Gemini Native /v1beta generateContent — Google Format

Call Gemini via POST /v1beta/models/:generateContent using x-goog-api-key. Supports generateContent and streamGenerateContent actions.

KiosAPI supports Gemini’s native Google API format — use it with the Google GenAI SDK or any client that already targets the Google AI API. You point your existing Google-format requests at KiosAPI’s base URL and authenticate with your KiosAPI key; no other changes to your code are required.

Use camelCase for all parameters (e.g. toolConfig ✅, tool_config ❌). Some parameters may not be recognised when passed in snake_case.

Request

POST https://kiosapi.com/v1beta/models/{model}:{action}

Path Parameters

model · string · required

The Gemini model to call (e.g. gemini-2.5-flash).

action · string · required

The action to perform. Use generateContent for a standard request, or streamGenerateContent?alt=sse for a streaming response.

Headers

Header	Required	Description
Content-Type	Yes	application/json
x-goog-api-key	No*	Your KiosAPI key, e.g. sk-xxx
Authorization	No*	Bearer sk-xxx (alternative to x-goog-api-key)

You can authenticate with either the x-goog-api-key header or Authorization: Bearer. Both are accepted — use whichever your client already supports.

Request Body

contents · array · required

Array of content objects representing the conversation turns.

Show contents properties

contents[].role · string · required

Role of this turn: user or model.

contents[].parts · array · required

Array of part objects making up this turn’s content.

Show parts properties

contents[].parts[].text · string

Text content for this part.

Examples

cURL (Non-Streaming)

curl -X POST "https://kiosapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "How are you?"}
        ]
      }
    ]
  }'

cURL (Streaming)

curl -X POST "https://kiosapi.com/v1beta/models/gemini-2.5-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

import requests

url = "https://kiosapi.com/v1beta/models/gemini-2.5-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 the full parameter reference — including generationConfig, safetySettings, systemInstruction, and toolConfig — see the Gemini official documentation.