Sora 2 Pro Image to Video API

openai/sora-2-pro/image-to-video

Sora 2 Pro (Image to Video) animates high-fidelity static reference images into cinematic videos up to 1080p Full HD, supporting auto aspect ratio matching, resolution options from 720p to 1080p, and native synchronized acoustics. It locks subject identity, intricate surface textures, and nuanced illumination while producing smooth three-dimensional camera trajectories and believable physical dynamics.

Discontinued

openai/sora-2-pro/image-to-video

Choose another model to keep creating

Text to Video

ByteDance

Seedance 2.5

ByteDance Seed's Seedance 2.5 video model with separate text-to-video, start/end-frame image-to-video, and multimodal reference-to-video API workflows at 480p, 720p, or 1080p for 4 to 30 seconds.

From

$0.140

per output second

Try it

Text to Video

MiniMax

MiniMax H3

MiniMax H3 on Vidgo API with separate text-to-video, start/end-frame image-to-video, and multimodal reference-to-video workflows at fixed 2K output.

From

$0.105

per second

Try it

Text to Video

ByteDance

Seedance 2.0

ByteDance Seedance 2.0 Standard and Fast video generation with text, ordered start/end frames, or multimodal image, video, and audio references.

From

$0.100

per output second

Try it

Text to Video

MiniMax

Hailuo 2.3

MiniMax's Hailuo 2.3 video model for realistic human motion, expressive characters, and text-to-video or first-frame guided generation at 768p and 1080p.

From

$0.175

per video

Try it

Text to Video

Kling

Kling 3.0

Kuaishou's most advanced video model with native 4K/60fps output, multi-shot storyboarding, multilingual audio, and character consistency for up to 3 people.

From

$0.135

per second

Try it

Discontinued: this model no longer accepts generation requests. The API documentation below is retained for reference only.

REST API

Quick Start

Authenticate, pass reference image and motion prompt, then retrieve 1080p animated video.

Step 1: Set up authentication

Include Authorization: Bearer VIDGO_API_KEY in all HTTP request headers.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Step 2: Submit image-to-video task

Send POST request to /api/generate/submit with model openai/sora-2-pro/image-to-video, prompt, image_urls, and auto aspect ratio.

Submit request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "openai/sora-2-pro/image-to-video",
  "input": {
    "prompt": "The young woman on the balcony turns her head slowly toward the camera and smiles softly, long hair flowing in the golden sunset breeze, cinematic warm light. Natural sound: gentle wind, soft distant ambience, a quiet breath. Realistic motion, no text, no logos.",
    "duration": 4,
    "resolution": "1080p",
    "aspect_ratio": "auto",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/openai/sora-2-pro/image-to-video/v1/01/input.png"
    ]
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Step 3: Poll for video result

Poll with task_id while status is not_started or running, and stop at finished or failed. On success, read data.files[].file_url; on failure, read data.error_message.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll with task_id while status is not_started or running, and stop at finished or failed. On success, read data.files[].file_url; on failure, read data.error_message.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-sora2-pro-i2v-781923",
    "status": "running",
    "created_time": "2026-09-17T10:00:00Z"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete script example

Expand for a complete script with HTTP and business-code checks, task_id validation, polling, terminal-state handling, and a 600-second polling timeout.

Complete script example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "openai/sora-2-pro/image-to-video",
  "input": {
    "prompt": "The young woman on the balcony turns her head slowly toward the camera and smiles softly, long hair flowing in the golden sunset breeze, cinematic warm light. Natural sound: gentle wind, soft distant ambience, a quiet breath. Realistic motion, no text, no logos.",
    "duration": 4,
    "resolution": "1080p",
    "aspect_ratio": "auto",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/openai/sora-2-pro/image-to-video/v1/01/input.png"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input parameters

Parameters passed within the input object to /api/generate/submit:

Field	Type	Required	Default	Description
prompt	string	Yes	—	Action and camera motion prompt, at least 1 character.
image_urls	array	Yes	—	Array containing exactly one public image URL. Supported formats: JPEG, PNG, WebP (≤10MB).
duration	integer	No	4	4, 8, 12, 16, or 20, in seconds.
aspect_ratio	string	No	16:9	auto, 16:9, or 9:16. auto is supported when image_urls is present.
resolution	string	No	1024p	720p, 1024p, or 1080p.

Response Fields

Task creation payload and query status response details:

Field	Type	Description
code	integer	Application result code; successful responses return 200.
message	string	Human-readable status or error message.
data.task_id	string	Unique asynchronous task identifier.
data.status	string	Current lifecycle: not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp in ISO 8601 format.
data.files[]	array	Output files generated upon completion.
data.files[].file_url	string	Public URL for downloading or playing the generated video.
data.error_message	string \| null	Detailed error explanation when task status is failed.

Task Lifecycle

Poll status until reaching finished or failed:

not_started
Task accepted and waiting in compute dispatch queue.
running
Diffusion model is animating reference image frames in 1080p and synthesizing audio.
finished
Generation completed; read video URL from data.files[0].file_url.
failed
Task stopped due to invalid image or safety filter; inspect data.error_message.

Polling and Errors

AuthenticationVerify Bearer API key in request header if 401 is received.
Image & Resolution validationEnsure image_urls contains 1 valid URL and resolution is within 720p/1024p/1080p on 400 response.
Polling intervalPoll with a 2-second base interval, extending gradually for longer jobs.
Webhook callbackProvide callback_url at request top level to receive asynchronous POST notifications.

Endpoint limits

Specification	Value	Details
Input mode	Text + One Image	A prompt guides motion, and image_urls provides exactly one required reference image.
Output	MP4 video with native audio	Asynchronous video generation with downloadable MP4 URL upon completion.
Duration	4 / 8 / 12 / 16 / 20 seconds	Default is 4 seconds.
Aspect ratio	auto / 16:9 / 9:16	Default is 16:9; auto inherits input image aspect ratio.
Resolution	720p / 1024p / 1080p	Default is 1024p, supporting up to 1080p Full HD.
Image requirements	JPEG / PNG / WebP, ≤ 10MB	Must provide exactly one publicly accessible URL.
Billing basis	Per second × resolution rate	720p: 48 credits/s; 1024p: 80 credits/s; 1080p: 112 credits/s.

Sora 2 Pro Image to Video

Sora 2 Pro Image to Video is OpenAI's flagship model for image-to-video synthesis. Using a single reference image as a visual anchor, it evolves static keyframes into cinematic video clips featuring nuanced facial expressions, volumetric lighting, and native synchronized stereo audio. With auto aspect ratio adaptation and up to 1080p Full HD rendering, it is tailored for luxury commercial deliverables, high-end e-commerce animation, and ultra-high-definition digital assets.

Why Choose This Endpoint?

Flagship 1080p Full HD ResolutionDelivers up to 1080p resolution, preserving facial skin textures, hair strands, metallic reflections, and fabric weaves ready for broadcast.
Native Auto Aspect Ratio MatchingOffers native auto aspect ratio support, automatically detecting and inheriting source image dimensions without cropping or letterboxing.
High-Fidelity Identity & Lighting PreservationMaintains character identity, silhouette contours, and subtle ambient shadows across large physical movements without morphing artifacts.
Synchronized Native Stereo AcousticsPerforms joint multimodal audio synthesis to embed authentic ambient room noise and physical Foley effects aligned to visual action.
Tiered Resolutions & Structured DurationsProvides 720p, 1024p, and 1080p resolutions alongside 4s to 20s tiers to easily balance quick motion tests with full master delivery.
Transparent Predictable Pay-As-You-Go BillingBilled transparently on a resolution rate per second basis, offering complete flexibility with no forced monthly subscriptions.

Parameters

Parameter	Requirement	Description
prompt	Required	String. Describe action choreography, camera trajectory, environmental lighting, and acoustic cues. Minimum 1 character after trimming.
image_urls	Required	Array of strings. Exactly one public URL pointing to a JPEG, PNG, or WebP image, up to 10MB.
duration	Optional	Integer. Sets clip duration in seconds: 4, 8, 12, 16, or 20. The playground defaults to 4 seconds. Default`48121620`
aspect_ratio	Optional	String. Sets framing format: auto (recommended), 16:9, or 9:16. The playground defaults to 16:9. Default`16:9auto9:16`
resolution	Optional	String. Sets output resolution: 720p, 1024p, or 1080p. The playground defaults to 1024p. Default`1024p720p1080p`

How to Use

Prepare High-Fidelity Image & API KeyHost a clean reference image publicly (JPEG, PNG, or WebP, ≤10MB) and attach Authorization: Bearer <API_KEY>.
Set Aspect Ratio & ResolutionChoose auto aspect ratio to preserve source dimensions, and select 720p, 1024p, or 1080p with 4s to 20s clip length.
Submit Request & Download VideoSend POST request to /api/generate/submit with prompt and image_urls, poll status until finished, and retrieve your 1080p video.

Pricing Structure

Sora 2 Pro Image to Video shares the standard Pro pricing rates: 720p at 48 credits/s (4s=192 credits), 1024p at 80 credits/s (4s=320 credits, default), and 1080p at 112 credits/s (4s=448 credits). Based on 2,000 credits for $10, it offers pay-as-you-go convenience with no recurring plan requirements.

Usage	Rate	Details
720p Tier (4–20s)	48 credits/s (from 192 credits / 4s, ~$0.96)	Fast motion validation tier, optimal for testing complex character gestures.
1024p Tier (4–20s, default)	80 credits/s (from 320 credits / 4s, ~$1.60)	Default selection, offering elite optical texture and balanced generation speed.
1080p Tier (4–20s)	112 credits/s (from 448 credits / 4s, ~$2.24)	Full HD master deliverable tier for commercial TVCs, luxury product animation, and gallery showcases.

Best Use Cases

Luxury Product & Industrial Design AnimationAnimate static watch, jewelry, or automotive renderings with realistic optical reflections and accurate physics in Full HD 1080p.
Commercial Campaign Key Visual ActivationLeverage auto aspect ratio to animate campaign posters and key visuals directly without composition loss or aspect distortion.
Film Concept Art & Storyboard PrototypingConvert detailed concept paintings into 1080p cinematic sequences with dynamic camera moves and acoustic presence for pitch reels.
High-Fidelity Game Character AnimationBring 2D splash art and 3D character stills to life with natural hair physics, breathing micro-motion, and synchronized voice cues.

Pro Tips

Use aspect_ratio: "auto" to preserve exact original image proportions to guide framing.
Provide uncompressed, well-illuminated source images to let the Pro model cleanly extract subtle skin textures and lighting layers.
Focus text prompts primarily on desired motion and camera staging rather than reiterating visual details already established in the image.
Specify physical Foley cues (e.g. footsteps on polished tile, silk fabric rustling) to trigger immersive synchronized audio generation.

Usage Notes

image_urls accepts exactly one public URL pointing to a JPEG, PNG, or WebP image file up to 10MB.
aspect_ratio supports auto, 16:9, and 9:16; auto is active exclusively when image_urls is provided.
Optional resolution parameter accepts 720p, 1024p (default), or 1080p, delivering MP4 files with native stereo audio.

Related Models

Gemini Omni 1.1 Flash Text-to-Video preview

Gemini Omni 1.1 Flash Text-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Image-to-Video preview

Gemini Omni 1.1 Flash Image-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Reference-to-Video preview

Gemini Omni 1.1 Flash Reference-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Video Edit preview

Gemini Omni 1.1 Flash Video EditGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Wan 3.0 Text-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Image-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Reference-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Prime Text-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Image-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Reference-to-Video preview

Wan 3.0 Prime Reference-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Grok Imagine Image 2.0 Text to Image preview

Grok Imagine Image 2.0 Text to ImageGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

Grok Imagine Image 2.0 EditGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

FLUX 3 Text to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

FLUX 3 Image to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

FLUX 3 First Last Frame to Video preview

FLUX 3 First Last Frame to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

FLUX 3 Extend VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

Sora 2 Pro Image to Video API frequently asked questions

What is the Sora 2 Pro Image to Video API?

Sora 2 Pro Image to Video is OpenAI's flagship model for image-to-video generation. It uses a single reference image as a visual anchor, animating camera paths and subject movements according to text instructions into cinematic videos up to 1080p Full HD with native synchronized stereo audio. Built on OpenAI's most capable multimodal diffusion architecture, it preserves subject identity, micro-textures, and spatial lighting while generating smooth 3D motion dynamics. You can call it programmatically or try it from the playground above.

How do I use auto aspect ratio in Sora 2 Pro Image to Video?

Set aspect_ratio to "auto" in your request payload. The model automatically detects and matches the pixel aspect ratio of your uploaded reference image, using those proportions to guide the generated composition.

What resolutions are supported by Sora 2 Pro Image to Video?

The endpoint supports 720p, 1024p, and 1080p resolutions (the playground defaults to 1024p). The 1080p mode is tailored for high-end commercial delivery, fully resolving skin pores, fine fabric textures, and subtle reflections.

Does Sora 2 Pro Image to Video maintain character facial consistency?

Yes. Sora 2 Pro features advanced facial landmark extraction and 3D spatial projection. When you provide a well-lit, unobstructed reference portrait and focus text prompts on actions, the model preserves facial likeness consistently across turns, smiles, and head movements.

Can Sora 2 Pro Image to Video generate ambient audio for still images?

Yes. The model employs joint audiovisual reasoning, identifying scene elements in the keyframe (such as fireplaces, oceans, forests, or vehicles) and automatically synthesizing realistic synchronized stereo background audio and motion foley without external audio tools.

How many reference images does Sora 2 Pro Image to Video accept?

The endpoint accepts exactly 1 reference image passed in the image_urls array. The image functions as the initial start frame, and submitting arrays with more than 1 image will return a validation error.

What clip durations does Sora 2 Pro Image to Video offer?

A single call supports generating clips up to 20 seconds, with exact duration options of 4, 8, 12, 16, or 20 seconds (the playground defaults to 4 seconds). Fixed durations allow teams to calculate exact credit expenditures before submitting jobs.