2025年Gemini 2.5 Pro API完全免费使用终极指南：3种方法独家解析

curl -X POST \
https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-exp:generateContent \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
  "contents": [{
    "parts": [{
      "text": "你好，请介绍一下自己"
    }]
  }]
}'

curl https://api.laozhang.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
    "model": "gemini-2.5-pro",
    "messages": [
        {"role": "user", "content": "你好，请介绍一下自己"}
    ]
}'

import requests
import json

# 设置API密钥和端点
API_KEY = "your_api_key_here"  # 替换为您在laozhang.ai获取的API密钥
API_URL = "https://api.laozhang.ai/v1/chat/completions"

# 准备请求头和请求体
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

payload = {
    "model": "gemini-2.5-pro",
    "messages": [
        {"role": "user", "content": "请详细介绍一下Gemini 2.5 Pro的主要功能"}
    ]
}

# 发送请求
response = requests.post(API_URL, headers=headers, json=payload)
result = response.json()

# 打印响应结果
print(json.dumps(result, ensure_ascii=False, indent=2))

# 提取AI回复内容
if "choices" in result and len(result["choices"]) > 0:
    ai_response = result["choices"][0]["message"]["content"]
    print("\n=== AI回复 ===\n")
    print(ai_response)
else:
    print("未获取到有效回复")

import requests
import base64

# 图片转base64
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

# 构建多模态请求
image_base64 = encode_image("your_image.jpg")

payload = {
    "model": "gemini-2.5-pro",
    "messages": [
        {
            "role": "user", 
            "content": [
                {"type": "text", "text": "请分析这张图片的内容"},
                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_base64}"}}
            ]
        }
    ]
}

# 发送请求
response = requests.post(API_URL, headers=headers, json=payload)
result = response.json()

# 读取长文档
with open("large_document.txt", "r", encoding="utf-8") as file:
    long_text = file.read()

payload = {
    "model": "gemini-2.5-pro",
    "messages": [
        {"role": "user", "content": f"请总结以下文档内容：\n\n{long_text}"}
    ]
}

payload = {
    "model": "gemini-2.5-pro",
    "messages": [
        {"role": "user", "content": "解决这个数学问题：一个商店以每件120元的价格出售T恤，成本是每件80元。如果商店想要20%的利润率，应该定价多少？"}
    ],
    "response_format": {"type": "thinking"}
}