Modelo MiniMax | Documentación de API

# MiniMax Model

Call MiniMax M3 through the shared Chat Completions endpoint.

POST https://api.apihop.ai/v1/chat-completions

MiniMax M3 is available through the Common Chat Completions endpoint, with both non-streaming and SSE streaming text responses.

```text
POST https://api.apihop.ai/v1/chat-completions
```

## Available Model

| `model` value | Type | Non-streaming | SSE streaming |
| --- | --- | --- | --- |
| `minimax-m3` | Text chat | Yes | Yes |

## Authentication

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Non-streaming Request

```json
{
  "model": "minimax-m3",
  "messages": [
    {
      "role": "system",
      "content": "You are a code review assistant."
    },
    {
      "role": "user",
      "content": "List five risk areas to review in a payment webhook implementation."
    }
  ],
  "thinking": {
    "type": "disabled"
  },
  "stream": false
}
```

## Streaming Request

```json
{
  "model": "minimax-m3",
  "messages": [
    {
      "role": "user",
      "content": "Analyze a duplicate queue-consumption issue step by step."
    }
  ],
  "stream": true
}
```

This endpoint returns one complete JSON response by default. Set `stream: true` explicitly when you need SSE streaming.

## Request Fields

### `model` (string, required)

Use `minimax-m3`.

### `messages` (object[], required)

OpenAI Chat Completions style messages. Each message contains `role` and `content`.

### `stream` (boolean, Default: false)

`true` returns SSE; `false` returns one complete JSON response.

### `max_tokens` (integer)

Optional maximum output tokens, as a positive integer. Omit this field to use the upstream default for the selected model. Depending on the model, the budget may include reasoning tokens as well as final text. A small budget can truncate the answer or be exhausted before final text; increasing it may increase cost.

### `max_completion_tokens` (integer)

Optional compatibility alternative to `max_tokens`, with the same budget considerations. The selected model determines support; omit both fields to use the upstream default.

### `thinking` (object)

MiniMax thinking control. Use `{ "type": "disabled" }` for short, direct answers that do not need hidden reasoning. Omit the field to keep the model's default thinking behavior.

See [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions) for shared fields such as `temperature`, `top_p`, `frequency_penalty`, `presence_penalty`, `stop`, and `n`. `minimax-m3` accepts these standard fields, but not every parameter necessarily produces a measurable semantic change.

## Success Response

```json
{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "minimax-m3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Start by checking idempotency keys, acknowledgements, and retry policy..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 29,
    "completion_tokens": 104,
    "total_tokens": 133
  }
}
```

`usage` may include optional cached-input or reasoning-token details. Continue to base accounting and telemetry on the standard input, output, and total token fields.

## Usage Notes

- The current public contract is Chat Completions, including non-streaming and SSE streaming.
- `minimax-m3` is not currently published as an OpenAI Responses or Claude Messages model.
- Use `minimax-m3` exactly.
- Use `GET https://api.apihop.ai/v1/models` for the models visible to the current API Key, and use the console for current pricing.

## Related Docs

- [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions)
- [Model Catalog](https://apihop.ai/en/docs/api-reference/models)

MiniMax M3 está disponible mediante el endpoint Chat Completions común, con respuestas de texto sin streaming y con streaming SSE.

text

POST https://api.apihop.ai/v1/chat-completions

Modelo disponible

Valor de `model`	Tipo	Sin streaming	Streaming SSE
`minimax-m3`	Chat de texto	Sí	Sí

Autenticación

http

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Solicitud sin streaming

json

{
  "model": "minimax-m3",
  "messages": [
    {
      "role": "system",
      "content": "You are a code review assistant."
    },
    {
      "role": "user",
      "content": "List five risk areas to review in a payment webhook implementation."
    }
  ],
  "thinking": {
    "type": "disabled"
  },
  "stream": false
}

Solicitud con streaming

json

{
  "model": "minimax-m3",
  "messages": [
    {
      "role": "user",
      "content": "Analyze a duplicate queue-consumption issue step by step."
    }
  ],
  "stream": true
}

Este endpoint devuelve una respuesta JSON completa de forma predeterminada. Establece stream: true explícitamente cuando necesites streaming SSE.

Campos de solicitud

modelstringobligatorio

Usa minimax-m3.

messagesobject[]obligatorio

Mensajes al estilo OpenAI Chat Completions. Cada mensaje contiene role y content.

streambooleanPredeterminado: false

true devuelve SSE; false devuelve una respuesta JSON completa.

max_tokensinteger

Máximo opcional de tokens de salida, como entero positivo. Omite este campo para usar el valor predeterminado del proveedor para el modelo elegido. Según el modelo, el límite puede incluir tokens de razonamiento y texto final. Un límite pequeño puede truncar la respuesta o agotarse antes del texto final; aumentarlo puede incrementar el coste.

max_completion_tokensinteger

Alternativa opcional de compatibilidad a max_tokens, con las mismas consideraciones sobre el límite. El modelo elegido determina la compatibilidad; omite ambos campos para usar el valor predeterminado del proveedor.

thinkingobject

Control de razonamiento de MiniMax. Usa { "type": "disabled" } para respuestas breves y directas que no necesiten razonamiento oculto. Omite el campo para mantener el comportamiento predeterminado de razonamiento del modelo.

Consulta Chat Completions común para campos compartidos como temperature, top_p, frequency_penalty, presence_penalty, stop y n. minimax-m3 acepta estos campos estándar, pero no todos los parámetros producen necesariamente un cambio semántico medible.

Respuesta correcta

json

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "minimax-m3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Start by checking idempotency keys, acknowledgements, and retry policy..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 29,
    "completion_tokens": 104,
    "total_tokens": 133
  }
}

usage puede incluir detalles opcionales de entrada en caché o tokens de razonamiento. Sigue basando la contabilidad y telemetría en los campos estándar de tokens de entrada, salida y total.

Notas de uso

El contrato público actual es Chat Completions, tanto sin streaming como con streaming SSE.
minimax-m3 no está publicado actualmente como modelo de OpenAI Responses ni Claude Messages.
Usa exactamente minimax-m3.
Usa GET https://api.apihop.ai/v1/models para consultar los modelos visibles para la clave actual y la consola para los precios vigentes.