In early October 2026, xAI added Grok Imagine Video 1.5 Lite (grok-imagine-video-1.5-lite) to its API — a lighter version of the Grok Imagine Video 1.5 model. Lite is distilled from the full model and trades some quality for price and speed. xAI explicitly recommends it for simple videos.
What Grok Imagine Video 1.5 Lite can do
- Clips with audio. Sound effects, ambience and lip-synced speech are generated together with the video, so no separate voiceover is needed.
- Length: 1 to 15 seconds.
- Resolution: 480p, 720p and 1080p. Lite renders natively up to 720p and upscales to 1080p.
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 and 5:2. When animating a photo, the aspect ratio follows the source image.
- Modes: text-to-video and image-to-video. For text prompts, the model first draws an opening frame and then animates it.
How Lite differs from the full Video 1.5
| Video 1.5 Lite | Video 1.5 | |
|---|---|---|
| 1080p | upscaled from 720p | native |
| Length | 1–15 s | 1–15 s |
| Audio and speech | yes | yes |
| References | no | up to 14 images |
| Voices | no | up to 3 voices |
| First and last frame | no | yes |
| Keyframes | no | up to 4 |
| API price, 1080p | $0.14 per second | higher |
Lite is the pick for a quick, cheap clip from a single prompt or photo. For a scene with a specific character, voice or ending, you need the full Video 1.5. Our Grok Video guide covers it in detail.
Pricing and availability
In the xAI API, Lite costs $0.02 per second at 480p, $0.03 at 720p and $0.14 at 1080p, plus $0.01 per input image. A 10-second 720p clip comes to $0.30. The model is available in the xAI API and supports the Batch API.
How to try it in AI2Face
Grok Imagine is available in the AI2Face generator alongside other video models with audio: Veo 3.1, Kling and Seedance. It’s easy to compare them on the same prompt or photo, and the cost is shown before each generation. For an overview of all options, see our guide to AI video generators.
FAQ
How much does Grok Imagine Video 1.5 Lite cost?
In the xAI API it's $0.02 per second at 480p, $0.03 at 720p and $0.14 at 1080p. An input image costs $0.01. Lite at 1080p costs the same as the full Video 1.5 at 720p.
How is Grok Imagine Video 1.5 Lite different from Video 1.5?
Lite only accepts text and a single first-frame image, and its 1080p is upscaled from 720p. The full Video 1.5 renders 1080p natively and supports up to 14 references, 3 voices, first and last frames and up to 4 keyframes.
How long are Grok Imagine Video 1.5 Lite clips?
From 1 to 15 seconds, with audio and lip-synced speech, in 9 aspect ratios from 1:1 and 9:16 up to 21:9.
Sources
4
- https://docs.x.ai/developers/models/grok-imagine-video-1.5-lite
- https://docs.x.ai/developers/model-capabilities/video/overview
- https://docs.x.ai/developers/model-capabilities/video/generation
- https://openrouter.ai/x-ai/grok-imagine-video-1.5-lite
