Skip to main content

Grok Imagine Video 1.5 from xAI animates a first frame for 1–15 seconds with sound, steered by an end image, up to four timed keyframes or a seamless loop.

From $0.028/s

Workbench

Input

Image to video
169/4096
Describe the action, setting and optional quoted dialogue in up to 4,096 characters; prompt length is not a billing tier. at least 1 characters · at most 4096 characters
1/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

  • 1
1 / 1 files
Required opening-frame image for the animation; it establishes the start rather than a separate price tier. at least 1 characters
0/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

0 / 1 files
Optionally supply the ending frame; leave it out when loop is enabled, as these controls cannot be used together. This field adds no separate billing tier. at least 1 characters
0/1

Drop files or media links, paste, or browse · Up to 1 files · Max 10 MB · JPG · PNG · WEBP · GIF

0 / 1 files
Optionally add one reference image and name it @image1 in the prompt; image-to-video billing follows seconds and resolution. at most 1 items
Use auto to follow the opening image, or 16:9, 9:16, 1:1, 4:3, 3:4, 3:2 or 2:3; the shared default is 16:9. This choice does not alter the resolution rate.
Timed keyframes0/4
Provide up to four intermediate images, each with time_seconds specifying when the video passes through it; keyframe count does not set a separate rate. at most 4 items
Loop
Enable matching first and last frames for a loop; do not also send last_image_url. Loop mode is not a separate billing tier.
affects price
Choose 480p, 720p or 1080p; 480p is the default and higher tiers cost more per second.
Durationaffects price
Request 1–15 seconds, with 6 seconds used by default; longer output increases the seconds billed. no lower than 1 · no higher than 15
Generate audio
Generate a soundtrack by default, or disable it for a result without an audio track; the rate is unchanged.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result

Missing the model you need?

SOUND, STILLS AND TIMED SCENES

Grok Imagine Video 1.5 API at a glance

Describe a fjord crossing, time a change of setting, or animate a paper crane into a repeating shot.

Choose the running time
1–15 S
A clip defaults to six seconds when duration is omitted.
Dialogue with the scene
SOUND
Quoted lines can be spoken in the generated soundtrack.
Text and still workflows
1080P
480p and 720p are also available at lower per-second rates.
Intermediate image slots
4
Each keyframe gives the shot an image to pass through at a specified second.
Reference image capacity
7
Reference-to-video can combine people, objects and settings.
Seamless loop
LOOP
Image-to-video offers a loop control instead of a closing still.

Results

What you can make with Grok Imagine Video 1.5

  • Dialogue in the scene

    A whisper followed by a visible reply

    At a rooftop bar at dusk, a woman in a red backless dress leans toward a man and whispers, "Let's get out of here." Our six-second 480p sample includes that line on the soundtrack, followed by his smile and the hand-taking action. Use the example to plan a brief exchange: identify the speaker, quote the line, and describe the other person's response. Review the returned speech and movement together.

    Generated sample: six seconds, 480p, 16:9, with "Let's get out of here" spoken on the soundtrack.

  • Written scene

    A crossing with a spoken line

    In our tests, a small fishing boat crossed the sunrise fjord beneath circling gulls. The six-second result included sound and the captain delivering the quoted dialogue.

    Text-led sample: six seconds at 480p with generated dialogue and sound.

  • Timed image

    Reach the greenhouse at second three

    In our tests, a rainy lantern alley gave way to a bright Victorian greenhouse at the requested three-second keyframe. The complete shot ran six seconds with sound.

    A greenhouse keyframe guides the scene at three seconds in this six-second sample.

  • Repeatable motion

    A crane that rocks back to its start

    In our tests, the white origami crane moved gently on a blue table through a four-second loop. Its opening and closing frames matched.

    Four-second looping sample with matching first and last frames.

  • Two visual sources

    Put a dancer and an origami bird in one studio

    In our tests, the dancer in black rehearsal clothes moved slowly through a white studio while a paper crane floated nearby. Two uploaded references guided the six-second 848x480 result.

    Two-image reference sample rendered as a six-second 848x480 clip.

Content test

Is Grok Imagine Video 1.5 uncensored? What we tested

Content levels tested on Grok Imagine Video 1.5, by mode
LevelImage to videoText to video
Mild
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Moderate
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Strong
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Very strong
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
Maximum
RefusedTested Nov 11, 2026
RefusedTested Nov 11, 2026
How we test

How each mode behaves

All modes
Generated video files are kept for 14 days, then deleted.
All modes
A requested clip must fit within 1–15 seconds.
Image to video
Use a closing image or loop mode; the two settings cannot be combined.
Image to video
Intermediate-frame guidance accepts at most four images.
Reference to video
Reference-led generation accepts 1–7 images and stops at 720p.

Use cases

What to build with the Grok Imagine Video 1.5 API

  • Dialogue-led story moments

    Build a short interaction around one quoted line and a visible response. The rooftop sample pairs a whispered invitation with a smile and a hand-taking action in a six-second clip with sound.

  • Transitions with a planned arrival

    Guide a change of setting with an intermediate image at a chosen second. Our alley-to-greenhouse test reached the sunny greenhouse at second three of a six-second shot.

  • Repeating motion from a still

    Animate an opening image with loop enabled for motion that returns to its start. Our loop test followed the matching-frame setting; inspect the playback join before using the clip in a repeating placement.

  • Scenes assembled from references

    Supply separate images for people, props, or locations and assign each an @image role in the prompt. The reference workflow accepts one to seven images, with a charge for each supplied reference.

  • Silent inserts for an existing edit

    Disable generated audio when the sequence will use an existing soundtrack. Our audio-off test returned no audio track, while the selected duration and resolution still determine the video rate.

Prompts

Grok Imagine Video 1.5 prompt examples you can copy

  • Text to video

    An invitation above the city

    Result from this prompt

    At a rooftop bar at dusk, a woman in a red backless dress leans close to a man and whispers: "Let's get out of here." He smiles, takes her hand, string lights and the city skyline behind them.

    Why it works. Assigns the line to one speaker and gives the second person a visible response. The linked sample demonstrates the rooftop exchange with its spoken line; the ages and wardrobe here are proposed variations.

    Try this prompt
  • Text to video

    A quiet closing-time exchange

    Inside a jazz lounge after the performance, a woman in her forties wearing a navy silk dress turns toward a man in his forties in an open-collar white shirt. She says, "One more song?" He nods. Amber table lamps, a relaxed mood, close two-person framing, slow camera push.

    Why it works. Keeps the dialogue short and assigns a separate action to each person. The clothing, lighting, and camera direction define the intended mood without adding a second setting.

    Try this prompt
  • Image to video

    A portrait begins to move

    Animate the woman in her forties from the opening image, wearing the same emerald evening dress. She turns slightly toward the window and smiles, then looks back toward the camera. Keep the warm window light and quiet hotel-lounge mood; use a restrained camera move.

    Why it works. Treats the opening still as the composition and asks for a small motion sequence. Upload the opening still, then pick the length and resolution on their own.

    Try this prompt
  • Image to video

    Lantern alley to greenhouse

    Result from this prompt

    A slow walk from a lantern alley into a sunlit greenhouse.

    Why it works. Describes the transition while the supplied keyframe controls its timing. Pair it with a six-second clip and a greenhouse keyframe placed at the three-second mark, as in our test.

    Try this prompt
  • Image to video

    Paper motion for a loop

    Result from this prompt

    The paper crane gently rocks in a soft breeze, seamless loop.

    Why it works. Suggests motion that returns to its starting position. Switch on the loop option and leave out a closing frame; the wording alone does not make the clip loop.

    Try this prompt
  • Reference to video

    A performer and a paper crane

    Result from this prompt

    The dancer from @image1 performs a slow contemporary routine while the paper crane from @image2 floats around him like a small bird, white studio, soft light.

    Why it works. Maps two uploads to different subjects before describing their interaction. This is a proposed variation on the linked reference scene; reference numbering must match upload order.

    Try this prompt
  • Reference to video

    A product in a new setting

    Use @image1 for a ceramic tea cup and @image2 for the glasshouse setting. Place the cup on a wooden table among the plants. Steam curls upward in warm morning light as the camera moves slowly closer, restful mood, no people in view.

    Why it works. Gives an object and a location separate reference roles, then requests one main movement. Select a reference count and output tier that fit the planned composition.

    Try this prompt

Pricing

Grok Imagine Video 1.5 API pricing

A 5-second clip starts at $0.14 at 480p and $0.45 at 1080p.

Get started

How to use the Grok Imagine Video 1.5 API in three steps

  1. Step 1

    Pick the source for the scene

    Choose text for a written shot, image-to-video for a required opening still, or reference-to-video for a composition guided by several images.

  2. Step 2

    Describe action and sound

    Name the subject, clothing, setting, light, and a manageable action. Put a spoken line in quotation marks and identify who delivers it.

  3. Step 3

    Choose timing and output

    Set 1-15 seconds, a supported aspect ratio, and the resolution tier. For still animation, add timed keyframes and choose an ending image or loop when needed.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

Grok Imagine Video 1.5 API FAQ

About Grok Imagine Video 1.5

Begin with the material you already have: a sentence for text-to-video, an opening still for image animation, or a set of numbered references for a new composition. The rooftop sample shows a short exchange with its quoted line on the soundtrack; the greenhouse transition demonstrates an image placed at a chosen moment. Select duration and resolution together, since both affect the bill, and remember the extra reference-image charge for reference-to-video. Check the delivered motion, sound, and dimensions, then download the accepted clip before the 14-day retention period ends.

All Grok models8

Video models1

  • Grok Imagine Video 1.5CurrentText to video · Image to video · +1From $0.028per output second

Text models4

Related models and next tasks