MiniMax
Endpoint: https://mmu.vod-qcloud.com/v1인증: VOD ApiToken / Bearer
기본 정보
| 항목 | 값 |
|---|---|
| 호출 주소 | https://mmu.vod-qcloud.com |
| 인증 | VOD 애플리케이션에서 발급한 ApiToken / Bearer |
| 출력 | 텍스트 / 구조화된 응답 |
| 응답 방식 | JSON / SSE |
지원 프로토콜
| 규격 | 경로 | 대상 |
|---|---|---|
| Chat Completions | POST /v1/chat/completions | 아래 모든 모델 |
| Messages | POST /v1/messages | minimax-m2.7 |
아래 모델 ID에 해당 규격을 사용합니다. 인증과 공통 필드는 API Reference를 따릅니다.
샘플링 옵션
이 문서에 나열된 모든 모델에 공통으로 적용됩니다.
| 파라미터 | 설정 |
|---|---|
temperature | 설정 가능 |
top_p | 설정 가능 |
temperature는 샘플링 온도, top_p는 누적 확률 범위를 지정합니다. 한 가지 방식을 중심으로 조정합니다.
버전별 추론 설정
| 모델 ID | 설정 방식 | 비활성화 |
|---|---|---|
minimax-m2.7 | thinking_enabled | 비활성화 불가 |
minimax-m2.5 | thinking_enabled | 비활성화 불가 |
Chat Completions 기준입니다. 추론 내용은 reasoning_content, 최종 답변은 content에서 읽습니다. 비활성화할 수 없는 버전에는 비활성화 옵션을 전달하지 않습니다.
요청 파라미터
| 파라미터 | 필수 | 타입 | 설명 |
|---|---|---|---|
model | 필수 | String | 버전별 옵션 표의 모델 ID |
messages | 필수 | Array | Chat Completions / Messages의 대화 입력 |
max_tokens | 선택 | Integer | Chat Completions / Messages의 생성 한도. Messages에서는 필수 |
stream | 선택 | Boolean | true: SSE / false: JSON |
요청 예시
Chat Completions
json
{
"model": "minimax-m2.7",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 2048,
"stream": false
}응답
json
{
"id": "01a0de41-429b-777d-aaee-51066e76e8e6",
"object": "chat.completion",
"model": "minimax-m2.7",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "OK",
"reasoning_content": "The user asks: \"Reply with exactly OK and nothing else.\" That is a direct instruction. There's no policy violation. So the assistant should respond with exactly \"OK\". No extra characters, no punctuation beyond exactly \"OK\"? The user said \"Reply with exactly OK and nothing else.\" That likely means the assistant must output \"OK\" exactly, no extra whitespace, no newline? The user wants exactly \"OK\". So output \"OK\". Must ensure no extra spaces, no line breaks. It is safe. So final answer is just"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 51,
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 14
},
"prompt_cached_tokens_details": {
"audio_tokens": 0
},
"completion_tokens": 114,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0
},
"total_tokens": 165
}
}Messages
json
{
"model": "minimax-m2.7",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 512,
"stream": false
}응답
json
{
"id": "01a0de34-dae5-7c93-816b-35ec7b860908",
"model": "minimax-m2.7",
"type": "message",
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": "The user says: \"Reply with exactly OK and nothing else.\" They want the assistant to reply with exactly \"OK\". This is a direct request. There's no policy conflict. The user wants a simple response. The instruction is to reply with exactly OK and nothing else.\n\nWe must comply. So output \"OK\".",
"signature": "8754e352280f346195f01e478898770cf8c079fad609a972559acf7eb41e66b6"
},
{
"type": "text",
"text": "OK"
}
],
"stop_reason": "end_turn",
"usage": {
"input_tokens": 49,
"output_tokens": 68
}
}특수 설정
텍스트 대화와 코드 작업에 사용합니다. Messages의 thinking 객체로 추론 설정을 전달합니다. Messages 규격에서는 텍스트 블록과 추론 블록을 구분해 읽습니다. 추론 토큰도 생성 한도를 사용하므로 최종 답변이 비어 있으면 종료 사유와 토큰 사용량을 확인합니다.
Messages 추론 요청
minimax-m2.7
json
{
"model": "minimax-m2.7",
"messages": [
{
"role": "user",
"content": "Find the smallest positive integer n for which n squared is divisible by 72. Explain briefly."
}
],
"max_tokens": 2048,
"stream": false,
"thinking": {
"type": "adaptive"
}
}응답의 content에서 type=thinking과 type=text를 구분합니다. 추론 블록의 서명은 후속 대화에서 원형을 유지합니다.