# Runway Gen-4 Image > Runway's Gen-4 Image model with references. Use up to 3 reference images to create the exact image you need. Capture every angle. - **Provider**: replicate - **Model ID**: runwayml/gen4-image - **Category**: face_image_generation - **Credits**: 190 per request - **Pricing Type**: input_based ## 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 - `seed` (integer, optional): Random seed. Set for reproducible generation - `aspect_ratio` (string, optional): Image aspect ratio (Default: `16:9`; Options: `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`) - `reference_tags` (array, optional): An optional tag for each of your reference images. Tags must be alphanumeric and start with a letter. You can reference them in your prompt using @tag_name. Tags must be between 3 and 15 characters. (Default: `[]`) - `reference_images` (array, optional): Up to 3 reference images. Images must be between 0.5 and 2 aspect ratio. (Default: `[]`) - `resolution` (string, optional): Image resolution (Default: `1080p`; Options: `720p`, `1080p`) - `prompt` (string, **required**): Text prompt for image generation ## Example Request ```json { "model": "runwayml/gen4-image", "input": { "aspect_ratio": "4:3", "prompt": "a close up portrait of @woman and @man standing in @park, hands in pockets, looking cool. She is wearing her pink sweater and bangles.", "resolution": "1080p", "reference_tags": [ "park", "woman", "man" ], "reference_images": [ "https://replicate.delivery/pbxt/NHVhGWPplgrmOE8EGTVhbeSqWuZBcZLHyMQrgrTH4Hpa1ljU/m4hjkmbk79rma0cqrnxt67cqnw.jpg", "https://replicate.delivery/pbxt/NHVhFhdxAAmuXKUyT4r10KIalYrXf9vp5B40CmAeXlPieuOs/w99em95b01rmc0cqrny8chf49w.jpg", "https://replicate.delivery/pbxt/NHVhGE5GSJlAfL9RkGFvUbx70KVl7l7KamUNLHOAUd1sQVuF/psjdbkzgm1rmc0cqrnysbg93cm.jpg" ] } } ``` ## 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 runway, gen-4, image-generation, reference-images, consistent-character, text-to-image ## Documentation https://replicate.com/runwayml/gen4-image