Gemini-3.1-Flash Official 画像生成
Generate images using Google Gemini 3.1 Flash official direct-connect model with thinking mode and extreme aspect ratios
中国本土のユーザー向け: 中国本土のユーザーは https://toapis.cn を API エンドポイント(Base URL)としてご利用ください。本ドキュメント内の例では https://toapis.com を https://toapis.cn に置き換えてください。
- Direct connection to Google Vertex AI using the Gemini 3.1 Flash Image native API
- Select the
gemini-3.1-flash-image-officialmodel via the model parameter - Supports text-to-image and image-to-image generation
- Supports native generation parameters like temperature, topP, and maxOutputTokens
- Supports resolution (1K/2K/4K), personGeneration, and imageOutputOptions image configuration
- Supports thinkingConfig thinking mode for improved complex scene generation
- Supports safetySettings for content safety control
- Supports extreme aspect ratios (4:1, 8:1)
- Asynchronous task management with task ID for result querying
Important Change: For better performance and cost control, we no longer support passing base64 image data directly in image_urls. Please use the Upload Image endpoint to upload images first, then use the returned URL in this API.
Authorizations
Authorizationstringヘッダー必須All endpoints require Bearer Token authentication
Get API Key: Visit the API Key Management page to obtain your API Key
Add to request headers:
Authorization: Bearer YOUR_API_KEYBody
modelstringボディ必須デフォルト: gemini-3.1-flash-image-officialImage generation model name
Example: "gemini-3.1-flash-image-official"
promptstringボディ必須Text description for image generation
sizestringボディImage aspect ratio
Supported formats:
1:1- Square3:2/2:33:4/4:34:5/5:49:16/16:921:94:1/8:1- Extreme widescreen ratios
nintegerボディデフォルト: 1Number of images to generate
Fixed at 1
image_urlsstring[]ボディReference image URL array for image-to-image generation or editing
⚠️ Only URL format is supported (base64 is no longer supported)
- Publicly accessible image URLs (http:// or https://)
- Use the Upload Image endpoint to upload local images and get URLs
Limits:
- Maximum 14 images
- Maximum file size per image: 10MB
- Supported formats: .jpeg, .jpg, .png, .webp
metadataobjectボディVertex AI native extension parameters
Show metadata fields
temperaturenumberボディGeneration temperature, controls output randomness
Range: 0.0 - 2.0, default 1.0
topPnumberボディTop-P sampling parameter
Range: 0.0 - 1.0, default 0.95
maxOutputTokensintegerボディMaximum output tokens
Default 32768
resolutionstringボディOutput image resolution, automatically mapped to Vertex AI native imageSize
Options: 1K, 2K, 4K, default 1K
groundingstringボディデフォルト: noneGoogle 検索によるグラウンディング。有効にすると、モデルは生成前に Google を検索し、結果の grounding_metadata に引用元が含まれる場合があります。
オプション:
none- 無効(デフォルト)web- ウェブ検索image- 画像検索web_image- ウェブ+画像検索
実際に実行された検索クエリごとに課金され、$0.014/クエリです。リクエスト送信時に最大 4 クエリ分のデポジットが予約され、未使用分は決済時に返金されます。
personGenerationstringボディPerson generation control
Options:
ALLOW_ALL- Allow generating all people (including adults and children)ALLOW_ADULT- Allow generating adults onlyALLOW_NONE- Disallow generating people
imageOutputOptionsobjectボディImage output format configuration
imageOutputOptions fields
mimeTypestringボディOutput image format
Options: image/png, image/jpeg, image/webp
compressionQualityintegerボディCompression quality (JPEG only)
thinkingConfigobjectボディThinking mode configuration. When enabled, the model reasons before generating images, improving results for complex scenes
thinkingConfig fields
thinkingBudgetintegerボディThinking token budget, controls the depth of model reasoning
Range: 0 - 24576, default is determined by the model
thinkingLevelstringボディThinking level
Options: LOW, MEDIUM, HIGH, MINIMAL
safetySettingsarrayボディSafety settings array for content safety filtering
safetySettings elements
categorystringボディSafety category
Options: HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HARASSMENT
thresholdstringボディFiltering threshold
Options: OFF, BLOCK_LOW_AND_ABOVE, BLOCK_MEDIUM_AND_ABOVE, BLOCK_ONLY_HIGH
レスポンス
idstringUnique task identifier for querying task status
objectstringObject type, always generation.task
modelstringモデル name used
statusstringTask status
queued- Queued for processingin_progress- Processingcompleted- Successfully completedfailed- Failed
progressintegerTask progress percentage (0-100)
created_atintegerTask creation timestamp (Unix timestamp)
metadataobjectTask metadata
リクエスト例
curl --request POST \
--url https://toapis.com/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gemini-3.1-flash-image-official",
"prompt": "An ink wash painting of mountains and rivers, layered peaks with swirling mist",
"size": "16:9",
"n": 1,
"metadata": {
"temperature": 1.0,
"topP": 0.95,
"resolution": "1K",
"personGeneration": "ALLOW_ALL",
"thinkingConfig": {
"thinkingLevel": "HIGH"
}
}
}'import requests
response = requests.post(
"https://toapis.com/v1/images/generations",
headers={
"Authorization": "Bearer your-ToAPIs-key",
"Content-Type": "application/json"
},
json={
"model": "gemini-3.1-flash-image-official",
"prompt": "An ink wash painting of mountains and rivers, layered peaks with swirling mist",
"size": "16:9",
"n": 1,
"metadata": {
"temperature": 1.0,
"topP": 0.95,
"resolution": "1K",
"personGeneration": "ALLOW_ALL",
"thinkingConfig": {
"thinkingLevel": "HIGH"
}
}
}
)
task = response.json()
print(f"Task ID: {task['id']}")
print(f"Status: {task['status']}")const response = await fetch('https://toapis.com/v1/images/generations', {
method: 'POST',
headers: {
'Authorization': 'Bearer your-ToAPIs-key',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'gemini-3.1-flash-image-official',
prompt: 'An ink wash painting of mountains and rivers, layered peaks with swirling mist',
size: '16:9',
n: 1,
metadata: {
temperature: 1.0,
topP: 0.95,
resolution: '1K',
personGeneration: 'ALLOW_ALL',
thinkingConfig: {
thinkingLevel: 'HIGH'
}
}
})
});
const task = await response.json();
console.log(`Task ID: ${task.id}`);
console.log(`Status: ${task.status}`);レスポンス例
{
"id": "task_img_abc123def456",
"object": "generation.task",
"model": "gemini-3.1-flash-image-official",
"status": "queued",
"progress": 0,
"created_at": 1703884800,
"metadata": {}
}