Create video generation

curl --request POST \
  --url https://api.infery.ai/v1/videos/generations \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "n": 1,
  "image_url": "<string>",
  "video_url": "<string>",
  "audio_url": "<string>",
  "person_generation": "allow_all",
  "style": "<string>"
}
'

import requests

url = "https://api.infery.ai/v1/videos/generations"

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "n": 1,
    "image_url": "<string>",
    "video_url": "<string>",
    "audio_url": "<string>",
    "person_generation": "allow_all",
    "style": "<string>"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    n: 1,
    image_url: '<string>',
    video_url: '<string>',
    audio_url: '<string>',
    person_generation: 'allow_all',
    style: '<string>'
  })
};

fetch('https://api.infery.ai/v1/videos/generations', 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.infery.ai/v1/videos/generations",
  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([
    'model' => '<string>',
    'prompt' => '<string>',
    'duration' => 123,
    'resolution' => '<string>',
    'aspect_ratio' => '<string>',
    'n' => 1,
    'image_url' => '<string>',
    'video_url' => '<string>',
    'audio_url' => '<string>',
    'person_generation' => 'allow_all',
    'style' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	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.infery.ai/v1/videos/generations")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/videos/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "0f9c3b1e-6d2a-4c17-9f83-2b5e7a41c8d0",
  "status": "queued",
  "progress": 0,
  "created": 1713204900,
  "model": "veo-3.1-fast"
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

POST

videos

generations

Create video generation

curl --request POST \
  --url https://api.infery.ai/v1/videos/generations \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "n": 1,
  "image_url": "<string>",
  "video_url": "<string>",
  "audio_url": "<string>",
  "person_generation": "allow_all",
  "style": "<string>"
}
'

import requests

url = "https://api.infery.ai/v1/videos/generations"

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "n": 1,
    "image_url": "<string>",
    "video_url": "<string>",
    "audio_url": "<string>",
    "person_generation": "allow_all",
    "style": "<string>"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    n: 1,
    image_url: '<string>',
    video_url: '<string>',
    audio_url: '<string>',
    person_generation: 'allow_all',
    style: '<string>'
  })
};

fetch('https://api.infery.ai/v1/videos/generations', 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.infery.ai/v1/videos/generations",
  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([
    'model' => '<string>',
    'prompt' => '<string>',
    'duration' => 123,
    'resolution' => '<string>',
    'aspect_ratio' => '<string>',
    'n' => 1,
    'image_url' => '<string>',
    'video_url' => '<string>',
    'audio_url' => '<string>',
    'person_generation' => 'allow_all',
    'style' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	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.infery.ai/v1/videos/generations")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/videos/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"n\": 1,\n  \"image_url\": \"<string>\",\n  \"video_url\": \"<string>\",\n  \"audio_url\": \"<string>\",\n  \"person_generation\": \"allow_all\",\n  \"style\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "0f9c3b1e-6d2a-4c17-9f83-2b5e7a41c8d0",
  "status": "queued",
  "progress": 0,
  "created": 1713204900,
  "model": "veo-3.1-fast"
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

Video generation is asynchronous. Submit → receive the job id → poll the status endpoint until complete.

Submit a job

curl https://api.infery.ai/v1/videos/generations \
  -H "Authorization: Bearer $INFERY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1-fast",
    "prompt": "A cat surfing on a banana at sunset, cinematic",
    "duration": 4,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

Response:

{
  "id": "0f9c3b1e-6d2a-4c17-9f83-2b5e7a41c8d0",
  "status": "queued",
  "progress": 0,
  "created": 1713204900,
  "model": "veo-3.1-fast"
}

The job handle is id (a UUID), not job_id, and the timestamp is created, not created_at. The duration field is duration; duration_seconds is not recognised and an unrecognised key is ignored rather than refused, so the model’s default duration is rendered and billed instead.

Image-to-video

Pass a reference image via image_url. There is no inline-base64 field on this endpoint:

{
  "model": "veo-3.1-fast",
  "prompt": "Animate this photo with gentle camera pan",
  "image_url": "https://cdn.example.com/source.jpg"
}

The URL is fetched anonymously, so it must be publicly reachable, and it is SSRF-checked before anything is billed.

Supported models

Google Veo (3 and 2), OpenAI Sora, xAI (Grok Video), Alibaba Wan. See Models catalog.

Storage

The result.url of a completed job is the upstream provider’s URL and expires with it — usually within an hour. Video jobs write no copy into workspace storage and return no file_id. Download the clip as soon as the job completes, and upload it through POST /v1/files if you need a durable handle.

Authorizations

Authorization

string

header

required

API key in format: Bearer inf_***

Body

application/json

model

string

required

Model ID to use for generation

prompt

string

required

Text prompt describing the video to generate

duration

number

Duration in seconds (model-specific, see /v1/models)

resolution

string

Video resolution (model-specific, see /v1/models)

aspect_ratio

string

Video aspect ratio (model-specific, see /v1/models)

integer

default:1

Number of videos to generate

image_url

string

Reference image URL for image-to-video

video_url

string

Reference video URL for video-to-video generation (model-specific)

audio_url

string

Reference audio URL for lipsync generation (model-specific)

person_generation

enum<string>

default:allow_all

Person generation policy (Google Veo models)

Available options:

dont_allow,

allow_adult,

allow_all

fps

enum<integer>

Frame rate of the generated clip. Only 24, 30 and 60 are accepted; anything else is refused with 400. Also refused with 400 for a model served directly by Google (the Veo family), which has no frame-rate parameter — omit it there. Where it is accepted it is a billing dimension: the credit hold and the settle are both priced on it.

Available options:

24,

30,

60

style

string

Free-form style hint. Accepted, persisted with the job and carried into the provider request object — but INERT today: no video provider reads it. The FAL mapper forwards only fields the model's own schema declares (and none declares style), and the direct providers build their request bodies field by field without it. Declared because the endpoint takes it, not because it changes the video.

Response

Video generation job submitted. Poll GET /v1/videos/generations/{jobId} until status === "completed".

string

Job ID to poll for status

Example:

"0f9c3b1e-6d2a-4c17-9f83-2b5e7a41c8d0"

status

enum<string>

Available options:

queued,

processing,

completed,

failed

Example:

"queued"

progress

integer

Progress percentage (0-100)

Example:

0

created

integer

Example:

1713204900

model

string

Example:

"veo-3.1-fast"

Overview

Chat Completions

Embeddings

Images

Audio

Video

Music

Files

Models

Capabilities

Workflows

Create video generation

Submit a job

Image-to-video

Supported models

Storage

Authorizations

Body

Response

​Submit a job

​Image-to-video

​Supported models

​Storage

Authorizations

Body

Response

Submit a job

Image-to-video

Supported models

Storage