快速入门

在几分钟内完成您的第一次 API 调用。

本快速入门专为 OpenAI 兼容推理服务设计。请将下面的占位符值替换为您的 API 密钥和模型名称。

---

前提条件

在开始之前，请确保您具备以下条件：

• 您的推理服务 API 密钥
• 已安装 curl，或者如果您想使用 SDK，需安装 Python / Node.js

---

第 1 步：创建并导出 API 密钥

您可以在此处创建 API 密钥。请将 API 密钥存储在环境变量中，而不是硬编码在源文件中。

export INFERENCE_BASE_URL="https://api.luchentech.com/inference/v1"
export INFERENCE_API_KEY="your_api_key_here"
export INFERENCE_MODEL="minimax/minimax-m2.5"

---

第 2 步：发起第一次 API 调用

curl

curl --request POST \
  --url "$INFERENCE_BASE_URL/chat/completions" \
  --header "Authorization: Bearer $INFERENCE_API_KEY" \
  --header "Content-Type: application/json" \
  --data @- <<EOF
{
  "model": "${INFERENCE_MODEL}",
  "messages": [
    {
      "role": "user",
      "content": "How are you?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 128
}
EOF

成功的响应通常如下所示：

{
    "id": "e63095aef9bc4d7292b769edb2cb6583",
    "object": "chat.completion",
    "created": 1773651537,
    "model": "minimax/minimax-m2.5",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hi there! I'm doing well, thank you for asking. How about you? How's your day going so far? Is there anything I can help you with today?",
                "reasoning_content": null,
                "tool_calls": null
            },
            "logprobs": null,
            "finish_reason": "stop",
            "matched_stop": 248046
        }
    ],
    "usage": {
        "prompt_tokens": 15,
        "total_tokens": 692,
        "completion_tokens": 677,
        "prompt_tokens_details": null,
        "reasoning_tokens": 0
    },
    "metadata": {
        "weight_version": "default"
    }
}

Python (OpenAI SDK)

安装 SDK：

pip install openai

然后调用您的服务：

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFERENCE_API_KEY"],
    base_url=os.environ["INFERENCE_BASE_URL"],
)

response = client.chat.completions.create(
    model=os.environ["INFERENCE_MODEL"],
    messages=[
        {"role": "user", "content": "Say hello in Spanish."}
    ],
    temperature=0.7,
    max_tokens=128,
)

print(response.choices[0].message.content)

JavaScript / TypeScript (OpenAI SDK)

安装 SDK：

npm install openai

然后调用您的服务：

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.INFERENCE_API_KEY,
  baseURL: process.env.INFERENCE_BASE_URL,
});

const response = await client.chat.completions.create({
  model: process.env.INFERENCE_MODEL,
  messages: [
    {
      role: "user",
      content: "Say hello in Spanish.",
    },
  ],
  temperature: 0.7,
  max_tokens: 128,
});

console.log(response.choices[0].message.content);