Native Gemini Format Image Generation

POST

/v1beta/models/{model}:generateContent

Gemini Native (Image)

Invoke the AboAI API using the Google Gemini native format

Introduction

The Gemini Native API utilizes Google Gemini's request and response formats, making it suitable for official Google clients (such as the google-generativeai SDK) or scenarios that require direct use of Gemini data structures. This interface complies with the Gemini API specifications and fully supports features such as Thinking mode, multimodal input, tool calling, Google Search (Grounding), and image generation.

API Endpoints

Feature	Method	Path
Content Generation (Non-streaming)	POST	`/v1beta/models/{model}:generateContent`

Authentication

Supports either of the following methods:

Header Parameter	Type	Description
`Authorization`	string	Bearer Token: `Bearer sk-xxxxxxxxxx` (Recommended, consistent with other AboAI interfaces)
`x-goog-api-key`	string	Google-style API Key: `x-goog-api-key: sk-xxxxxxxxxx`

You can also pass the parameter via the URL: ?key=sk-xxxxxxxxxx.

请求参数

Authorization

API Key

在 header 添加参数

x-goog-api-key

示例：

x-goog-api-key: ********************

Path 参数

Query 参数

Header 参数

Body 参数application/json

示例

{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Generate a picture of a cute cartoon cat"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "imageSize": "1k",
            "aspectRatio": "16:9"
        },
        "maxOutputTokens": 4096
    }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.peakkai.ai/v1beta/models/gemini-2.5-flash-image:generateContent?key=undefined' \
--header 'Authorization;' \
--header 'x-goog-api-key: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Generate a picture of a cute cartoon cat"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "imageSize": "1k",
            "aspectRatio": "16:9"
        },
        "maxOutputTokens": 4096
    }
}'

返回响应

🟢200

application/json

Bodyapplication/json

示例

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Response text\n"
          },
          {
            "inlineData": {
              "data": "",
              "mimeType": "image/png"
            }
          }
        ],
        "role": "model"
      },
      "index": 0,
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": integer,
    "candidatesTokenCount": integer,
    "totalTokenCount": integer,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": integer
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": integer
      },
      {
        "modality": "TEXT",
        "tokenCount": integer
      }
    ]
  },
  "modelVersion": "gemini-2.5-flash-image",
  "responseId": "sXvYaYm-IqjZ8eEP6fv1oAI"
}

修改于 2026-11-02 09:46:28

Native OpenAI Format Image Editing (Multipart)

Create Video Generation Task

Native Gemini Format Image Generation

Gemini Native (Image)#

Introduction#

API Endpoints#