Wan · Video model

    Wan 3.0 Text to Video: specs, pricing and how to use it

    Alibaba's Wan 3.0 generates video with native audio from a text prompt. Ranked #1 on the Artificial Analysis text-to-video board at launch. 480p, 720p or 1080p, 2-15 seconds, five aspect ratios or adaptive, with prompt expansion and an optional slower reasoning pass.

    6 credits · was 8Up to 1080p3 variants#1 overallFeatured

    What Wan 3.0 Text to Video is best at

    Text to video
    Text drivenNative audioTop RankedPrompt expansionCinematic

    Pricing

    Wan 3.0 Text to Video costs 6 credits on Versely, discounted 30% from 8 credits. It bills per second, at a rate that changes with output resolution, so a full job runs 6 to 168 credits depending on output resolution.

    OptionPrice
    SD43 credits
    HD86 credits
    4K1612 credits

    Prices are Versely credits. Your plan's credit allowance is on the pricing page.

    Wan 3.0 Text to Video variants

    Versely runs 3 versions of this model - tiers and input modes share the same underlying model, so they live here rather than on 3 near-identical pages. Prices range from 6 to 6 credits.

    VariantModeTierCreditsMax resolutionDurations
    Wan 3.0 Image to Videoimage to videoStandard6-2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
    Wan 3.0 Reference to Videoreference to videoStandard6-2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
    Wan 3.0 Text to VideoThis pagetext to videoStandard6-2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s

    Specs

    Aspect ratios
    16:99:161:14:33:4
    Durations
    2s3s4s5s6s7s8s9s10s11s12s13s14s15s
    Qualities
    480p720p1080p

    Inputs

    Starting image

    Not required - generates from a text prompt alone.

    Video input

    Not supported.

    Rankings

    Wan 3.0 Text to Video ranks #1 overall with an Elo score of 1334 on Versely's live model rankings.

    CategoryRankEloMeasured
    Text to video#113342026-08

    Release

    Wan 3.0 Text to Video was released on August 23, 2026 (released 21 days ago).

    Compare Wan 3.0 Text to Video

    Side-by-side pricing, resolution and rankings against models buyers weigh it against.

    Other video models

    Use Wan 3.0 Text to Video inside these tools

    Frequently asked questions

    How much does Wan 3.0 Text to Video cost on Versely?+

    Wan 3.0 Text to Video is normally 8 credits, currently discounted 30% to 6 credits. A full job runs 6-168 credits depending on output resolution.

    What is Wan 3.0 Text to Video best for?+

    Alibaba's Wan 3.0 generates video with native audio from a text prompt. Ranked #1 on the Artificial Analysis text-to-video board at launch. 480p, 720p or 1080p, 2-15 seconds, five aspect ratios or adaptive, with prompt expansion and an optional slower reasoning pass. On Versely it is filed as a Wan video model for text to video.

    How many versions of Wan 3.0 Text to Video are there?+

    Versely runs 3 Wan 3.0 Text to Video variants - Wan 3.0 Text to Video (text to video, 6 credits); Wan 3.0 Image to Video (image to video, 6 credits); Wan 3.0 Reference to Video (reference to video, 6 credits). They range from 6 to 6 credits.

    What resolution does Wan 3.0 Text to Video output?+

    Wan 3.0 Text to Video supports output up to 1080p (available qualities: 480p, 720p, 1080p).

    How does Wan 3.0 Text to Video rank against other video models?+

    Wan 3.0 Text to Video ranks #1 overall with an Elo score of 1334 on Versely's live model rankings.

    Try Wan 3.0 Text to Video inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.