Skip to main content

pixverse/pixverse-v6-max-t2v

V6-max is a video generation model launched by PixVerse. The t2v (text-to-video) model generates videos from prompts and supports videos up to 15 seconds, audio, and multiple resolutions from 360P to 1080P.

Inference Service Provider

The inference service provider for pixverse/pixverse-v6-max-t2v is PixVerse.

Model Capabilities

CapabilitySupportCapabilitySupport
Input ModalityTextOutput ModalityVideo
Model ExperienceUnsupportedFunction CallingUnsupported
Structured OutputsUnsupportedWeb SearchUnsupported
Prefix CompletionUnsupportedContext CachingUnsupported
Batch InferenceUnsupportedFine-tuningUnsupported

Context Limits

ParameterValueParameterValue
Max Input Length—Max Output Length—
Context Window—

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
  • China (Beijing)
Billing ItemPrice (CNY)Unit
Video Generation(360P)0.27Per second
Video Generation(540P)0.33Per second
Video Generation(720P)0.44Per second
Video Generation(1080P)0.83Per second
Video Generation(360P No Audio)0.18Per second
Video Generation(540P No Audio)0.27Per second
Video Generation(720P no audio)0.33Per second
Video Generation(1080P no audio)0.65Per second

Rate Limits

  • China (Beijing)
ParameterValue
RPM (Requests Per Minute)300