Skip to main content

​
接口概览

Gemini 提供两种调用方式：
方式路径适用场景
OpenAI 兼容/v1/chat/completions推荐，便于多云切换
原生接口/v1beta/models/{model}:generateContent需要 Gemini 特有功能
所有接口统一使用 Authorization: Bearer <Token> 认证。
推荐使用 OpenAI 兼容接口，代码可在不同模型供应商间无缝切换。

​
快速开始

​
OpenAI 兼容方式（推荐）

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "system", "content": "你是一个友好的助手"},
      {"role": "user", "content": "你好"}
    ]
  }'

​
原生接口方式

curl -X POST "$BASE_URL/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{"text": "你好"}]
    }]
  }'

​
流式输出

​
OpenAI 兼容

curl -N "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "写一首诗"}],
    "stream": true
  }'

​
原生接口

curl -N "$BASE_URL/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "写一首诗"}]}]
  }'

​
多模态输入

​
图片理解

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "描述这张图片"},
        {"type": "image_url", "image_url": {"url": "data:image/png;base64,<BASE64>"}}
      ]
    }]
  }'

​
音频理解

curl -X POST "$BASE_URL/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "转写这段音频"},
        {"inline_data": {"mime_type": "audio/mp3", "data": "<BASE64>"}}
      ]
      }]
    }'

​
视频分析（gemini-3-pro-preview-file）

gemini-3-pro-preview-file 模型支持通过 URL 直接分析视频文件。详细用法请参阅 视频分析 文档。

​
思考模式（Reasoning）

Gemini 2.5 和 3 系列支持思考推理能力。

​
OpenAI 兼容方式

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "逐步推理 23*47 的结果"}],
    "reasoning_effort": "medium"
  }'
reasoning_effort 可选值：low、medium、high

​
原生接口方式

Gemini 3 系列使用 thinkingLevel： 
{
  "generationConfig": {
    "thinkingConfig": {
      "thinkingLevel": "high"
    }
  }
}
Gemini 2.5 系列使用 thinkingBudget： 
{
  "generationConfig": {
    "thinkingConfig": {
      "thinkingBudget": 8192
    }
  }
}

​
返回思考过程

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "解释量子纠缠"}],
    "reasoning_effort": "high",
    "extra_body": {
      "google": {
        "thinking_config": {"include_thoughts": true}
      }
    }
  }'
思考内容会在响应的 reasoning_content 字段中返回。

​
工具调用

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "北京今天天气怎么样？"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "获取城市天气",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string", "description": "城市名"}
          },
          "required": ["city"]
        }
      }
    }]
  }'

​
JSON 模式

curl -X POST "$BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "生成一个用户信息 JSON"}],
    "response_format": {"type": "json_object"}
  }'

​
生成参数

参数说明默认值
temperature随机性，0-21.0
max_tokens最大输出 token 数模型默认
top_p核采样概率0.95
stop停止序列-
Gemini 3 建议保持 temperature 为 1.0，过低可能导致推理性能下降。

​
SDK 示例

​
Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-token",
    base_url="https://models.kapon.cloud/v1"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "你好"}]
)
print(response.choices[0].message.content)

​
Python (Google SDK)

from google import genai

client = genai.Client(
    api_key="your-token",
    http_options={"base_url": "https://models.kapon.cloud"}
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="你好"
)
print(response.text)