Gemini (Native Format) - File Analysis

Use Gemini models via native Google format

Gemini (Native Format) - File Analysis

Gemini’s native request format uses the Google API structure. The platform supports both snake_case and camelCase parameter names, but camelCase is recommended for consistency.

Use camelCase for all parameters (e.g. toolConfig ✅, tool_config ❌). Some parameters may not be recognized with snake_case.

Request

Path Parameters

Parameter	Required	Description	Example
model	Yes	Model name	gemini-3.8-flash
action	Yes	Action type	generateContent or streamGenerateContent?alt=sse

Headers

Header	Required	Description
Content-Type	Yes	application/json
x-goog-api-key	No*	sk-xxx (or use Authorization: Bearer sk-xxx)

You can authenticate with either x-goog-api-key header or Authorization: Bearer header.

Request Body

Parameter	Type	Required	Description
contents	array	Yes	Array of content objects
contents[].role	string	Yes	Role: user or model
contents[].parts	array	Yes	Array of part objects
contents[].parts[].text	string	No	Text content

Example Request - Non-streaming

curl -X POST "https://kiosapi.com/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "How are you?"}
        ]
      }
    ]
  }'

Example Request - Streaming

curl -X POST "https://kiosapi.com/v1beta/models/gemini-3.8-flash:streamGenerateContent?alt=sse" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "How are you?"}
        ]
      }
    ]
  }'

Python Example

import requests

url = "https://kiosapi.com/v1beta/models/gemini-3.8-flash:generateContent"
headers = {
    "Content-Type": "application/json",
    "x-goog-api-key": "sk-xxx"
}
data = {
    "contents": [
        {
            "role": "user",
            "parts": [{"text": "How are you?"}]
        }
    ]
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(result["choices"][0]["message"]["content"])

Response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1724972230,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm doing well, thank you for asking! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 15,
    "total_tokens": 20
  }
}

For full parameter details and usage examples, see the Gemini official documentation.