Back
MiniMax-M3
MiniMax·Token-based
TPS
—
Average latency
—
Success rate
—
Pricing
Base Price
Input
$0.618/ 1M
Output
$2.471/ 1M
Cache write$0.124/ 1M
Pricing by Group
Auto Group Chain→default
| Group | Ratio | Input | Output | Cache Write |
|---|---|---|---|---|
| default | 1x | $0.618 | $2.471 | $0.124 |
Prices shown per 1M tokens
Model
ProviderMiniMax
TypeToken-based
Groups
default
Endpoints
openai