Grok Imagine 1.5 API Pricing: $0.0114 per Second at 480p

TL;DR

• Grok Imagine 1.5 is xAI's image-to-video model. On HiAPI it is billed per second: $0.0114/s at 480p, $0.0214/s at 720p, and $0.057142/s at 1080p. A 6-second 480p clip costs $0.0684.
• Duration is anything from 1 to 15 seconds, and cost scales linearly with it. Failed tasks are not charged.
• You can try it in the browser on the model page playground without writing code. New accounts get 200 credits ($0.10), enough for one 6-second 480p clip.

Price table

Model	Endpoint	480p / second	720p / second	1080p / second
Grok Imagine 1.5 grok-imagine-1.5/image-to-video	Image-to-video	$0.0114	$0.0214	$0.057142
Grok Imagine grok-imagine/text-to-video	Text-to-video	$0.0114	$0.0214	$0.057142
Grok Imagine grok-imagine/image-to-video	Image-to-video	$0.0114	$0.0214	$0.057142

HiAPI public resolution-policy prices, checked October 22, 2026. Multiply the selected tier by the requested duration; check the live estimate before submitting.

All three endpoints cost the same per second. For 1.5, use 1–7 reference images at 480p or 720p, or exactly one image at 1080p. Duration is an integer from 1 to 15 seconds. For a text-only starting point, choose grok-imagine/text-to-video instead.

Cost by duration

Duration	480p	720p	1080p
1 second	$0.0114	$0.0214	$0.057142
6 seconds	$0.0684	$0.1284	$0.342852
8 seconds (default)	$0.0912	$0.1712	$0.457136
10 seconds	$0.114	$0.214	$0.57142
15 seconds	$0.171	$0.321	$0.85713

$10 covers about 877 seconds at 480p or 467 seconds at 720p. Note that duration defaults to 8 seconds, so if you leave it out you are billed for 8.

What you get

This example from the model page uses a jellyfish illustration as the start frame, at 720p for 6 seconds.

The giant jellyfish slowly pulses and drifts upward, its lace tentacles flowing gracefully, the school of silver fish spirals around it, tiny plankton particles drift past the camera, gentle cinematic push-in, smooth natural motion, consistent lighting across frames

Generate with this prompt → (upload your own image, then manually select 6 seconds and 720p)

grok-imagine-1.5/image-to-video, 720p, 6 seconds: the current estimated cost is $0.1284, or $0.0684 at 480p. This is a recalculated budget, not a new generation run.

Choose a resolution for your budget

A 6-second clip is $0.0684 at 480p, $0.1284 at 720p, or $0.342852 at 1080p. Start at 480p to test motion, then choose the tier your delivery needs. The 1080p tier accepts one reference image only.

For a current comparison with other models, use the live model pricing table. Different models have different input, duration, and audio settings, so a matching headline price is not a like-for-like comparison.

Try it in the playground

1. Open the Grok Imagine 1.5 model page and sign up or log in.
2. Upload an image and describe what should happen next. The prompt is optional and works best in English.
3. Pick duration, resolution, and aspect ratio, then generate.

API call

curl -X POST https://api.hiapi.ai/v1/tasks \
  -H "Authorization: Bearer $HIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-1.5/image-to-video",
    "input": {
      "image_urls": ["https://your-cdn.example.com/start.jpg"],
      "prompt": "camera slowly pushes in, the subject turns toward the light",
      "resolution": "480p",
      "duration": 6,
      "aspect_ratio": "auto"
    }
  }'

• image_urls accepts 1–7 images at 480p or 720p, but exactly one at 1080p: JPEG, PNG, or WebP, up to 20 MB each. SVG is not supported.
• resolution defaults to 480p, duration to 8 seconds, and aspect_ratio to auto. With a single reference image the output follows that image and aspect_ratio has no effect. With multiple reference images, you can also choose 1:1, 16:9, 9:16, 3:2, or 2:3.
• The call returns a taskId. Poll GET /v1/tasks/{taskId} for the result, and download output[0].url right away, since it is a temporary link.

FAQ

Does Grok Imagine 1.5 do text-to-video?

On HiAPI, 1.5 is image-to-video only. For text-only prompts, use the previous-generation grok-imagine/text-to-video, which costs the same.

Can it output 1080p?

Yes. The current public schema offers 480p, 720p, and 1080p. At 1080p, pass exactly one reference image. This is a quality tier; actual pixel dimensions follow the input aspect ratio.

Am I charged for failed tasks?

No. You are billed only for clips that generate successfully.

Should I use 1.5 or the previous generation?

Use 1.5 for image-to-video with 1–15 seconds of requested duration; it also accepts multiple reference images at 480p and 720p. For text-to-video, use grok-imagine/text-to-video. Check each model’s current inputs before switching; the listed resolution-policy prices are the same at the time of this check.

To try it, upload an image on the Grok Imagine 1.5 model page. Every model's price is on the pricing page.