Grok image and video models

    Grok Image makes stills six at a time, while Grok Video and Grok Imagine Video 1.5 make clips with sound.

    Try Grok ImageCompare models
    A golden retriever astronaut sitting on a red desert dune at sunrise, helmet under one paw, long shadows, wide sky with two small moons, photoreal, warm film grain, no text
    Grok Image
    Grok Video
    Grok Imagine Video 1.5

    The lineup

    A golden retriever astronaut sitting on a red desert dune at sunrise, helmet under one paw, long shadows, wide sky with two small moons, photoreal, warm film grain, no text

    Prompt: A golden retriever astronaut sitting on a red desert dune at sunrise, helmet under one paw, long shadows, wide sky with two small moons, photoreal, warm film grain, no text

    • 2:3
    Rainy Tokyo back alley at night, a woman in a yellow raincoat holding a transparent umbrella, neon signs reflected in puddles, shallow depth of field, cinematic 35mm photo, rich teal and magenta light, no text

    Prompt: Rainy Tokyo back alley at night, a woman in a yellow raincoat holding a transparent umbrella, neon signs reflected in puddles, shallow depth of field, cinematic 35mm photo, rich teal and magenta light, no text

    • 2:3
    Editorial still life of a glass bowl of ripe oranges and blue ceramic cups on a sunlit windowsill, hard morning light, crisp shadows, soft linen curtain, medium format photo, no text

    Prompt: Editorial still life of a glass bowl of ripe oranges and blue ceramic cups on a sunlit windowsill, hard morning light, crisp shadows, soft linen curtain, medium format photo, no text

    • 2:3
    Turn this into a vintage enamel pin design: thick dark outlines, three flat colors, glossy metal edges, centered on a plain cream background

    Prompt: Turn this into a vintage enamel pin design: thick dark outlines, three flat colors, glossy metal edges, centered on a plain cream background

    • 2:3

    Grok Image

    Six takes per prompt, or two edits of an image.

    Built for volume: one prompt returns six images, a contact sheet to choose from instead of a single guess. Use it early in a brief, when the question is which direction, not which pixel.

    Best for

    • Exploring a direction with six options
    • Social posts, reaction art, poster illustration
    • Restyling or restaging a still you have

    Pick another model for

    • Small in-image text or exact product detail
    • Edits needing several reference images at once

    Specs

    Modes
    Text to image, image edit
    Images per run
    6 from text, 2 per edit
    Edit input
    1 image
    Aspect ratios
    2:3, 3:2, 1:1, 9:16, 16:9
    Prompt
    Up to 5,000 characters
    Negative prompt
    Not supported
    Try Grok Image
    See prices

    Price

    OptionRateUnit
    Text to image14credits
    Edit14credits
    Current rates in credits.

    Prompt: A corgi in a tiny chef hat flips a pancake that lands on its own head, cozy home kitchen, handheld phone footage feel, sizzling pan, a surprised bark

    • 6s
    • 720p
    • 9:16
    • Fun

    Prompt: The golden retriever astronaut slowly turns its head toward the rising sun, red dust drifts across the dune, slow push in, long shadows shifting

    • 6s
    • 720p

    Grok Video

    Clips with sound from a prompt or a still.

    The Grok video model that starts from text as well as a still. A mode switch sets the feel: Normal reads the prompt straight, Fun takes a looser, more playful turn.

    Best for

    • A quick clip with no image yet
    • Animating a meme or poster with sound
    • Vertical 9:16 drafts for short-form feeds

    Pick another model for

    • Lengths other than 6 or 10 seconds
    • Anything above 720p, or exact product detail

    Specs

    Output
    Video with audio
    Starts from
    A prompt, or 1 image
    Duration
    6 or 10 seconds
    Resolution
    480p or 720p
    Aspect ratios (text to video)
    2:3, 3:2, 1:1, 9:16, 16:9
    Prompt
    Up to 5,000 characters
    Try Grok Video
    See prices

    Price

    OptionRateUnit
    Text to video, 6 s65credits
    Image to video65credits
    Current rates in credits.

    Prompt: The woman walks slowly toward camera under the clear umbrella, rain falls, neon reflections ripple in the puddles, soft ambient rain and distant traffic

    • 4s
    • 480p

    Grok Imagine Video 1.5

    Image to video only, any length from 2 to 15s.

    The newer Grok video model, running on Kubeez as a preview release. It turns one still into a clip and sets length to the second, so a 3 second loop and a 14 second scene come from one model.

    Best for

    • Animating a still you already like
    • Short 2 to 4 second loops
    • Keeping your image's exact framing

    Pick another model for

    • Starting from a prompt alone: use Grok Video
    • First to last frame transitions, or above 720p

    Specs

    Output
    Video with audio, from 1 image
    Duration
    Any whole second, 2 to 15
    Resolution
    480p or 720p
    Aspect ratios
    Auto, 1:1, 16:9, 9:16
    More ratios
    4:3, 3:4, 3:2, 2:3
    Prompt
    Optional, up to 4,096 characters
    Try Grok Imagine Video 1.5
    See prices

    Price

    OptionRateUnit
    480p20credits / sec
    720p30credits / sec
    Current rates in credits.

    The three Grok models side by side

    ModelOutputStarts fromLengthResolutionAspect ratios
    Grok ImageImages, 6 per promptText, or 1 imageNot applicableNo resolution setting5 ratios
    Grok VideoVideo with audioText, or 1 image6 or 10 seconds480p or 720p5, text to video
    Grok Imagine Video 1.5Video with audio1 image, required2 to 15 seconds480p or 720pAuto plus 7 ratios

    Which Grok should I use?

    How the family fits together

    Grok on Kubeez is three separate models that share a name, not a job. Grok Image is the only one that outputs pictures. Grok Video starts from a prompt or a still. Grok Imagine Video 1.5, the newer release, needs a still. No image yet? Make one in Grok Image.

    Getting more out of Grok

    • Pick the best of six in Grok Image, then animate it in either video model.
    • On Grok Imagine Video 1.5, test at 2 or 3 seconds and 480p, then render at 720p.
    • In image to video, describe the motion, not the picture; the still already shows the frame.

    Pick a plan

    One credit balance covers images, video and audio. Pick the size that fits how much you make.

    Most popular

    Studio Pro

    Studio value with extra headroom.

    49 EURmonth
    6,400credits / month
    Team seats

    2 seats included

    What you'll generate

    • Images~1,600
    • Songs~492
    • Videos~640
    • Separations~1,066
    • Caption Minutes~213
    • All modelsIncluded
    Select plan

    Starter

    Low tier generations for regular use.

    10 EURmonth
    1,100credits / month

    What you'll generate

    • Images~275
    • Songs~84
    • Videos~110
    • Separations~183
    • Caption Minutes~36
    • All modelsIncluded
    Select plan

    Pro

    Access full experience.

    20 EURmonth
    2,600credits / month

    What you'll generate

    • Images~650
    • Songs~200
    • Videos~260
    • Separations~433
    • Caption Minutes~86
    • All modelsIncluded
    Select plan

    Powerhouse

    Most cost efficient.

    99 EURmonth
    13,000credits / month

    13,000 credits/mo

    Team seats
    3 seats

    Extra seats €19/seat/mo

    What you'll generate

    • Images~3,250
    • Songs~1,000
    • Videos~1,300
    • Separations~2,166
    • Caption Minutes~433
    • All modelsIncluded
    Select plan

    Enterprise

    For teams that outgrow standard plans.

    Custom

    Pricing tailored to your team

    What's included

    • Custom number of seats
    • Custom credit volume
    • Invoice billing
    • Priority support
    Contact sales
    Or pay-as-you-go

    Test any model with one-time credit packs

    Credits never expire and don't require a subscription — buy a pack, generate, see if Kubeez fits.

    Quick refill

    Quick refill for short bursts of generation.

    Credits

    500

    You pay

    €6

    Standard pack

    Mid-size pack at the standard per-credit rate.

    Credits

    1,500

    You pay

    €18

    −5%

    Volume pack

    Larger pack with a volume discount built in.

    Credits

    5,000

    You pay

    €60€57

    −10%

    Production pack

    Best per-credit price for sustained production.

    Credits

    15,000

    You pay

    €180€162

    Frequently asked questions

    • No. They are separate models that share a name. Grok Image outputs stills only; the two video models output clips.

    • Grok Video. Grok Imagine Video 1.5 always needs one image as its first frame.

    • Yes. Both video models return the clip with an audio track, with no setting to skip it. For a silent clip, mute or replace the track in your edit.

    • Both video models offer 480p and 720p. For 1080p, pick another video family on Kubeez.

    • No. All three models run inside Kubeez on your regular balance, in the studio and through the Kubeez API.

    Open Grok in the studio

    Pick the model that fits your job, write your prompt and run it.

    Open the studioAll model families