imagesarray
List of URLs of the images to edit. A maximum of 3 images are supported.
Grok Imagine Image Edit
xai/grok-imagine-image/editGrok Imagine Image Edit is xAI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.
Try the model
Playground
Input
Text description of the desired image.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
List of URLs of the images to edit. A maximum of 3 images are supported.
Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution. Allowed values: 1k, 2k.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The format of the generated image. Allowed values: jpeg, png.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "Make this scene more realistic but still keep the game vibes" }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Image Editing
- Rank
- #26 of 77
- Elo
- 1073 ±13
- Gap to #1
- −126
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
- #21MAI-Image-2.5-Flash1091±13
- #22Qwen-Image-3.0-Pro1091±13
- #23Fibo 2.01088±14
- #24Qwen-Image-2.11081±13
- #25Luma UNI 1 Max1079±13
- #26grok-imagine-image1073±13
- #27FLUX 3 Image Klein1072±14
- #28Ideogram 4.5 (High)1070±15
- #29Qwen-Image-2.1-Pro1069±13
- #30Qwen-Image-3.01068±13
Grok Imagine Image Edit
Grok Imagine Image edit (standard): fast, low-cost image edits.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 8,000 characters. |
images | image URL[] | — | Images to edit or combine, Image 1, Image 2, … |
resolution | 1k / 2k | 1k | Sets the per-image rate. |
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 | — | Output shape. |
output_format | jpeg / png | jpeg | Output file format. |
Billing
$0.02 per output image plus $0.002 per input image.
| Request | Price |
|---|---|
| 1 input image | $0.022 |
| 3 input images | $0.026 |
Failed runs are not charged.
Prompting
- Quote any text that must appear.
Limits
- One output image per request.
Also on SandBase
Other Grok Imagine Image endpoints: xai/grok-imagine-image/quality, xai/grok-imagine-image/quality/edit, xai/grok-imagine-image/2.0/text-to-image, xai/grok-imagine-image/2.0/edit.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "xai/grok-imagine-image/edit",
"images": [
"https://static.sandbase.ai/examples/xai/grok-imagine-image/edit/input_images_0.png"
],
"prompt": "Make this scene more realistic but still keep the game vibes",
"resolution": "1k",
"output_format": "jpeg"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
promptstringrequired
Text description of the desired image.
resolutionstring
Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution.
Default: "1k"
Possible values: "1k", "2k"
aspect_ratiostring
The aspect ratio of the generated image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
output_formatstring
The format of the generated image.
Default: "jpeg"
Possible values: "jpeg", "png"
{
"model": "xai/grok-imagine-image/edit",
"images": [
"https://static.sandbase.ai/examples/xai/grok-imagine-image/edit/input_images_0.png"
],
"prompt": "Make this scene more realistic but still keep the game vibes",
"resolution": "1k",
"output_format": "jpeg"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "xAI schema mirror",
"source_url": "https://docs.x.ai/",
"url": "https://static.sandbase.ai/examples/fef66c03-8926-4e6f-962b-7c117da372e4/output/b2da9da9-9e53-44f9-86fd-2363ac37b163.jpg"
}
]