# OpenAI Sora 2 > OpenAI's flagship video generation model with synchronized audio. Advanced physics simulation, realistic motion, multi-shot sequences, and versatile styles from photorealistic to anime. - **Provider**: replicate - **Model ID**: openai/sora-2 - **Category**: video_generation - **Credits**: 600 per request - **Pricing Type**: fixed ## API Endpoint Base URL: https://api.core.today/v1 ### Create Prediction POST /predictions ### Get Status GET /predictions/{job_id} ### Cancel DELETE /predictions/{job_id} ## Authentication Header: `X-API-Key: YOUR_API_KEY` ## Input Parameters - `openai_api_key` (string, optional): Optional: Your OpenAI API key for direct billing - `aspect_ratio` (string, optional): Video aspect ratio. Portrait is 720x1280, landscape is 1280x720. (Default: `landscape`; Options: `portrait`, `landscape`) - `seconds` (integer, optional): Duration in seconds (4-12) (Default: `4`; Range: min: 4, max: 12) - `prompt` (string, **required**): A text description of the video to generate - `input_reference` (string, optional): Optional image to use as the first frame. Must match video aspect ratio. ## Example Request ```json { "model": "openai/sora-2", "input": { "prompt": "Bob ross in his studio painting a landscape on a background of red orange yellow goo", "aspect_ratio": "landscape", "seconds": 4 } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending", "provider": "replicate", "model": "black-forest-labs/flux-schnell", "created_at": "2026-01-01T00:00:00Z", "result": null, "error": null } ``` Status values: `pending`, `processing`, `completed`, `failed`, `cancelled` ## Usage Flow 1. POST /predictions with model and input → receive job_id 2. Poll GET /predictions/{job_id} until status is `completed` or `failed` 3. Result contains output URL(s) or data ## Output Type url ## Tags openai, sora, video-generation, text-to-video, image-to-video, audio, physics, cinematic, flagship ## Documentation https://replicate.com/openai/sora-2