Image Editing
gemini-3-1-flash-image-preview Image Editing API
Designed for fast image editing, local inpainting, style transfer, and wide-aspect creative asset revisions.
Authorization
BearerAuth
Model relay interface recognition. Request heading: Autoration: Bearer .
In: header
Path Parameters
Gemini model name.
"gemini-3.1-flash-image-preview"Request Body
application/json
Enter an array of content to carry one or more rounds of messages between users, models or tools. Each element is a Content object, usually consisting of __ FD_PROTECT_0 __ and __ FD_PROTECT_1 __: __ FD_PROTECT_2 __, commonly known as _ FD_PROTECT_3 __, _ FD_PROTECT_4 __, single-cycle user_9 _ with _ FD_PROTECT_10, _ FD_PROTECT_11 __, _ FD_PROTECT_12 __, _ FD_PRT_13 _ _ _ _ _ _FCED_14 Applies to scenarios such as text conversations, image/audio/video/document understanding, function calls and multimodular generation. The number of arrays and media sizes are based on upstream model and operational configuration limits.
Gemini system command.
Generates configurations such as temperature, TopK, TopP, maximum output length.
Security policy settings. List of safetySettings. Scope: An array length is based on upstream or business configuration.
Gemini tool definition. . Scope: The length of arrays and the complexity of schema are based on upstream limits.
Response Body
application/json
curl -X POST "https://api.tokaify.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \ -H "Content-Type: application/json" \ -d '{ "contents": [ { "parts": [ { "text": "Writing a four-word Chinese short poem on the theme of urban night rain." } ] } ], "generationConfig": { "temperature": 0.7, "maxOutputTokens": 100000 } }'{
"candidates": [],
"usageMetadata": {},
"modelVersion": "string"
}Request Parameters
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
contents | array | Yes | None | Gemini content array including edit instructions and the input image. |
contents[].parts[].text | string | Yes | None | Edit instruction. |
contents[].parts[].inline_data | object | Yes | None | Input image containing mime_type and Base64 data. |
generationConfig.responseModalities | string[] | No | ["TEXT","IMAGE"] | Recommended value: ["IMAGE"]. |
generationConfig.imageConfig.aspectRatio | string | No | 1:1 | Supports 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, and 21:9. |
Example Code
curl "https://api.tokaify.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
-H "Authorization: Bearer $TOKAIFY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [{
"role": "user",
"parts": [
{ "text": "Extend the image into a 21:9 banner, keep the main subject on the left, and leave title space on the right." },
{ "inline_data": { "mime_type": "image/png", "data": "BASE64_IMAGE" } }
]
}],
"generationConfig": {
"responseModalities": ["IMAGE"],
"imageConfig": { "aspectRatio": "21:9" }
}
}'import requests
response = requests.post(
"https://api.tokaify.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent",
headers={"Authorization": "Bearer YOUR_TOKAIFY_API_KEY"},
json={
"contents": [{"role": "user", "parts": [
{"text": "Extend the image into a 21:9 banner, keep the main subject on the left, and leave title space on the right."},
{"inline_data": {"mime_type": "image/png", "data": "BASE64_IMAGE"}},
]}],
"generationConfig": {"responseModalities": ["IMAGE"], "imageConfig": {"aspectRatio": "21:9"}},
},
)
print(response.json())const response = await fetch("https://api.tokaify.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.TOKAIFY_API_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({
contents: [{ role: "user", parts: [
{ text: "Extend the image into a 21:9 banner, keep the main subject on the left, and leave title space on the right." },
{ inline_data: { mime_type: "image/png", data: "BASE64_IMAGE" } },
] }],
generationConfig: { responseModalities: ["IMAGE"], imageConfig: { aspectRatio: "21:9" } },
}),
});
console.log(await response.json());Response Example
{
"candidates": [
{
"content": {
"role": "model",
"parts": [{ "inlineData": { "mimeType": "image/png", "data": "iVBORw0KGgoAAAANSUhEUg..." } }]
},
"finishReason": "STOP"
}
]
}Notes
Billing follows the configured model and channel ratios. Extreme aspect-ratio edits may reduce the stability of subject details.
How is this guide?
Last updated on