PixVerse v6

Directed, multi-shot video with cinematic camera control and native audio

About model

On Together AI, PixVerse v6 costs $0.09 per video.

PixVerse v6 is the flagship video model from PixVerse, advancing shot execution, character performance, and multi-shot audio-visual generation. More than 20 cinematic camera controls give directed shots, characters carry deeper and more nuanced emotional expression, and motion stays physically accurate through action-heavy scenes. The model generates multi-shot sequences with native audio coherent across shots, renders multilingual text cleanly within the frame, and holds stable generation up to 15 seconds at 1080p. Available on Together AI.

‍

Camera Controls

20+

Cinematic lens and movement control for directed shots

Max Clip Length

15s

Stable generation at 1080p

Multi-Shot Audio

Native

Audio stays coherent across connected shots

Model key capabilities

Cinematic Camera Control: More than 20 camera and lens controls for directed, intentional shots
Character Performance: Deeper, more nuanced emotional expression and physically accurate motion
Multi-Shot with Native Audio: Connected shot sequences with synchronized audio and clean in-frame multilingual text
Available on Together AI: Serverless access through the Together AI API

API usage

cURL
Python
Typescript

Endpoint:

pixverse/pixverse-v6

curl --request POST \
  --url https://api.together.ai/v2/videos \
  --header "Authorization: Bearer $TOGETHER_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "pixverse/pixverse-v6",
    "prompt": "some penguins building a snowman"
  }'

from together import Together

client = Together()

# Create a video generation job
job = client.videos.create(
    prompt="A serene sunset over the ocean with gentle waves",
    model="pixverse/pixverse-v6"
)

import Together from "together-ai";

const together = new Together();

async function main() {
  // Create a video generation job
  const job = await together.videos.create({
    prompt: "A serene sunset over the ocean with gentle waves",
    model: "pixverse/pixverse-v6"
  });

Model card
Architecture Overview:
• Flagship PixVerse video model succeeding v5.6
• Text and image input with video output, including native audio
• Stable generation up to 15 seconds at 1080p

Training Methodology:
• Developed by PixVerse with a focus on camera execution, character performance, and multi-shot audio-visual coherence

Performance Characteristics:
• Native rendering of Chinese, English, and other languages within the frame, with clear typography and natural blending
• Handles complex scenes including intense action and transformations with synchronized audio
‍
Prompting
Together AI API Access:
• Access PixVerse v6 via Together AI APIs using the endpoint pixverse/pixverse-v6
• Authenticate using your Together AI API key in request headers
• Create a video request from a text prompt or input image, directing camera movement and shot structure in the prompt, then poll until the video completes
• Available on Together AI with serverless access
‍
Applications & use cases
Film & Commercial Production:
• Direct shots with specific camera moves and lens choices
• Generate multi-shot sequences with consistent audio
• Produce action and effects-heavy scenes

Advertising & Brand Content:
• Create finished-looking product and brand clips from one prompt
• Render on-screen text in multiple languages
• Turn product photos into video ads

Character-Driven Content:
• Animate characters with expressive performances
• Keep motion physically believable through complex movement
• Pair performances with synchronized dialogue and sound
‍

Model specifications

Model data

Model provider
PixVerse
Type
Video
Main use cases
Text-to-Video
Image-to-Video
Resolution/Duration
1080p / up to 15s
Deployment
Serverless
Endpoint
pixverse/pixverse-v6
Price
$0.09 / video
Input modalities
Text
Image
Output modalities
Video

Released
March 29, 2026
Category
Video

Run in Playground

Quickstart docs

Deploy Model

PixVerse v6

About model

API usage

Model card

Prompting

Applications & use cases