MiniMax - Alibaba Cloud Model Studio

Este documento aplica-se apenas à região da China continental. Para usar o modelo, obtenha uma chave de API na região da China continental.

Primeiros passos

Pré-requisitos: Crie uma chave de API e defina-a como variável de ambiente. Caso utilize um SDK para chamar o modelo, instale o SDK do OpenAI ou DashScope.

OpenAI compatible
DashScope

Python
Node.js
HTTP

Código de exemplo

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="MiniMax-M2.5",
    messages=[{"role": "user", "content": "Who are you?"}],
    stream=True,
)

reasoning_content = ""  # Full chain-of-thought
answer_content = ""     # Full response
is_answering = False    # Whether response has started

print("\n" + "=" * 20 + "Chain of thought" + "=" * 20 + "\n")

for chunk in completion:
    if chunk.choices:
        delta = chunk.choices[0].delta
        # Collect only chain-of-thought content
        if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
            if not is_answering:
                print(delta.reasoning_content, end="", flush=True)
            reasoning_content += delta.reasoning_content
        # Start response when content arrives
        if hasattr(delta, "content") and delta.content:
            if not is_answering:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            print(delta.content, end="", flush=True)
            answer_content += delta.content

Resposta

====================Chain of thought====================

The user asked "Who are you?".

I should reply and introduce myself as an AI assistant.
====================Full response====================

Hello! I am MiniMax-M2.5, an AI assistant. I can help you answer questions, provide information, hold conversations, and more. How can I help you?

Código de exemplo

import OpenAI from "openai";
import process from 'process';

// Initialize the OpenAI client
const openai = new OpenAI({
    // If you have not set the environment variable, replace this with your Alibaba Cloud Model Studio API key: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = ''; // Full chain-of-thought
let answerContent = ''; // Full response
let isAnswering = false; // Whether response has started

async function main() {
    const messages = [{ role: 'user', content: 'Who are you?' }];

    const stream = await openai.chat.completions.create({
        model: 'MiniMax-M2.5',
        messages,
        stream: true,
    });

    console.log('\n' + '='.repeat(20) + 'Chain of thought' + '='.repeat(20) + '\n');

    for await (const chunk of stream) {
        if (chunk.choices?.length) {
            const delta = chunk.choices[0].delta;
            // Collect only chain-of-thought content
            if (delta.reasoning_content !== undefined && delta.reasoning_content !== null) {
                if (!isAnswering) {
                    process.stdout.write(delta.reasoning_content);
                }
                reasoningContent += delta.reasoning_content;
            }

            // Start response when content arrives
            if (delta.content !== undefined && delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    }
}

main();

Resposta

====================Chain of thought====================

The user asked "Who are you?".

I should reply and introduce myself as an AI assistant.
====================Full response====================

Hello! I am MiniMax-M2.5, an AI assistant. I can help you answer questions, provide information, hold conversations, and more. How can I help you?

Código de exemplo

curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "MiniMax-M2.5",
    "messages": [
        {
            "role": "user",
            "content": "Who are you?"
        }
    ]
}'

Resposta

{
    "choices": [
        {
            "message": {
                "content": "Hello! I am MiniMax-M2.5, an AI assistant developed by MiniMax. I can help you answer questions, provide information, hold conversations, and complete various text-related tasks. How can I help you?",
                "reasoning_content": "The user asked \"Who are you?\".\n\nI should reply and introduce myself.",
                "role": "assistant"
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 40,
        "completion_tokens": 72,
        "total_tokens": 112,
        "completion_tokens_details": {
            "reasoning_tokens": 26
        },
        "prompt_tokens_details": {
            "cached_tokens": 0
        }
    },
    "created": 1771944590,
    "system_fingerprint": null,
    "model": "MiniMax-M2.5",
    "id": "chatcmpl-b1277a9c-52da-9de7-988a-d5c063d83xxx"
}

Python
Java
HTTP

Código de exemplo

import os
from dashscope import Generation

# Initialize request parameters
messages = [{"role": "user", "content": "Who are you?"}]

completion = Generation.call(
    # If you have not set the environment variable, replace this with your Alibaba Cloud Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="MiniMax-M2.5",
    messages=messages,
    result_format="message",  # Set result format to message
    stream=True,              # Enable streaming output
    incremental_output=True,  # Enable incremental output
)

reasoning_content = ""  # Full chain-of-thought
answer_content = ""     # Full response
is_answering = False    # Whether response has started

print("\n" + "=" * 20 + "Chain of thought" + "=" * 20 + "\n")

for chunk in completion:
    message = chunk.output.choices[0].message

    # Collect only chain-of-thought content
    if message.reasoning_content:
        if not is_answering:
            print(message.reasoning_content, end="", flush=True)
        reasoning_content += message.reasoning_content

    # Start response when content arrives
    if message.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
            is_answering = True
        print(message.content, end="", flush=True)
        answer_content += message.content

# After the loop ends, reasoning_content and answer_content contain the full content
# You can process them further as needed
# print(f"\n\nFull chain of thought:\n{reasoning_content}")
# print(f"\nFull response:\n{answer_content}")

Resposta

====================Chain of thought====================

The user asked "Who are you?".

I should reply and introduce myself as an AI assistant.
====================Full response====================

Hello! I am MiniMax-M2.5, an AI assistant. I can help you answer questions, provide information, hold conversations, and more. How can I help you?

Código de exemplo

// DashScope SDK version >= 2.19.4
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.Flowable;
import java.lang.System;
import java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

public class Main {
    private static final Logger logger = LoggerFactory.getLogger(Main.class);
    private static StringBuilder reasoningContent = new StringBuilder();
    private static StringBuilder finalContent = new StringBuilder();
    private static boolean isFirstPrint = true;

    private static void handleGenerationResult(GenerationResult message) {
        String reasoning = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
        String content = message.getOutput().getChoices().get(0).getMessage().getContent();

        if (reasoning != null && !reasoning.isEmpty()) {
            reasoningContent.append(reasoning);
            if (isFirstPrint) {
                System.out.println("====================Chain of thought====================");
                isFirstPrint = false;
            }
            System.out.print(reasoning);
        }

        if (content != null && !content.isEmpty()) {
            finalContent.append(content);
            if (!isFirstPrint) {
                System.out.println("\n====================Full response====================");
                isFirstPrint = true;
            }
            System.out.print(content);
        }
    }
    private static GenerationParam buildGenerationParam(Message userMsg) {
        return GenerationParam.builder()
                // If you have not set the environment variable, replace this line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("MiniMax-M2.5")
                .incrementalOutput(true)
                .resultFormat("message")
                .messages(Arrays.asList(userMsg))
                .build();
    }
    public static void streamCallWithMessage(Generation gen, Message userMsg)
            throws NoApiKeyException, ApiException, InputRequiredException {
        GenerationParam param = buildGenerationParam(userMsg);
        Flowable<GenerationResult> result = gen.streamCall(param);
        result.blockingForEach(message -> handleGenerationResult(message));
    }

    public static void main(String[] args) {
        try {
            Generation gen = new Generation();
            Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you?").build();
            streamCallWithMessage(gen, userMsg);
            // Print final results
            // if (reasoningContent.length() > 0) {
            //     System.out.println("\n====================Full response====================");
            //     System.out.println(finalContent.toString());
            // }
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            logger.error("An exception occurred: {}", e.getMessage());
        }
        System.exit(0);
    }
}

Resposta

====================Chain of thought====================

The user asked "Who are you?".

I should reply and introduce myself as an AI assistant.
====================Full response====================

Hello! I am MiniMax-M2.5, an AI assistant. I can help you answer questions, provide information, hold conversations, and more. How can I help you?

Código de exemplo

curl

curl -X POST "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "MiniMax-M2.5",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters": {
        "result_format": "message"
    }
}'

Resposta

{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "content": "Hello! I am MiniMax-M2.5, an AI assistant developed by MiniMax. I can help you answer questions, provide information, hold conversations, and complete various text-related tasks. How can I help you?",
                    "reasoning_content": "The user asked \"Who are you?\".\n\nI should reply and introduce myself. I should state that I am MiniMax-M2.5, an AI assistant developed by MiniMax.",
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "input_tokens": 41,
        "output_tokens": 79,
        "output_tokens_details": {
            "reasoning_tokens": 39
        },
        "prompt_tokens_details": {
            "cached_tokens": 0
        },
        "total_tokens": 120
    },
    "request_id": "1bbd770e-564a-4601-83fc-3bf639423xxx"
}

Outros recursos

Modelo	Conversa em múltiplas rodadas	Pensamento profundo	Chamada de função	Saída estruturada	Busca na web	Modo parcial	Cache de contexto
MiniMax-M2.5	Supported	Supported	Supported	Not supported	Supported	Not supported	Supported Apenas cache implícito.

Valores padrão dos parâmetros

Modelo	temperature	top_p	presence_penalty
MiniMax-M2.5	1,0	0,95	0,0

Modelos e faturamento

O MiniMax-M2.5 destaca-se em programação, tarefas de escritório, resumo de texto e outras atividades, com alta velocidade de saída. Recomendamos este modelo. Para obter informações sobre a janela de contexto e os preços, consulte Modelos recomendados. O faturamento baseia-se na quantidade de tokens de entrada e saída.

Códigos de erro

Se a chamada do modelo falhar e retornar uma mensagem de erro, consulte as mensagens de erro para solucionar o problema.

​Primeiros passos

Código de exemplo

Resposta

​Outros recursos

​Valores padrão dos parâmetros

​Modelos e faturamento

​Códigos de erro

Primeiros passos

Outros recursos

Valores padrão dos parâmetros

Modelos e faturamento

Códigos de erro