X AI Grok Imagine Image V2.0 Edit API Documentation
Playground
Try it on WaveSpeedAI!xAI Grok Imagine Image V2.0 Edit transforms input images with text prompts, with configurable resolution and quality for precise image editing, visual refinements, creative variations, social content, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Grok Imagine Image V2.0 Edit transforms one to three source images with natural-language instructions. It is designed for prompt-guided image editing with configurable resolution and quality, making it suitable for creative iteration, visual refinement, and marketing asset updates.
Parameters
| Parameter | Required | Description |
|---|---|---|
| images | Yes | Input images to edit, as an array of 1 to 3 images. |
| prompt | Yes | Text instruction describing the desired edit. |
| resolution | No | Output resolution: 1k or 2k. Default: 2k. |
| quality | No | Generation quality: low or medium. Default: medium. |
How to Use
- Upload 1 to 3 source images in the
imagesarray. - Write a clear edit prompt describing what should change.
- Choose the output
resolutionandqualitytier. - Submit the request and retrieve the edited image URL.
Pricing
| Resolution | Quality | Price per image |
|---|---|---|
| 1k | low | $0.04 |
| 1k | medium | $0.06 |
| 2k | low | $0.06 |
| 2k | medium | $0.08 |
Each input image adds $0.01.
| Example | Price |
|---|---|
| 1 image, 1k low | $0.05 |
| 1 image, 2k medium (default) | $0.09 |
| 3 images, 2k medium | $0.11 |
Best Use Cases
- Prompt-guided image editing — Transform an existing image with simple natural-language instructions.
- Style and visual changes — Adjust mood, color, composition, or overall style.
- Product and marketing updates — Refine product shots, campaign assets, and promotional visuals.
- Creative iteration — Explore multiple edit directions from the same source image.
Related Models
- Grok Imagine Image V2.0 Text-to-Image — Generate images from natural-language prompts.
- Grok Imagine Image V2.0 Edit — Edit images with text instructions.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"resolution": "2k",
"quality": "medium"
}
JSON
)
# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 \
-X POST "https://api.wavespeed.ai/api/v3/x-ai/grok-imagine-image-v2.0/edit" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}"); then
printf 'Submit failed. %s\n' "${CHECK}" >&2
exit 1
fi
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
# Transient errors (429, 5xx) are retried, honoring Retry-After.
HTTP_CODE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
--output "${BODY_FILE}" --write-out '%{http_code}' \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
case "${HTTP_CODE}" in
2??) ;;
000|429|5??) # dropped connection or temporary error: keep polling
printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
sleep 10; continue ;;
*) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
cat "${BODY_FILE}" >&2; exit 1 ;;
esac
RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted)
printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| images | array<string> | Yes | - | 0 ~ 3 items | Input images to edit, 1 to 3. Supports jpg, jpeg, png, and webp. |
| prompt | string | Yes | 1 ~ unlimited characters | Text instruction describing how to edit the image. | |
| resolution | string | No | 2k | 1k, 2k | Output image resolution tier. |
| quality | string | No | medium | low, medium | Generation quality tier. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |