Create video (Omni and Veo formats)
curl --request POST \
--url https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"instances": [
{
"prompt": "A cinematic aerial shot of a modern city at sunrise",
"referenceImages": [
{
"image": {
"inlineData": {
"mimeType": "image/png",
"data": "BASE64_IMAGE_DATA"
}
},
"referenceType": "asset"
}
]
}
],
"parameters": {
"aspectRatio": "16:9",
"durationSeconds": 5,
"resolution": "720p"
}
}
'import requests
url = "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning"
payload = {
"instances": [
{
"prompt": "A cinematic aerial shot of a modern city at sunrise",
"referenceImages": [
{
"image": { "inlineData": {
"mimeType": "image/png",
"data": "BASE64_IMAGE_DATA"
} },
"referenceType": "asset"
}
]
}
],
"parameters": {
"aspectRatio": "16:9",
"durationSeconds": 5,
"resolution": "720p"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
instances: [
{
prompt: 'A cinematic aerial shot of a modern city at sunrise',
referenceImages: [
{
image: {inlineData: {mimeType: 'image/png', data: 'BASE64_IMAGE_DATA'}},
referenceType: 'asset'
}
]
}
],
parameters: {aspectRatio: '16:9', durationSeconds: 5, resolution: '720p'}
})
};
fetch('https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'instances' => [
[
'prompt' => 'A cinematic aerial shot of a modern city at sunrise',
'referenceImages' => [
[
'image' => [
'inlineData' => [
'mimeType' => 'image/png',
'data' => 'BASE64_IMAGE_DATA'
]
],
'referenceType' => 'asset'
]
]
]
],
'parameters' => [
'aspectRatio' => '16:9',
'durationSeconds' => 5,
'resolution' => '720p'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning"
payload := strings.NewReader("{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}"
response = http.request(request)
puts response.read_body{
"name": "models/veo3.1-fast/operations/abc123"
}Video generation Omni and Veo formats
Create video (Omni and Veo formats)
This series supports OpenAI video generation formats (see the link Video generation Sora compatible formats).
This API topic page explains the video formats related to Omni and Veo, as well as the current gateway support status for the native Veo format.
For external use of the current Veo series, please use OpenAI Sora compatibility mode: POST /v1/videos.
The reserved path for Google native mode is: POST /v1beta/models/{model}:predictLongRunning. The current gateway is not yet connected to the native task dispatch pipeline of Veo, so calls using the native [[TERM_1]] request body are not yet supported.
Note: The endpoints supported by the gemini-omni model are the Sora compatible format POST /v1/videos or the Seedance format POST /api/v3/contents/generations/tasks; this page does not support Google native Veo predictLongRunning endpoints.
POST
/
v1beta
/
models
/
{model}
:predictLongRunning
Create video (Omni and Veo formats)
curl --request POST \
--url https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"instances": [
{
"prompt": "A cinematic aerial shot of a modern city at sunrise",
"referenceImages": [
{
"image": {
"inlineData": {
"mimeType": "image/png",
"data": "BASE64_IMAGE_DATA"
}
},
"referenceType": "asset"
}
]
}
],
"parameters": {
"aspectRatio": "16:9",
"durationSeconds": 5,
"resolution": "720p"
}
}
'import requests
url = "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning"
payload = {
"instances": [
{
"prompt": "A cinematic aerial shot of a modern city at sunrise",
"referenceImages": [
{
"image": { "inlineData": {
"mimeType": "image/png",
"data": "BASE64_IMAGE_DATA"
} },
"referenceType": "asset"
}
]
}
],
"parameters": {
"aspectRatio": "16:9",
"durationSeconds": 5,
"resolution": "720p"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
instances: [
{
prompt: 'A cinematic aerial shot of a modern city at sunrise',
referenceImages: [
{
image: {inlineData: {mimeType: 'image/png', data: 'BASE64_IMAGE_DATA'}},
referenceType: 'asset'
}
]
}
],
parameters: {aspectRatio: '16:9', durationSeconds: 5, resolution: '720p'}
})
};
fetch('https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'instances' => [
[
'prompt' => 'A cinematic aerial shot of a modern city at sunrise',
'referenceImages' => [
[
'image' => [
'inlineData' => [
'mimeType' => 'image/png',
'data' => 'BASE64_IMAGE_DATA'
]
],
'referenceType' => 'asset'
]
]
]
],
'parameters' => [
'aspectRatio' => '16:9',
'durationSeconds' => 5,
'resolution' => '720p'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning"
payload := strings.NewReader("{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aiid.edu.kg/v1beta/models/{model}:predictLongRunning")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"instances\": [\n {\n \"prompt\": \"A cinematic aerial shot of a modern city at sunrise\",\n \"referenceImages\": [\n {\n \"image\": {\n \"inlineData\": {\n \"mimeType\": \"image/png\",\n \"data\": \"BASE64_IMAGE_DATA\"\n }\n },\n \"referenceType\": \"asset\"\n }\n ]\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"16:9\",\n \"durationSeconds\": 5,\n \"resolution\": \"720p\"\n }\n}"
response = http.request(request)
puts response.read_body{
"name": "models/veo3.1-fast/operations/abc123"
}Authorizations
Use Bearer Token authentication.
Format: Authorization: Bearer sk-xxxxxx
Path Parameters
Veo Model name.
Available options:
veo3, veo3-fast, veo3-fast-frames, veo3-frames, veo3-pro, veo3-pro-frames, veo3.1, veo3.1-4k, veo3.1-components, veo3.1-fast, veo3.1-pro, veo3.1-pro-4k Example:
"veo3.1-fast"
Body
application/json
Minimum array length:
1Hide child attributes
Hide child attributes
Generate prompt
Example:
"A cinematic aerial shot of a modern city at sunrise"
Optional. 1–3 reference images, using Google native inlineData or file URI structures.
Hide child attributes
Hide child attributes
Example:
"asset"
Response
200 - application/json
Reserved success response structure. Currently provided for protocol documentation only; actual calls are not supported.
The operation name, used for subsequent status queries.
Example:
"models/veo3.1-fast/operations/abc123"