MiniMax
4 params
MiniMax Minimax M3 parameters
These are the parameters modelparams.dev tracks for MiniMax Minimax M3. Each row gives the type, default, valid range or values, and the conditions that gate it. It's the same data the JSON API serves.
| Parameter | Type | Default | Description | Condition |
|---|---|---|---|---|
| Length · 1 param | ||||
|
Max completion tokens
max_completion_tokens
|
integer (1…+∞) | — | Maximum number of tokens to generate in the completion. | — |
| Sampling · 2 params | ||||
|
Temperature
temperature
|
number (0.01…1 step 0.01) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. Values must be greater than 0 and at most 1. | — |
|
Top P
top_p
|
number (0.01…1 step 0.01) | 0.95 | Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability. | — |
| Reasoning · 1 param | ||||
|
Split reasoning
reasoning_split
|
boolean | false | Returns the model's reasoning in a separate reasoning_details field instead of inline with the response. | — |
Other MiniMax models
MiniMax M2
MiniMax M2
subscription
MiniMax M2.1
MiniMax M2.1
subscription
MiniMax M2.1 Highspeed
MiniMax M2.1 Highspeed
subscription
MiniMax M2.5
MiniMax M2.5
subscription
MiniMax M2.5 Highspeed
MiniMax M2.5 Highspeed
subscription
MiniMax M2.7
MiniMax M2.7
subscription
MiniMax M2.7 Highspeed
MiniMax M2.7 Highspeed
subscription
MiniMax M3
subscription