Inference provider
Minimax
8 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
8
Median output speed
72 t/s
Median latency
732ms
Median price / 1M
$0.525
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
- MiniMax M3MiniMax29.2
- M2.7MiniMax22.8
- M2.5MiniMax22.8
- M2.1MiniMax20.9
- MiniMax M2MiniMax18.6
View as table
| Model | Intelligence |
|---|---|
| MiniMax M3 (MiniMax) | 29.2 |
| M2.7 (MiniMax) | 22.8 |
| M2.5 (MiniMax) | 22.8 |
| M2.1 (MiniMax) | 20.9 |
| MiniMax M2 (MiniMax) | 18.6 |
Fastest output
Median tokens per second
- M2.7MiniMax252 t/s
- M2.5MiniMax211 t/s
- MiniMax M3MiniMax115 t/s
- MiniMax M2MiniMax92 t/s
- M2-herMiniMax53 t/s
- MiniMax M1MiniMax49 t/s
- M2.1MiniMax41 t/s
- MiniMax-01MiniMax27 t/s
View as table
| Model | Tokens/s |
|---|---|
| M2.7 (MiniMax) | 252 |
| M2.5 (MiniMax) | 211 |
| MiniMax M3 (MiniMax) | 115 |
| MiniMax M2 (MiniMax) | 92 |
| M2-her (MiniMax) | 53 |
| MiniMax M1 (MiniMax) | 49 |
| M2.1 (MiniMax) | 41 |
| MiniMax-01 (MiniMax) | 27 |
Full catalogue
All 8 models on Minimax
Filter by creator
8 of 8 models| MiniMax M3 MiniMaxopen | 29.2 | $0.11 |
| M2.7 MiniMaxopen | 22.8 | $0.11 |
| M2.5 MiniMaxopen | 22.8 | $0.09 |
| M2.1 MiniMaxopen | 20.9 | $0.11 |
| MiniMax M2 MiniMaxopen | 18.6 | $0.09 |
| M2-her MiniMax | — | $0.04 |
| MiniMax M1 MiniMax | — | $0.20 |
| MiniMax-01 MiniMaxopen | — | $0.04 |