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
80 t/s
Median latency
719ms
Median price / 1M
$0.499
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 M3MiniMax45.4
- M2.7MiniMax38.9
- M2.5MiniMax34.5
- M2.1MiniMax32.1
- MiniMax M2MiniMax28.9
View as table
| Model | Intelligence |
|---|---|
| MiniMax M3 (MiniMax) | 45.4 |
| M2.7 (MiniMax) | 38.9 |
| M2.5 (MiniMax) | 34.5 |
| M2.1 (MiniMax) | 32.1 |
| MiniMax M2 (MiniMax) | 28.9 |
Fastest output
Median tokens per second
- M2.7MiniMax307 t/s
- MiniMax M2MiniMax119 t/s
- M2.5MiniMax91 t/s
- MiniMax M3MiniMax84 t/s
- MiniMax M1MiniMax76 t/s
- M2.1MiniMax66 t/s
- M2-herMiniMax26 t/s
- MiniMax-01MiniMax3 t/s
View as table
| Model | Tokens/s |
|---|---|
| M2.7 (MiniMax) | 307 |
| MiniMax M2 (MiniMax) | 119 |
| M2.5 (MiniMax) | 91 |
| MiniMax M3 (MiniMax) | 84 |
| MiniMax M1 (MiniMax) | 76 |
| M2.1 (MiniMax) | 66 |
| M2-her (MiniMax) | 26 |
| MiniMax-01 (MiniMax) | 3 |
Full catalogue
All 8 models on Minimax
Filter by creator
8 of 8 models| MiniMax M3 MiniMaxopen | 45.4 | $0.11 |
| M2.7 MiniMaxopen | 38.9 | $0.10 |
| M2.5 MiniMaxopen | 34.5 | $0.08 |
| M2.1 MiniMaxopen | 32.1 | $0.11 |
| MiniMax M2 MiniMaxopen | 28.9 | $0.09 |
| M2-her MiniMax | — | $0.04 |
| MiniMax M1 MiniMax | — | $0.20 |
| MiniMax-01 MiniMaxopen | — | $0.04 |