ModelStream LogoModelStream Logo
Models
Video API
Image API
Chat API
Audio API
Studio
Pricing
Docs
Menu
IntroductionQuickstartAPI KeysUse with Hermes AgentUse with OpenClaw
Model ListBilling Guide
ModelStream

Video API

  • Seedance 2.0
  • Happyhorse 1.0
  • Vidu Q3
  • Kling V3.0
  • Veo 3.1
  • Wan 2.7
  • More Video Models →

Image API

  • GPT Image 2
  • Nano Banana 2
  • Seedream 5.0
  • Imagen 4
  • Qwen Image 2.0
  • Z-Image Turbo
  • More Image Models →

Audio API

  • Suno Music
  • Qwen3 TTS Flash
  • More Audio Models →

Chat API

  • GLM-5.2
  • Claude Opus 4.8
  • Gemini 3.5 Flash
  • Qwen 3.7 Max
  • GPT 5.5
  • More Chat Models →

About Us

  • Privacy Policy
  • Terms of Service
  • Support
  • Enterprise

© 2026 ModelStream Inc. All rights reserved.

API Documentation
API Reference
Videos
Generate Video

Generate Video

Loading models...
V
Vidu Q3-Turbo (viduq3-turbo)
viduq3-turbo0 models support this endpoint

Vidu Q3 Turbo delivers the same audio-visual synchronization and 1080p output quality as Q3 Pro at significantly faster generation speeds. Built on Vidu's optimized Q3 inference pipeline, it transforms reference images into up to 16 seconds of video with dialogue and sound effects, making it ideal for rapid iteration and high-volume production workflows where turnaround time matters.

Generate video

https://api.modelstream.ai
POST/v1/video/generations

Authentication

BearerAuth
AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Generation Mode

Choose the generation mode. Single Image: upload one image as the first frame. Head-tail Frames: upload a first and last frame to generate the transition video between them. Only one mode can be used at a time.

image*string

[Single Image mode] Upload an image as the starting frame of the video. Supports JPG, JPEG, PNG formats, max 50MB, aspect ratio must be between 1:4 and 4:1.

RequiredExample Value: https://static.modelstream.ai/demo/vidu/viduq3-turbo.png
prompt*string

Text prompt describing the video scene and motion, max 5000 characters. When 'Recommended prompt optimization' is enabled, the system rewrites this prompt automatically.

RequiredExample Value: Rain falls steadily through the alley. Water droplets splash on the wet pavement and bounce off umbrellas. Neon signs from the food stands reflect and shimmer in the puddles on the ground. Steam rises from a ramen stall. People walk past with umbrellas, their reflections rippling in the wet street. The woman stands still, rain dripping from her hair. Cinematic, moody.Placeholder: Describe the video content you want to generate...
duration?number

Video duration in seconds, range 1-16 seconds.

Example Value: 5Value Range: 1 ≤ value ≤ 16step: 1
resolution?string

Video output resolution. Options: 540p, 720p, 1080p.

Example Value: 720p
Enum/Options:
540p720p1080p
audio?boolean

Enable integrated audio-video direct output, producing video with sound. Enabled by default. Off-peak mode is unavailable when this is off.

Example Value: true
is_rec?boolean

Whether to use recommended prompt optimization. When enabled, the system optimizes the prompt automatically and costs an additional 10 credits per task. Disabled by default.

Example Value: false
seed?number

Random seed value. Set a fixed value for reproducible results, leave empty for a random seed.

Example Value: 0Placeholder: Leave empty for random seed
off_peak?boolean

Off-peak generation mode lowers task priority, extends processing time (up to 18 hours), and offers better pricing. Available only when 'Generate Audio' is enabled. Disabled by default.

Example Value: false

Response Parameters

application/json
200apiDocs.responses.successCreateVideoGenTask
task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams
error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3-turbo",
  "image": {
    "imageUrl": "https://static.modelstream.ai/demo/vidu/viduq3-turbo.png"
  },
  "prompt": "The astronaut waved and the camera moved up.",
  "duration": 5,
  "seed": 0,
  "resolution": "1080p",
  "audio": true,
  "isRec": false,
  "offPeak": false
}'
{
  "task_id": "abcd1234efgh",
  "status": "queued"
}