Text Generation + Thinking - Streaming

Endpoint: POST https://4zapi.com/v1beta/models/gemini-3.8-flash:streamGenerateContent

Official documentation: https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn#multi-turn-conversations

Parameters

• key (query, string, required)
• alt (query, string)
• Content-Type (header, string, required)

Request body (application/json)

• contents (array<object>, required)

Request example

{
  "contents": [
    {
      "parts": [
        {
          "text": "1+2+3+4+5+....+999?"
        }
      ],
      "role": "user"
    }
  ],
  "generationConfig": {
    "temperature": 1,
    "thinkingConfig": {
      "includeThoughts": true,
      "thinkingBudget": 26240
    },
    "topP": 1
  },
  "safetySettings": [
    {
      "category": "HARM_CATEGORY_HATE_SPEECH",
      "threshold": "OFF"
    },
    {
      "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
      "threshold": "OFF"
    },
    {
      "category": "HARM_CATEGORY_HARASSMENT",
      "threshold": "OFF"
    },
    {
      "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
      "threshold": "OFF"
    },
    {
      "category": "HARM_CATEGORY_CIVIC_INTEGRITY",
      "threshold": "BLOCK_NONE"
    }
  ],
  "systemInstruction": {
    "parts": [
      {
        "text": "hi"
      }
    ],
    "role": "user"
  },
  "tools": []
}