Documentation API gemini-3-pro-image

gemini-3-pro-image

ImagesGoogleNano Banana Progemini-3-pro-image

Ouvrir le Playground Gérer les clés API

谷歌最强大的图像生成模型

Authentification

Base URL: https://api.dreamtoai.com
Authorization: Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
Nom du modèle (model): gemini-3-pro-image

Protocole d'intégration

Pourquoi choisir ce protocole

适合原本使用 Gemini SDK 或 generateContent 接口的用户直接迁移。

URL de l'endpoint

POST/v1beta/models/gemini-3-pro-image:generateContent

Authorization: Bearer YOUR_API_KEYContent-Type: application/json

JSON de requête et de réponse

Exemples de requête

Avec une URL d'imagefileData.fileUri

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "修复键盘顶端斑驳痕迹，其他内容不变"
        },
        {
          "fileData": {
            "fileUri": "https://example.com/reference.png"
          }
        }
      ]
    }
  ],
  "generationConfig": {
    "imageConfig": {
      "imageSize": "1K"
    },
    "responseModalities": [
      "IMAGE"
    ]
  }
}

Avec Base64inlineData.mimeType + inlineData.data

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "修复键盘顶端斑驳痕迹，其他内容不变"
        },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "BASE64_IMAGE_DATA"
          }
        }
      ]
    }
  ],
  "generationConfig": {
    "imageConfig": {
      "imageSize": "1K"
    },
    "responseModalities": [
      "IMAGE"
    ]
  }
}

Exemple de réponse

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8Xw8AAoMBgAqJvhoAAAAASUVORK5CYII="
            }
          }
        ]
      }
    }
  ],
  "modelVersion": "gemini-3-pro-image",
  "usageMetadata": {
    "promptTokenCount": 8,
    "candidatesTokenCount": 16,
    "totalTokenCount": 24
  }
}

Champs de requête et de réponse

Champs de requête

Champ	Type	Obligatoire
contents	array	Y
contents[]	object	Y
contents[].role	string	Y
contents[].parts	array	Y
contents[].parts[]	object	Y
contents[].parts[].text	string	Y
generationConfig	object	Y
generationConfig.imageConfig	object	Y
generationConfig.imageConfig.imageSize	string	Y

Champs de réponse

Champ	Type	Obligatoire
output.images[]	image	N

Exemples de code

cURLrequest.sh

curl -X POST "https://api.dreamtoai.com/v1beta/models/gemini-3-pro-image:generateContent" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "修复键盘顶端斑驳痕迹，其他内容不变"
        },
        {
          "fileData": {
            "fileUri": "https://example.com/reference.png"
          }
        }
      ]
    }
  ],
  "generationConfig": {
    "imageConfig": {
      "imageSize": "1K"
    }
  }
}'

# cURL pour téléverser le fichier de référence
curl -X POST "https://api.dreamtoai.com/v1/files/upload" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "kind=image" \
  -F "purpose=reference" \
  -F "[email protected]"