2024) (Cohere) | 74 |
| Command A (Cohere) | 32 |
| North Mini Code (free) (Cohere) | 26 |
| Command R (08-2024) (Cohere) | 17 |
| Command R+ (08-2024) (Cohere) | 15 |
Full catalogue
All 5 models on Cohere
Filter by creator
5 of 5 models| North Mini Code (free) Cohereopen | 20.2 | Free |
| Command A Cohereopen | 7.5 | $0.38 |
| Command R7B (12-2024) Cohere | — | $0.006 |
| Command R (08-2024) Cohere | — | $0.02 |
| Command R+ (08-2024) Cohere | — | $0.38 |