Sora 2 Pro API

Build with the Sora 2 Pro API through EvoLink to generate short clips from text or an input image. OpenAI lists per-second pricing and resolution tiers for sora-2-pro, and the Sora 2 Pro API lets an image reference act as the first frame when you need brand consistency.

Prompt

A cinematic shot of a futuristic cityscape at night, with flying vehicles weaving between neon-lit skyscrapers. The camera sweeps through the scene, revealing intricate details of the architecture and dynamic lighting.

Parameters

aspect_ratio

16:9

duration

quality

high

remove_watermark

true

Estimated Cost

46 Credits

Sample Result

Prompt

218 (suggested: 2,000)

Input Images

Upload reference images

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 10

Aspect Ratio

Duration

Quality

Remove Watermark

0:00 / 0:00

Audio

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Sora 2 Pro API for text-to-video and image-to-video production

Create short cinematic clips with the Sora 2 Pro API using 4, 8, or 12-second presets and sizes like 720x1280, 1280x720, 1024x1792, or 1792x1024. Using the Sora 2 Pro API, add an optional image reference to lock in the first frame, then route jobs through EvoLink for stable access.

Studio scene showcase of video generation feature 1

What can you build with the Sora 2 Pro API?

Image-to-Video Brand Shots

Use the Sora 2 Pro API to animate a key visual, product still, or brand scene. By starting from an image reference, you can preserve the look of a campaign while adding motion for hero sections, app openers, and premium landing pages.

View documentation

Text-to-Video Storyboards

Turn a script or creative brief into short storyboards with the Sora 2 Pro API. Use repeatable prompts, keep shots to 4, 8, or 12 seconds, and estimate costs using per-second pricing so creative teams can iterate with confidence.

See examples

Storyboard showcase of video generation feature 3

Ads and Social Variants

Produce ad variations for different placements with the Sora 2 Pro API. Choose vertical or horizontal sizes, keep prompts aligned with your brand tone, and generate multiple versions quickly so performance teams can test hooks and messages across channels.

Check pricing

Social ad showcase of video generation feature 4

Why EvoLink + Sora 2 Pro

Short-form video generation with clear inputs, outputs, and published tiers.

Text + Image Inputs

Sora 2 Pro accepts text or image inputs and outputs video with synced audio, so teams can anchor a brand image and keep motion consistent across variations.

Published Tiers

OpenAI lists per-second pricing plus size tiers like 720x1280, 1280x720, 1024x1792, and 1792x1024, so you can map cost to duration and resolution.

Safety & Provenance

Sora’s system card documents moderation filters, output classifiers, and provenance signals such as metadata and watermarks, helping teams align internal review and responsible-use policies.

How to integrate the Sora 2 Pro API

Send a prompt, optionally add an image reference, then fetch the finished MP4 using standard async workflows.

Step 1 — Select Model and Format

Choose `sora-2-pro`, then set size (for example 1280x720) and a 4, 8, or 12-second duration.

Step 2 — Add Text and Image Input

Write a clear scene prompt and attach an image reference if you want the first frame to match a brand asset.

Step 3 — Retrieve the MP4

Poll job status or listen for a webhook, then download the final video with synced audio output.

Open API Playground

Sora 2 Pro API Capabilities

Practical Sora 2 Pro API controls for consistent, on-brand video generation.

Inputs

Text + Image Inputs

The Sora 2 Pro API accepts natural language or image input, so teams can start from a prompt or an existing visual.

Branding

First-Frame Image Reference

Attach an image reference to guide the first frame and preserve the look of a product or campaign scene.

Timing

Duration Presets

The video API lists 4, 8, and 12-second clip options, which are ideal for short-form ads and loops.

Quality

Resolution Tiers

OpenAI lists 720x1280, 1280x720, 1024x1792, and 1792x1024 sizes, giving a clear quality ladder.

Budgeting

Per-Second Pricing

Sora 2 Pro API pricing is published per second, with separate rates for standard and higher-resolution tiers.

Audio

Synced Audio Output

The model is positioned for synced-audio video generation, supporting sound alongside visuals.

Sora 2 Pro API - Frequently Asked Questions

Everything you need to know about the product and billing.

Sora 2 is OpenAI's video generation model that can create clips from natural language or images. Sora 2 Pro is the higher-tier option that keeps the same input types and adds higher resolution tiers with per-second pricing. If you want image-to-video, the Sora 2 Pro API supports image input and lets the reference image act as the first frame for consistent visuals.

The Sora 2 Pro API accepts an optional image reference that acts as the first frame. You attach the image as an input reference when you call the /v1/videos endpoint, and the file should match the target size. OpenAI lists supported formats such as JPEG, PNG, and WebP, so you can start from a brand still or concept image and animate it into a clip.

OpenAI lists four sizes for Sora 2 Pro: 720x1280, 1280x720, 1024x1792, and 1792x1024. These cover portrait and landscape layouts and provide a higher tier for more detailed outputs. Choose the size that fits your placement and budget, and verify availability in your account before launching large runs.

The Sora 2 Pro API lists 4, 8, and 12-second duration options in the video endpoint. Short presets are useful for ads, app loops, and social placements, while multiple clips can be stitched in post if you need longer sequences. This makes planning straightforward because duration directly affects per-second costs.

OpenAI publishes per-second pricing for the Sora Video API. For Sora 2 Pro, standard sizes are listed at $0.30 per second, while higher-resolution sizes are listed at $0.50 per second. Sora 2 (base) is listed at $0.10 per second. Use these published rates to estimate costs by clip length before you scale production.

Yes. Sora 2 Pro is described by OpenAI as a synced-audio video generation model, and the model lists audio as an output modality. In practice this means you can prompt for dialogue or ambience when appropriate and expect audio alongside the video output. Always verify output behavior in your account for your chosen model and size.

It is a strong fit for ads, product launches, and premium brand visuals because it supports image-to-video and short, repeatable formats. Many teams start with a brand keyframe, then generate a set of variations to test performance. Combine that with per-second pricing and listed sizes to keep campaigns predictable and scalable.

OpenAI's API reference lists the video generation endpoint as POST /v1/videos, and the allowed model values include sora-2 and sora-2-pro. Your request includes a prompt and optional input reference, plus seconds and size. EvoLink routes the request while keeping the model name consistent with OpenAI's API.

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/videos/generations

Create Video

Sora 2 Pro (sora-2-pro) model supports text-to-video, image-to-video and other modes.

Asynchronous processing mode, use the returned task ID to .

Generated video links are valid for 24 hours, please save them promptly.

Important Notes

Currently Sora2's content moderation mechanism is very strict, tasks may fail due to this.
Image input containing real human figures is not currently supported.

Request Parameters

modelstringRequiredDefault: sora-2-pro

Video generation model name.

Examplesora-2-pro

promptstringRequired

Prompt describing what kind of video to generate.

Notes

Limited to 5000 tokens

ExampleA cat playing piano

aspect_ratiostringOptionalDefault: 9:16

Video aspect ratio, `16:9` generates landscape video, `9:16` generates portrait video.

Value	Description
16:9	Landscape video
9:16	Portrait video

Example'16:9'

durationintegerOptionalDefault: 15

Specifies the generated video duration in seconds.

Value	Description
15	15 seconds duration
25	25 seconds duration (Higher Cost)

Notes

Billing is based on duration
When duration is 15, only 'high' quality is supported
When duration is 25, only 'standard' quality is supported

Example15

qualitystringOptionalDefault: standard

Video quality setting.

Value	Description
standard	Standard quality, standard pricing
high	High quality, higher pricing

Notes

When duration is 15, only 'high' quality is supported
When duration is 25, only 'standard' quality is supported

Examplestandard

image_urlsarrayOptional

Reference image URL list for image-to-video feature.

Notes

Images containing real human figures are not supported
Max 1 image per request
Max size: 10MB
Formats: .jpg, .jpeg, .png, .webp
URLs must be directly viewable by the server

Examplehttp://example.com/image1.jpg

remove_watermarkbooleanOptionalDefault: true

Whether to remove video watermark.

Value	Description
true	Remove watermark (default)
false	Keep watermark

Exampletrue

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/video-task-completed

Request Example

{
  "model": "sora-2-pro",
  "prompt": "A cat playing piano",
  "aspect_ratio": "16:9",
  "duration": 15,
  "quality": "high",
  "image_urls": [
    "http://example.com/image1.jpg"
  ],
  "remove_watermark": true,
  "callback_url": "https://your-domain.com/webhooks/callback"
}

Response Example

{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "sora-2-pro",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 300,
    "video_duration": 15
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 7,
    "user_group": "default"
  }
}