Sora 2

Overview

Sora 2 is an OpenAI video model for text-to-video and single-image-to-video workflows. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`sora-2`
Modes	`text-to-video`, `image-to-video`
Prompt length	1-10000 characters
Reference images	Exactly 1 URL for `image-to-video`
Aspect ratios	`landscape`, `portrait`
Durations	`4`, `8`, `12` seconds
Output format	MP4 video URLs

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/sora-2`	Submit a generation task
`GET`	`/statusTask/sora-2?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/sora-2" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic flyover of a futuristic city at sunrise, golden hour lighting, slow camera movement",
      "duration": 12,
      "aspect_ratio": "landscape"
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/sora-2?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://r2.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965932317,
    "costTime": 321388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "SensitiveContentDetected",
    "failMsg": "Your content was flagged by OpenAI as violating content policies.",
    "createTime": 1767965610929,
    "completeTime": 1767965630132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a slow aerial shot over a futuristic coastal city at sunset",
    "duration": 12,
    "aspect_ratio": "landscape",
    "remove_watermark": true
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "animate this portrait with a smooth camera push-in and soft cinematic lighting",
    "image_urls": [
      "https://example.com/source.jpg"
    ],
    "duration": 8,
    "aspect_ratio": "portrait",
    "remove_watermark": true
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input

object

required

Sora 2 input parameters.

Show properties

mode

string

required

Generation mode. Supported values: text-to-video, image-to-video.

prompt

string

required

Text prompt describing the desired video. Supports 1-10000 characters.

duration

integer

required

Output video duration in seconds. Supported values: 4, 8, 12.

image_urls

string[]

Reference image URLs. Required for image-to-video. Must contain exactly 1 public image URL.

aspect_ratio

string

default:"landscape"

Output aspect ratio. Supported values: landscape, portrait.

remove_watermark

boolean

default:"true"

Whether to request watermark removal when the selected route supports it.

Response format

Submit task response

POST /generateTask/sora-2 returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: pending, processing, success, or failed.

resultJson

string

JSON string containing generated video URLs. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds. Present after successful completion.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/sora-2" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "image-to-video",
      "prompt": "extend this scene into a gentle handheld camera move with realistic ambient motion",
      "image_urls": [
        "https://example.com/source.jpg"
      ],
      "duration": 8,
      "aspect_ratio": "portrait"
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Sora 2 is billed by generated video duration. The current public APIXO price on the pricing page is $0.09 / second.

Duration	APIXO price
`4` seconds	`$0.36 / video`
`8` seconds	`$0.72 / video`
`12` seconds	`$1.08 / video`

For current route and market comparison pricing, see Pricing.

Latency and polling

Actual latency may vary by prompt complexity, selected route, input image availability, and current queue load.

Duration	Typical generation time	Recommended first poll	Poll interval
`4` seconds	2-4 minutes	120s after task creation	10s
`8` seconds	3-5 minutes	180s after task creation	10s
`12` seconds	4-6 minutes	180s after task creation	10s

For production video workloads, use callback mode to avoid frequent polling while long-running tasks are queued or rendering.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, mode, parameter, prompt, or image URL shape	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance before retrying
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unmapped upstream failure	Retry with backoff
`502`	Upstream service error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Failure codes can vary by selected route. Common values include:

Fail code	Meaning	What to do
`PromptInvalid`	Prompt was rejected or malformed	Rewrite the prompt and retry
`SensitiveContent`	Prompt or media failed safety checks	Change the prompt or input image
`SensitiveContentDetected`	Upstream flagged generated or input content	Change the prompt or input image
`InputImageSensitiveContentDetected`	Reference image failed safety checks	Use a different public image URL
`ImageFormatIncorrect`	Reference image format could not be processed	Use a direct JPG, PNG, or WebP image URL
`InvalidImageSize`	Reference image dimensions or size are invalid	Resize or compress the image
`RateLimited`	Upstream route was rate limited	Retry with exponential backoff
`Timeout`	Generation did not finish in time	Retry, reduce prompt complexity, or use callback mode
`Unknown error`	Upstream returned an unmapped failure	Retry with backoff or contact support with the `taskId`

See Error Codes for the full error reference.

Getting Started

Image Models

Video Models

Audio Models

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Getting Started

Image Models

Video Models

Audio Models

Documentation Index

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Related links