grok-imagine-image-2.0 · xAI · image · 3 modes: text-to-image, image-to-image, reference-to-image.
This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls
get_model with the mode.Text To Image
Modetext-to-image. Text to image.
Input
Pricing
1.94–3.87 credits per image by quality and resolution (generate defaults to low, edit to medium), + 0.48 per input image. Fixed price: charged as estimated. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
Image To Image
Modeimage-to-image. Edit one image.
Input
References: up to 1: 1 images. Assets, URLs and elements are accepted.
Pricing
1.94–3.87 credits per image by quality and resolution (generate defaults to low, edit to medium), + 0.48 per input image. Fixed price: charged as estimated. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
Reference To Image
Modereference-to-image. Compose an image from 1 to 5 reference images, referred to as <IMAGE_0>, <IMAGE_1>… in the prompt.
Input
References: up to 5: 5 images. Assets, URLs and elements are accepted.
Pricing
1.94–3.87 credits per image by quality and resolution (generate defaults to low, edit to medium), + 0.48 per input image. Fixed price: charged as estimated. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
