# Gen-4.5 - Core.Today AI API > Runway's Gen-4.5 model, offering state-of-the-art video motion quality, prompt adherence, and visual fidelity for text-to-video and image-to-video generation. - **Provider**: Runway - **Model ID**: runwayml/gen-4.5 - **Category**: Video Generation - **Credits**: 1400 per 5s video (default) — billed per second (279/s, 5-10s) - **Speed**: Medium - **Quality**: Ultra ## Features - State-of-the-art motion quality and prompt adherence - Flat per-second pricing regardless of aspect ratio - Text-to-video or image-to-video from an optional first frame - 5 or 10 second duration options - Wide range of aspect ratios including 21:9 cinematic ## Use Cases - High-fidelity brand and marketing videos - Complex prompt-driven scenes requiring precise motion control - Animating a first-frame image into a fluid 5-10 second clip - Cinematic 21:9 shots for trailers or hero content - Reproducible generations using a fixed seed ## API Endpoint Base URL: https://api.core.today/v1 Create Prediction: POST /predictions Get Status: GET /predictions/{job_id} ## Authentication Header: X-API-Key: YOUR_API_KEY ## Input Parameters ### Required - **prompt**: string - Text prompt for video generation ### Optional - **image**: string - Optional initial image (first frame). If omitted, video is generated from text only - **duration**: integer (default: 5) - Duration of the output video in seconds Options: 5, 10 - **aspect_ratio**: string (default: 16:9) - Video aspect ratio Options: 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 - **seed**: integer - Random seed for reproducible generation ## Examples ### Text-to-Video (10s) A fully text-driven scene at the maximum 10-second duration ```json { "model": "runwayml/gen-4.5", "input": { "prompt": "A dense, verdant jungle world made up of small lego-like pieces. We see a rainbow chameleon running through the 3D world, the camera in and out of focus.", "duration": 10, "aspect_ratio": "16:9" } } ``` ### Cinematic 21:9 Clip (5s) A shorter, cheaper clip in a wide cinematic aspect ratio ```json { "model": "runwayml/gen-4.5", "input": { "prompt": "A vintage train winding through snow-capped mountains at golden hour", "duration": 5, "aspect_ratio": "21:9" } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending | processing | completed | failed", "result": "URL or data (when completed)" } ``` ## Usage Flow 1. POST /predictions with model and input -> receive job_id 2. GET /predictions/{job_id} -> poll until status is completed or failed 3. Result contains output URL(s) ## Tips - Pricing is a flat $0.12/sec regardless of resolution or aspect ratio - duration only accepts 5 or 10 seconds — a 10s clip costs exactly 2x a 5s clip - Providing an initial image anchors the first frame and often improves motion coherence - Use a fixed seed to reproduce or slightly vary a specific result ## Documentation https://replicate.com/runwayml/gen-4.5