xAI Grok Imagine v2 Image edit pricing
x-ai/grok-imagine-image-v2.0/edit
xAI's Grok Imagine v2 edit endpoint. No aspect ratio parameter, yet two resolution tiers and two quality steps, plus a charge for every input image.
What it costs
Per image, and what that comes to at volume. Every figure is computed through the same function the app estimates a real run with.
| Tier | per image | 1 image | 10 images | 100 images | 1,000 images |
|---|---|---|---|---|---|
| low, 1k | $0.05 | $0.05 | $0.50 | $5.00 | $50.00 |
| low, 2k | $0.07 | $0.07 | $0.70 | $7.00 | $70.00 |
| medium, 1k | $0.07 | $0.07 | $0.70 | $7.00 | $70.00 |
| medium, 2k | $0.09 | $0.09 | $0.90 | $9.00 | $90.00 |
- Sizing
- none, output tracks the input
- Max input images
- 3
Things that catch people out
- Bills $0.01 for every input image, the first included.
- Takes no aspect_ratio at all, so the output follows image 1. Its text-to-image sibling offers thirteen ratios, including 19.5:9 and 20:9.
- Accepts at most 3 input images.
What it accepts
Reference image
Takes input images, which is what holds a persona's face consistent between runs.
Aspect ratio
No aspect control on this endpoint.
Resolution tiers
2 tiers, and they are priced differently.
Quality control
2 steps (low, medium), each priced differently.
Web search
Not offered on this endpoint.
Image search
Not offered on this endpoint.
Others in this lane
Image to image. You supply one or more reference images and a prompt, and the model returns a new image of the same subject. This is the lane every persona workflow runs on, because the reference is what holds the face steady.