pixverse-pixverse-v6-r2v

Models/pixverse-v6-r2v

Model Code

pixverse/pixverse-v6-r2v

Model overview

Video generation

PixVerse V6 R2V is a multi-subject reference-to-video model. It accepts 2-7 images, intelligently fuses different subjects, and is suitable for complex medium and long shots while retaining text-to-video prompt control, image-to-video consistency, expressive emotion, fast motion, 15-second video, music, and multilingual text support.

Company: PixVerseProvider: Alibaba Cloud

Model capabilities

Input modalityT

Output modalityT

Model experience✓

Function calling-

Structured output-

Web search-

Prefix completion-

Context cache-

Batch inference-

Fine-tuning-

Model pricing

Video generation (360P)$0.03134/s

Video generation (540P)$0.0403/s

Video generation (720P)$0.05373/s

Video generation (1080P)$0.1015/s

Video generation (360P, silent)$0.02239/s

Video generation (540P, silent)$0.03134/s

Video generation (720P, silent)$0.0403/s

Video generation (1080P, silent)$0.0791/s

Rate limits and context

Maximum input length-

Context length-

Maximum output length-

RPM300

API reference

EndpointPOST /v1/video/generations

SDKOpenAI-compatible

API code examples

Get API Key

import os
import requests

response = requests.post(
    "https://api.wlrouter.com/v1/video/generations",
    headers={
        "Authorization": f"Bearer {os.environ['WLROUTER_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
  "model": "pixverse/pixverse-v6-r2v",
  "prompt": "A calm sunrise over a modern city skyline.",
  "duration": 4,
  "resolution": "720p",
  "parameters": {
    "generateAudio": False
  }
}
)
response.raise_for_status()
print(response.json())