Gemini 3.1 Flash Image Preview · Edit
整合
模型 id
gemini-3.1-flash-image-preview/edit
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/gemini-3.1-flash-image-preview/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/gemini-3.1-flash-image-preview/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/gemini-3.1-flash-image-preview/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/zh-TW/developers/docs/mcp)
claude mcp add --transport http doitong-models https://vit.doitong.com/api/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "gemini-3.1-flash-image-preview/edit",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
}
透過 Doitong API 呼叫 Gemini 3.1 Flash Image Preview · Edit 模型(gemini-3.1-flash-image-preview/edit)。代理程式文件:https://doitong.com/zh-TW/developers/models/gemini-3.1-flash-image-preview/edit.md
POST https://vit.doitong.com/api/v1/run/gemini-3.1-flash-image-preview/edit?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
如果回應狀態為 "queued" 或 "running",請輪詢 GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20,直到狀態變為 "succeeded";檔案位於 outputs[].url。使用相同主體傳送 POST https://vit.doitong.com/api/v1/quote/gemini-3.1-flash-image-preview/edit,可在執行前取得確切價格。
此請求: $0.08 80 API 點數 在此頁面執行
您的新 API 金鑰。 僅會在此時顯示,且已填入下方的程式碼與 API 金鑰欄位。請妥善保密:切勿將其放入在瀏覽器中執行的程式碼。
建立請求
控制項是根據模型結構描述生成的。變更設定時,程式碼和價格會同步更新。
POST
/run/gemini-3.1-flash-image-preview/edit?wait=20
報價 → $0.08
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/gemini-3.1-flash-image-preview/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/gemini-3.1-flash-image-preview/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/gemini-3.1-flash-image-preview/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "gemini-3.1-flash-image-preview/edit",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
},
"wait_seconds": 20
}
}
}
關於 Gemini 3.1 Flash Image Preview · Edit
使用 `prompt` 編輯影像,並以 `image_urls` 及選用的 `video_url`、`audio_url` 或 `pdf_url` 作為上下文(各自限制為 15MB)。支援 0.5K 到 4K 的 `resolution`、極端長寬比、網路搜尋、`system_prompt` 和 `thinking_level`。回傳 1 到 4 張編輯後的影像。
參數
請傳送標準名稱或原生名稱其中之一,不要同時傳送兩者。 標準名稱
名稱類型
預設值允許值
說明
prompt必填
類型string
≤ 50,000 個字元≥ 3 個字元
編輯圖像的文字指示。
num_images選填
num_outputs
類型integer
預設值1
1 – 4
請求生成的圖像數量。
seed選填
類型integer | null
初始化亂數生成的種子值。
aspect_ratio選填
類型enum
預設值auto
auto21:916:93:24:35:41:14:53:42:39:164:11:48:11:8
輸出圖像長寬比,包括極端選項 4:1、1:4、8:1、1:8。
output_format選填
類型enum
預設值png
jpegpngwebp
生成圖像的檔案格式。
safety_tolerance選填
類型enum
預設值4
123456
設定內容審核容忍度,範圍從限制最少的 6 到最嚴格的 1;1 會封鎖大多數內容。
image_urls選填
images
類型url[] · image
透過 URL 提供圖像編輯或圖像轉圖像生成的來源圖像,除非至少提供另一個輸入:`video_url`、`audio_url` 或 `pdf_url`。
system_prompt選填
類型string
預設值
≤ 50,000 個字元
可選的整個請求適用之角色與輸出風格指引;會以系統指示傳送給 Gemini,或以系統訊息傳送給 OpenAI 相容供應商。值為空白時,不會傳送此指示。
resolution選填
類型enum
預設值1K
0.5K1K2K4K
輸出圖像的解析度。
video_url選填
video
類型url · video
可選的影片內容,可提供 YouTube URL 或指向影片檔案的 http(s)/data URL。YouTube 連結會直接傳給模型而不下載;影片檔案會下載後內嵌傳送,大小上限為 15 MB。
audio_url選填
audio
類型url · audio
透過指向不超過 15 MB 檔案的 http(s) 或 data URL 提供可選的音訊內容。檔案下載後會內嵌傳送。
pdf_url選填
類型string | null
透過指向不超過 15 MB 文件的 http(s) 或 data URL 提供可選的 PDF 內容。文件下載後會內嵌傳送。
limit_generations選填
類型boolean
預設值true
可能在啟用時影響品質的實驗性生成上限。使用 `True` 時,每輪提示限制為 1 次生成,覆寫提示詞中的圖像數量指示,並忽略模型生成的中間圖像。
enable_web_search選填
類型boolean
預設值false
圖像生成的網路搜尋切換,允許模型將線上找到的最新資訊納入圖像。
thinking_level選填
類型enum
minimalhigh
選取 'minimal' 或 'high',以該層級啟用模型思考並將其思考內容納入生成;不設定層級則停用思考。
必填
標準名稱,也可使用
檔案參數接受公開的 https:// URL、最大 10 MB 的 data: URI,或上傳檔案的 file_url。 檔案
輸出
GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "gemini-3.1-flash-image-preview/edit",
"status": "succeeded",
"created_at": "2026-10-20T12:00:00Z",
"started_at": "2026-10-20T12:00:02Z",
"completed_at": "2026-10-20T12:00:09Z",
"queue_position": null,
"cost": {
"credits": 80,
"usd": "0.08",
"charged": 80,
"refunded": 0
},
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
},
"output": {
"images": [
{
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_name": "0-output.jpeg",
"file_size": 1843200,
"width": 1024,
"height": 768
}
],
"description": "string"
},
"outputs": [
{
"type": "image",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_size": 1843200,
"width": 1024,
"height": 768,
"stored": true
}
],
"error": null,
"metrics": {
"inference_seconds": 6.8
},
"urls": {
"self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
您的檔案,由您選擇每個 outputs[].url 都是儲存空間中的副本:可永久保留(按 GB-月計費),或免費保留 7 天;可透過帳戶設定或 ?storage= 設定。
所有模型使用相同結構圖片、影片和音訊皆包含 type、url、content_type、width、height 和 duration。output 是模型自己的結果物件。
輸出欄位
- images
- array of object {url, content_type, file_name, file_size, width, height}編輯產生的圖像。
- description
- string生成圖像附帶的描述。
其他 Gemini 3.1 Flash Image Preview 變體
更多模型:圖像編輯
給 AI 代理程式:此頁面的 Markdown 位於 https://doitong.com/zh-TW/developers/models/gemini-3.1-flash-image-preview/edit.md. 所有模型與指南: https://doitong.com/developers/llms.txt






