SandBase is live — $1 in free credits on signupStart free ›

meituan modelsvideo generation api

meituan/longcat-video/text-to-video/480p

Longcat Video 480p by meituan - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.

Input
The prompt to guide the video generation.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
110
The guidance scale to use for the video generation. Range: 1 to 10.
850
The number of inference steps to use for the video generation. Range: 8 to 50.
The seed for the random number generator.
The write mode of the generated video. Allowed values: fast, balanced, small.
The output type of the generated video. Allowed values: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif).
160
The frame rate of the generated video. Range: 1 to 60.
17961
The number of frames to generate. Range: 17 to 961.
The quality of the generated video. Allowed values: low, medium, high, maximum.
Idle

Example output — click Run to generate your own

API README

LongCat Video

LongCat Video Text to Video 480p turns a complete written shot specification into a low-resolution video proxy. It is the economical full-model text route for exploring subject staging, action timing, camera movement, and aspect ratio before a production team invests in larger frames. With no source image to carry visual assumptions, the prompt should name concrete visible events and keep the sequence simple enough to judge clearly at 480p.

The endpoint exposes fps, total frames, aspect ratio, guidance, inference steps, quality level, write mode, and four output containers. Its 480p ceiling makes it well suited to previsualization, prompt A/B tests, and large candidate pools, while the absence of refinement-step control keeps the workflow lean. Compare story and motion rather than microscopic detail, then transfer an approved brief to the 720p route for closer review.

Highlights

  • 480p proxy-first text generation. This route renders written scene direction at a fixed 480p target, making broad prompt and motion exploration economical before an HD pass.
  • Lean generation controls. num_inference_steps, guidance_scale, num_frames, and fps expose the main trade-offs for fast preview creation without a separate refinement stage.
  • Composition across delivery shapes. Ten aspect_ratio choices cover cinematic, square, landscape, and portrait proxies while preserving the route's 480p review purpose.
  • Review-friendly encodes. X264, VP9, ProRes 4444, and GIF outputs plus fast, balanced, or small write modes let teams tailor proxies to browser review, editing, or lightweight sharing.

Pricing

ConfigurationPrice
Billing ruleparams.duration * 0.025
Formula-priced requestStarts from $0.025000; final charge follows the billing rule above

When to Use

ScenarioWhy this model fits
Create the exact route outputChoose it when you need text-to-video generation and already have a shot description with subject, action, camera, and atmosphere.
Develop controlled variationsKeep the main brief fixed while changing one documented setting at a time to compare motion, framing, quality, or asset behavior.
Build repeatable batchesUse a consistent request shape for catalog, campaign, storyboard, game-asset, or social-content production.
Preserve source intentPrefer this route when the supplied reference material must remain the foundation of a coherent video interpretation of the written direction.
Connect a media pipelineUse asynchronous results in an automated review, approval, post-production, or asset-management workflow.

Prompt Guide

Start with the desired result, then describe the source relationship, subject action, composition or camera behavior, lighting, style, and timing. For text-to-video generation, state what must remain stable as clearly as what should change. Use only fields exposed by the schema; the example below is structurally valid for this route.

{
  "prompt": "realistic filming style, a person wearing a dark helmet, a deep-colored jacket, blue jeans, and bright yellow shoes rides a skateboard along a winding mountain road. The skateboarder starts in a standing position, then gradually lowers into a crouch, extending one hand to touch the road surface while maintaining a low center of gravity to navigate a sharp curve. After completing the turn, the skateboarder rises back to a standing position and continues gliding forward. The background features lush green hills flanking both sides of the road, with distant snow-capped mountain peaks rising against a clear, bright blue sky. The camera follows closely from behind, smoothly tracking the skateboarder’s movements and capturing the dynamic scenery along the route. The scene is shot in natural daylight, highlighting the vivid outdoor environment and the skateboarder’s fluid actions.",
  "fps": 15,
  "seed": 1,
  "num_frames": 162,
  "aspect_ratio": "21:9"
}

Technical Specs

SpecificationValue
Model IDmeituan/longcat-video/text-to-video/480p
WorkflowText-to-video generation
Required inputsprompt
fpsinteger; minimum: 1; maximum: 60
seedinteger
promptstring
num_framesinteger; minimum: 17; maximum: 961
aspect_ratiostring; options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
video_qualitystring; options: low, medium, high, maximum
guidance_scalenumber; minimum: 1; maximum: 10
video_write_modestring; options: fast, balanced, small
video_output_typestring; options: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)
num_inference_stepsinteger; minimum: 8; maximum: 50

Related Models

Related Models

meituan/longcat-video/text-to-video/720pLongcat Video 720p by meituan - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.meituan/longcat-video/distilled/image-to-video-480pLongcat Video Distilled Image To Video 480p is meituan's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.meituan/longcat-video/distilled/text-to-video-720pLongcat Video Distilled Text To Video 720p by sandbase-ai - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.meituan/longcat-video/distilled/text-to-video/480pLongcat Video Distilled 480p by meituan - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.meituan/longcat-video/image-to-videoLongcat Video is meituan's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.meituan/longcat-video/image-to-video-480pLongcat Video Image To Video 480p is meituan's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.meituan/longcat-video/distilled/image-to-videoLongcat Video Distilled is meituan's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.meituan/longcat-single-avatar/image-audio-to-videoLongcat Single Avatar Image Audio To Video by sandbase-ai - advanced AI model for audio-to-video. Delivers high-quality results with fast inference, suitable for both creative and production workflows.