Sora 2 Models

Overview

Vendor: OpenAI. sora-2 provides cinematic text- and image-guided video with native audio. sora-2-pro is the higher-fidelity option for polished cinematic scenes.

Supported modes

Credit pricing

The matrix is identical for text-to-video and image-to-video. Audio is a supported toggle and does not have a separate configured multiplier.

sora-2

sora-2-pro

All values are credits per generation.

cURL

curl -X POST https://vidrush-ai.com/api/v1/videos \
  -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "mode": "text-to-video",
    "prompt": "A paper kite crossing a bright summer sky",
    "options": {
      "duration": "8s",
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "audio": true
    }
  }'

CLI

vidrush generate -m sora-2 -p "A paper kite crossing a bright summer sky" \
  --duration 8s --resolution 720p --aspect-ratio 16:9 --audio --wait

MCP

Ask the connected MCP client to call generate_video with model: "sora-2"; it returns the credit cost and task ID.

Notes

• Send a public image URL in image_urls for image-to-video.
• Only use the duration, resolution, and aspect-ratio combinations listed above.