Text Generation

Text Generation V2

Generate text using MiniMax models with support for single-turn and multi-turn conversations

post/v1/text/chatcompletion_v2

Request

Request body

model'MiniMax-M1' | 'MiniMax-Text-01' required

Model ID for text generation

temperaturenumber double

Sampling temperature (0.0 to 1.0)

max_tokensinteger

Maximum number of tokens to generate

streamboolean

Whether to stream the response

top_pnumber double

Nucleus sampling parameter

Response

Successful response

idstring

Unique identifier for the completion

object'chat.completion'

Object type

createdinteger

Unix timestamp of creation

modelstring

Model used for completion

Changes

No recorded changes to this operation across all 1 revision of this API.