聊天

POST

/v1beta/models/{model-name}:generateContent

gemini API的使用方式和openai的不同，模型名字要在url中传递，比如：https://api.wenwen-ai.com/v1beta/models/gemini-3-flash-preview:generateContent
令牌选择google分组可支持cache。

请求参数

Path 参数

Header 参数

Body 参数application/json

示例

{
  "contents": [
    {
      "parts": [
        {
          "text": "你好"
        }
      ]
    }
  ],
  "generationConfig": {
    "thinkingConfig": {
      "thinkingLevel": "low"
    }
  }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.wenwen-ai.com/v1beta/models/:generateContent' \
--header 'x-goog-api-key: sk-xxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
  "contents": [
    {
      "parts": [
        {
          "text": "你好"
        }
      ]
    }
  ],
  "generationConfig": {
    "thinkingConfig": {
      "thinkingLevel": "low"
    }
  }
}'

返回响应

🟢200成功

application/json

Body

示例

{'candidates': [
        {'content': {
        'role': 'model', 
        'parts': [
                    {'text': "<think>**Formulating a Response**\n\nI'm currently crafting a friendly and helpful response in Chinese to the user's greeting. I plan to offer assistance and be prepared to switch to English if the user prefers, since that's my native language. I want to ensure the interaction is comfortable and productive.\n\n\n</think>\n\n你好！我能为你做些什么？"
                    }
                ]
            }, 
'finishReason': 'STOP', 
'index': 0, 
'safetyRatings': []
        }
    ], 
'usageMetadata': {'promptTokenCount': 8, 'candidatesTokenCount': 78, 'totalTokenCount': 86, 'thoughtsTokenCount': 0, 'promptTokensDetails': None
    }
}

修改于 2026-03-31 15:06:56

Gemini SDK使用指南

流式返回