Sora 2 Pro

Overview

Sora 2 Pro is an OpenAI video generation model for premium text-to-video and 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-pro`
Modes	`text-to-video`, `image-to-video`
Prompt length	1-5000 characters
Duration	`4`, `8`, or `12` seconds
Text-to-video sizes	`7201280`, `1280720`, `10241792`, `17921024`
Image-to-video resolutions	`720p`, `1080p`
Reference images	1 URL for `image-to-video`
Output format	MP4 video URL in `resultJson.resultUrls`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/sora-2-pro`	Submit a generation task
`GET`	`/statusTask/sora-2-pro?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-pro" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic tracking shot of a futuristic city with flying cars",
      "duration": 4,
      "size": "1280*720"
    }
  }'

Successful response:

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

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

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/sora-2-pro?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/xxx.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965790929,
    "costTime": 180000
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "PromptInvalid",
    "failMsg": "Prompt is invalid or rejected by upstream service",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

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 cinematic tracking shot of a futuristic city with flying cars",
    "duration": 8,
    "size": "1280*720"
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "make this image come alive with subtle camera motion",
    "duration": 4,
    "resolution": "1080p",
    "image_urls": [
      "https://example.com/reference-image.jpg"
    ]
  }
}

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 URL that can receive the final task payload. See Webhooks.

input

object

required

Sora 2 Pro 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 1-5000 characters.

duration

integer

required

Video duration in seconds. Supported values: 4, 8, 12.

size

string

Required for text-to-video. Supported values: 720*1280, 1280*720, 1024*1792, 1792*1024.

resolution

string

Required for image-to-video. Supported values: 720p, 1080p.

image_urls

string[]

Required for image-to-video. Provide exactly 1 publicly accessible reference image URL.

Response format

Submit task response

POST /generateTask/sora-2-pro 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 the 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-pro" \
  -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": "animate the scene with slow cinematic camera movement",
      "duration": 4,
      "resolution": "1080p",
      "image_urls": [
        "https://example.com/reference-image.jpg"
      ]
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Sora 2 Pro is billed per second. The selected output tier determines the per-second unit price, and the final task cost is:

unit price x duration

Output tier	APIXO price
`720p`	`$0.27 / second`
`1080p`	`$0.45 / second`

For text-to-video, 720*1280 and 1280*720 use the 720p tier, while 1024*1792 and 1792*1024 use the 1080p tier. For image-to-video, the resolution value selects the tier directly. For current route and market comparison pricing, see Pricing.

Latency and polling

Video generation usually takes longer than image generation. Actual latency may vary by prompt complexity, selected duration, output tier, route health, and current queue load.

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

For production workloads, use callback mode to avoid frequent polling during long video generations.

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, 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 or switch account/key
`403`	Key or route cannot access the model, or content was rejected	Check permissions and revise the prompt or input
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error	Retry with backoff
`502`	Upstream service error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failures

Symptom	Common cause	What to do
Prompt rejected	Prompt or image content was flagged by safety checks	Revise the prompt or use a different input image
Missing parameter	Required fields are absent for the selected `mode`	Check `duration`, `size`, `resolution`, and `image_urls`
Invalid image	The image URL cannot be fetched or decoded by the upstream service	Use a public direct image URL
Timeout or no progress	The upstream job is slow or temporarily unavailable	Keep polling with backoff, retry later, or use callback mode
Insufficient balance	The account does not have enough balance for the selected duration and tier	Add balance before retrying

Practical checks

prompt must be a non-empty string and must not exceed 5000 characters.
duration is required and must be 4, 8, or 12.
size is required only for text-to-video.
resolution and image_urls are required only for image-to-video.
image_urls must contain exactly 1 image URL. Use JPG, PNG, or WebP when possible, and keep the image under 10 MB to reduce upstream rejections.

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 failures

Practical checks

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 failures

​Practical checks

​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 failures

Practical checks

Related links