Grok Imagine Video 1.5 creates videos from text, a starting image or reference images, with durations from 1 to 15 seconds. On Raywake, text to video costs $0.13 per second at 480p, $0.23 at 720p and $0.40 at 1080p. The separate 1.5 Lite text operation lists upper-bound per-video prices of $0.23, $0.34 and $1.56 respectively. Reference mode supports 480p and 720p only.
Open Grok Imagine Video 1.5 or Grok Imagine Video 1.5 Lite to choose a text workflow. The available image and reference operations use different inputs and pricing units. Prices are as of 31 October 2026.
Grok Imagine Video 1.5 at a glance
| Operation | Required inputs | Duration | Resolution |
|---|---|---|---|
| 1.5 text to video | prompt | 1 to 15 seconds, default 6 | 480p, 720p, 1080p |
| 1.5 Lite text to video | prompt | 1 to 15 seconds, default 6 | 480p, 720p, 1080p |
| 1.5 image to video | prompt and image_url | 1 to 15 seconds, default 6 | 480p, 720p, 1080p |
| 1.5 reference to video | prompt and reference_image_urls | 1 to 15 seconds, default 8 | 480p, 720p |
Standard text and image generation include audio. Audio support is not confirmed for Lite or reference mode; choose standard text or image generation if sound is essential.
How much does Grok Imagine Video 1.5 cost?
Standard text generation has a per-second rate. Multiply that rate by the requested video duration to compare the listed options.
| Standard text resolution | Per second | 6-second example | 15-second example |
|---|---|---|---|
| 480p | $0.13 | $0.78 | $1.95 |
| 720p | $0.23 | $1.38 | $3.45 |
| 1080p | $0.40 | $2.40 | $6.00 |
The other operations have maximum prices, not that per-second schedule.
| Operation and setting | Catalog price |
|---|---|
| Lite text, 480p | Up to $0.23 per video |
| Lite text, 720p | Up to $0.34 per video |
| Lite text, 1080p | Up to $1.56 per video |
| Standard image, default options | Up to $1.35 per run |
| Standard reference, default options | Up to $1.15 per run |
Do not multiply the Lite prices by seconds. Likewise, do not treat a default-options upper bound as a fixed rate for every resolution and duration. Request a quote with the actual inputs before setting your production budget.
Which input mode should you use?
Use text to video when the scene can start from a written brief. Describe the subject, action and camera movement together. The standard text operation also generates audio, so the desired atmosphere can be part of the scene description.
Use image to video when an existing image is the starting material. Its required field is singular, image_url. That operation does not list an aspect_ratio field, so do not copy the text request unchanged and add a picture.
Use reference to video when you want to guide a scene using a group of images. It accepts one to seven reference images. That is a different request from animating one starting image, and it has its own default duration and resolution.
Which one should you use, standard or Lite?
Compare the two text operations if your starting point is a prompt. Lite has lower listed prices, but the pricing units differ. Get matching quotes for your intended duration and resolution before making a budget decision.
To compare speed and quality, keep the scene and frame shape constant, then judge the motion and composition against your brief. Treat “Lite” as a model name, not evidence that every request finishes sooner.
How to call Grok Imagine Video 1.5 through the API
This quote example uses the standard text endpoint with its default duration and resolution. It requests landscape framing explicitly.
curl --fail-with-body https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"xai/grok-imagine-video/v1.5/text-to-video","input":{"prompt":"An astronaut walks across a rocky plain beneath a ringed planet, slow tracking camera, quiet footsteps","duration":6,"resolution":"720p","aspect_ratio":"16:9"}}'For Lite text, replace the model ID with xai/grok-imagine-video/v1.5/lite/text-to-video. The image operation is xai/grok-imagine-video/v1.5/image-to-video; add image_url and omit aspect_ratio.
Reference mode uses xai/grok-imagine-video/v1.5/reference-to-video and reference_image_urls. Set resolution to 480p or 720p, since 1080p is not listed there. The quotes reference explains the quote response and subsequent request flow.
Common questions
How long can Grok Imagine Video 1.5 clips be?
All four operations described here accept an integer duration from 1 to 15 seconds.
Does reference mode support 1080p?
No. Its listed resolutions are 480p and 720p. Text and image modes also list 1080p.
How many reference images can I supply?
The reference operation describes one to seven images. Send them using reference_image_urls.
Does Lite have the same audio support?
Audio support is confirmed for standard text and image generation. If sound is essential, choose one of those operations; Lite audio support is not confirmed.
Create a video with Grok Imagine 1.5