Pixverse v6. Supports text-to-video, image-to-video, and reference-to-video with up to 10 reference images or 2 reference videos, 360p-1080p output, and optional audio generation.
Added Mar 31, 2026
Starting Price
From $0.025 per video
Final price depends on the selected settings and is shown before generation.
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
5
15 duration options
Aspect Ratio
Default
auto
Options (9)
Auto, Landscape (16:9), Standard (4:3), Square (1:1) +5 more
Auto matches reference media; text-to-video defaults to 16:9
Duration
Default
5
Options (15)
1 second, 2 seconds, 3 seconds, 4 seconds +11 more
Video length from 1 to 15 seconds
Generate Audio
Default
No
Enable audio generation (higher per-second billing)
Prompt Optimization
Default
auto
Options (3)
Auto, Enabled, Disabled
System-level prompt optimization
Resolution
Default
720p
Options (4)
360p, 540p, 720p, 1080p
Video quality level
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#10 / 81
ELO
1230.0
Appearances
5,790
95% CI
-8/8
Image to Video
#5 / 76
ELO
1340.0
Appearances
5,677
95% CI
-10/10
Release Date 2026-03 · Matched as PixVerse V6
Artificial Analysis APIExamples
Loading examples…
Related video models
Compare Pixverse v6 with similar models from the same provider or model family.
PixVerse Motion Control Mimic
pixverse/motion-control/mimicPixVerse Motion Control Mimic transfers the movement from a reference video onto a target image while preserving the target subject. Requires one image and one motion video; output quality supports 360p, 540p, and 720p.
PixVerse C1
pixverse-c1PixVerse C1. One model id that supports text-to-video (prompt only), image-to-video (start image), transition (start + end frame), or reference-to-video (reference image set). Supports 360p-1080p, 1-15 second clips, and optional audio generation.
Pixverse v5.6
pixverse-v56Pixverse v5.6 supports text-to-video and image-to-video in one model. Upload an image to animate it, or leave it blank to generate from text. 360p-1080p resolution, 5/8/10s durations, optional audio generation, prompt optimization, and negative prompts.
Pixverse v5.5 Effects
pixverse-v55-effectsPixverse v5.5 Effects. Apply cinematic effect presets (Kiss Me AI, Venom, Holy Wings, Muscle Surge, etc.) to portraits. 360p-1080p resolution, 5/8/10s durations.
Pixverse v5.5
pixverse-v55Pixverse v5.5. Text-to-video, image-to-video, and transition mode (first+last frame morphing). 360p-1080p resolution, 5/8/10s durations. Supports prompt optimization and audio generation.
Pixverse v5
pixverse-v5Pixverse v5 video generation model via Runware. Supports text-to-video and image-to-video with customizable styles, effects, camera movements, and sound effects. Resolutions from 360p to 1080p and durations of 5 or 8 seconds.