xAI
Grok Imagine API
xAI's Grok Imagine line — image and short video, with the longest clips per dollar we carry.
3
models in the line
Grok Imagine is xAI's generation line, covering both images and short video. Its distinguishing feature is duration: the video model accepts anything from 6 to 30 seconds in six fixed steps, at a price that starts under two cents — unusually cheap for clips that long. The image tiers are flat-priced regardless of framing.
At a glance
- From
- $0.016 / second
- Modes
- Text to video, Image to video, Text to image, Image to image
- Resolutions
- 480p, 720p
- Durations
- 6, 10, 15, 20, 25, 30 seconds
- Aspect ratios
- 16:9, 9:16, 1:1, 3:2, 2:3, 3:4, 4:3
Models in this family
| Model | From | Modes | Open |
|---|---|---|---|
| Grok Imagine 1.5 VideoGenerate short video from text or animate a reference image. | $0.016/ second | Text to video, Image to video | OpenDocs |
| Grok Imagine 1.5 ImageGenerate or transform images from a prompt and optional reference image. | $0.023/ generation | Text to image, Image to image | OpenDocs |
| Grok Imagine 2.0 ImageGenerate batches of images from a text prompt in common aspect ratios. | $0.023/ generation | Text to image | OpenDocs |
Pricing
| Model | Option | Price |
|---|---|---|
| Grok Imagine 1.5 Video | 480p | $0.016/ second |
| Grok Imagine 1.5 Video | 720p | $0.029/ second |
| Grok Imagine 1.5 Image | Standard | $0.023/ generation |
| Grok Imagine 2.0 Image | Standard | $0.023/ generation |
Which one to pick
Grok Imagine 1.5 Video
Short video from a prompt, or animating a still. Duration from 6 to 30 seconds at 480p or 720p.
Grok Imagine 1.5 Image
Image generation that can also transform a reference image.
Grok Imagine 2.0 Image
Batch image generation from a text prompt, with more aspect ratios than 1.5 — but no reference input.
Strengths
- Video duration reaches 30 seconds in six fixed steps, which only Seedance 2.5 also matches.
- Image and video share one vendor and one key.
- Flat image pricing — framing choice does not change the cost.
Limitations
- Video stops at 720p; there is no 1080p or 4K option in this line.
- Grok Imagine 2.0 dropped reference-image input, so image-to-image work has to stay on 1.5.
- The two image tiers are priced identically, so 2.0 costs the same as 1.5 while accepting less.
The vendor's own description of this line: xAI — models
Guides
- Text to videoWhich text-to-video model fits the shot you have in mind, prompts that actually work, and the full API run from create to finished file.9 min read
- Image to videoTurning a still into a shot — which model to animate it with, first and last frame control, motion transfer, and the prompts that keep the subject intact.8 min read
- Going to productionKey handling, webhooks over polling, idempotency, terminal states, retry policy by error code, balance monitoring, rate limits and media storage.10 min read