# Kling 2.5 Turbo Pro > Kuaishou Kling 2.5 Turbo Pro for cinematic text-to-video and image-to-video. Features smooth motion, cinematic depth, excellent prompt adherence, and style consistency. Supports complex camera movements and high-speed action. - **Provider**: replicate - **Model ID**: kwaivgi/kling-v2.5-turbo-pro - **Category**: video_generation - **Credits**: 525 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 - `duration` (integer, optional): Duration in seconds (Default: `5`; Options: `5`, `10`) - `image` (string, optional): Deprecated: Use start_image instead - `aspect_ratio` (string, optional): Aspect ratio (ignored if start_image is provided) (Default: `16:9`; Options: `16:9`, `9:16`, `1:1`) - `prompt` (string, **required**): Text prompt for video generation - `negative_prompt` (string, optional): Things you do not want to see in the video - `start_image` (string, optional): First frame of the video (image-to-video) ## Example Request ```json { "model": "kwaivgi/kling-v2.5-turbo-pro", "input": { "duration": 5, "prompt": "A woman is dancing", "aspect_ratio": "16:9" } } ``` ## 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 kling, kuaishou, video-generation, text-to-video, image-to-video, cinematic, turbo, pro ## Documentation https://replicate.com/kwaivgi/kling-v2.5-turbo-pro