gemini-3-pro-image-preview

POST

/v1beta/models/{model}:generateContent//gemini-3-pro-image-preview

Gemini 3 Pro Image Preview彻底改变了AI图像生成的格局。这款被内部称为"Nano Banana Pro"的模型，首次将大语言模型的推理能力与图像生成深度融合，实现了此前难以想象的功能组合：原生4K分辨率输出、几乎完美的多语言文字渲染、基于Google搜索的实时数据锚定，以及真正的多轮对话式图像编辑。对于每天需要生成数百甚至数千张图片的开发团队和企业来说，选择正确的图像生成模型直接影响产品质量、开发效率和运营成本。

Actual API Endpoint: POST https://refreshing-gratitude-production.up.railway.app/v1beta/models/{model}:generateContent/

Model Code: gemini-3-pro-image-preview

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Path Params

Body Params application/jsonRequired

Examples

Responses

🟢200

application/json

Request successful

Body

🟠401

🟠429

🔴500

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST '/v1beta/models/gemini-3-pro-image-preview:generateContent//gemini-3-pro-image-preview' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "draw a cat"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "TEXT",
            "IMAGE"
        ],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "2k"
        }
    }
}'

Response Example

{
    "candidates": [
        {
            "content": {
                "role": "string",
                "parts": [
                    {}
                ]
            },
            "finishReason": "string",
            "safetyRatings": [
                {}
            ]
        }
    ],
    "usageMetadata": {
        "promptTokenCount": 0,
        "candidatesTokenCount": 0,
        "totalTokenCount": 0
    }
}

Modified at 2026-03-23 18:04:25

gemini-2.5-flash-image

gemini-3.1-flash-image-preview