Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front.See what's new

PixVerse: PixVerse V6

PixVerse v6 brings image and video references into a flexible short-video workflow. It is useful when a new shot should draw on existing visual material while still leaving room to direct its action and pacing.
Compare models
pixverse-v6
AvailablePixVerseVideoAsync
Price
From $0.045
Modalities
Video

About PixVerse V6

PixVerse V6 is the flagship video model in PixVerse's lineup, launched on March 30, 2026. It generates clips of one to fifteen seconds in up to 1080p with native audio, and can build multi-shot short films from a single prompt. It accepts image and video references and offers extend and transition workflows. PixVerse cites better camera work and character performance than earlier releases.

Where it works well

  • Multi-shot short films with native audio can come from a single prompt, such as a product advertisement.
  • It is the PixVerse model that takes video references as well as images, and it has an extend operation.
  • Clip length is set per second, from short beats to fifteen seconds.
  • Text inside frames is supported in English, Chinese and other languages, per PixVerse's launch notes.

When to choose another model

  • PixVerse itself lists precise directional control in complex scenes and consistency across large spatial changes as open problems.
  • Adding video references raises the cost of a job, so heavy reference workflows deserve a small trial first.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image to videoReference to videoStart and end frames to videoText to videoTokenLab endpoint
    POST/v1/videos/generations
    curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "duration": 5,
      "operation": "text-to-video",
      "output_audio": false,
      "resolution": "720p",
      "model": "pixverse-v6",
      "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
    }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

360p · No video input · Audio off

per second
Official price
$0.025
Verified price
—
Discount
—

360p · No video input · Audio on

per second
Official price
$0.035
Verified price
—
Discount
—

540p · No video input · Audio off

per second
Official price
$0.035
Verified price
—
Discount
—

540p · No video input · Audio on

per second
Official price
$0.045
Verified price
—
Discount
—

720p · No video input · Audio off

per second
Official price
$0.045
Verified price
—
Discount
—

720p · No video input · Audio on

per second
Official price
$0.06
Verified price
—
Discount
—

1080p · No video input · Audio off

per second
Official price
$0.09
Verified price
—
Discount
—

1080p · No video input · Audio on

per second
Official price
$0.115
Verified price
—
Discount
—

Reference to video · 360p · Includes video input · Audio off

per second
Official price
$0.05
Verified price
—
Discount
—

Reference to video · 360p · Includes video input · Audio on

per second
Official price
$0.07
Verified price
—
Discount
—

Reference to video · 540p · Includes video input · Audio off

per second
Official price
$0.07
Verified price
—
Discount
—

Reference to video · 540p · Includes video input · Audio on

per second
Official price
$0.09
Verified price
—
Discount
—

Reference to video · 720p · Includes video input · Audio off

per second
Official price
$0.09
Verified price
—
Discount
—

Reference to video · 720p · Includes video input · Audio on

per second
Official price
$0.12
Verified price
—
Discount
—

Reference to video · 1080p · Includes video input · Audio off

per second
Official price
$0.18
Verified price
—
Discount
—

Reference to video · 1080p · Includes video input · Audio on

per second
Official price
$0.23
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open PixVerse V6 in Console with a prompt ready to edit or send.

Help me create with pixverse-v6 using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for
  • Text to Video
  • Ad spots

    Describe a product story in one prompt and receive a multi-shot clip with sound, ready for a rough cut.

  • Footage-based fusion

    Combine existing clips and stills as references so a new shot reuses a character, set, or motion.

  • Continuing a shot

    Extend a clip that ended too early, keeping the same subject and camera feel.

Prompt examples

Shot 1: wide of a coffee roastery at dawn. Shot 2: close-up of beans pouring. Shot 3: a cup placed on a counter. Warm music.

Use the attached clip for the dancer's movement and the attached photo for her costume; film in a neon alley.

Extend this shot by six seconds as the camera drifts past the lighthouse and the storm clears.

FAQ

What is PixVerse V6?

V6 is PixVerse's video model launched on March 30, 2026. It focuses on camera work, character performance, and multi-shot generation with native audio, and it covers text-to-video, image-to-video, transitions, extension, and reference-based fusion.

How long and how sharp are the clips?

One to fifteen seconds, in 360p, 540p, 720p or 1080p. The catalog lists whole-second choices, so you can match the clip to a beat instead of rounding to a fixed length.

Can I give it video references?

Yes. PixVerse documents V6 as accepting several reference images and up to two reference videos, with the total video length capped at fifteen seconds. C1, by comparison, takes images only.

Does V6 produce audio?

Yes, native audio is generated with the picture, and PixVerse lists an audio switch in its platform docs. That includes sound for multi-shot clips from a single prompt.

V6 versus C1 versus V5.6?

V6 is the broadest: extension, video references, per-second length. C1 targets action and storyboards without extension. V5.6 is the older fixed-length option at five, eight or ten seconds.

How much does PixVerse V6 cost?

On TokenLab, PixVerse V6 costs $0.025-$0.23 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should PixVerse V6 use?

Use https://api.tokenlab.sh/v1/videos/generations for PixVerse V6. The request example below shows the matching code shape.

Which operations does PixVerse V6 support?

PixVerse V6 supports Image to video, Reference to video, Start and end frames to video, Text to video. Select an operation above to see its endpoint and request example.

Compare PixVerse V6

Guides that use PixVerse V6

Sources

Reviewed Oct 2, 2026

More from PixVerse

Related models