Ideogram AI Ideogram Vector Image To Vector API Documentation
Playground
Try it on WaveSpeedAI!Ideogram Vector Image-to-Vector converts images into editable SVG graphics, with detailed and simplified modes for logos, icons, and illustrations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Ideogram Vector Image-to-Vector converts an existing image into editable SVG artwork. Use it to turn raster images into scalable vector graphics while keeping the overall structure and style of the source image.
Why Choose This?
- Image-to-SVG conversion — Turn an existing image into editable vector artwork.
- Two conversion modes — Choose between higher detail or a simpler, cleaner result.
- Scalable graphics — Resize the SVG freely without raster pixelation.
- Simple workflow — Upload one image, choose a mode, and generate.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Source image to convert. Supports JPEG, PNG, and WebP, up to 50 MB. |
| mode | No | Conversion mode: default preserves finer details, while simple uses fewer and simpler shapes. Default: default. |
How to Use
- Upload an image — Provide the source image you want to convert.
- Choose a mode — Use
defaultfor more detail orsimplefor a cleaner result. - Submit — Generate and download the SVG output.
Pricing
$0.11 per generated SVG.
The price is the same for both default and simple modes.
Best Use Cases
- Raster logo conversion — Convert existing logo images into editable vector artwork.
- Scalable icons — Turn small raster graphics into SVG assets.
- Illustration cleanup — Rebuild simple artwork in vector form.
- Design workflows — Prepare editable graphics for further refinement.
Pro Tips
- Start with a clear, high-quality source image for the best result.
- Use
defaultmode when finer details are important. - Use
simplemode when you want fewer shapes and a cleaner design. - Review the output before production use, especially around text and small details.
Notes
- Only one input image is supported per request.
- Supported formats are JPEG, PNG, and WebP.
- The maximum input file size is
50 MB. - No text prompt is required or supported.
- Each request generates one SVG.
- Fine details may be simplified during conversion, so manual cleanup may still be useful for production workflows.
Related Models
- Ideogram Vector Text-to-Vector — Generate editable SVG graphics from text prompts.
- Ideogram Vector Image-to-Vector — Convert existing images into editable SVG vector graphics.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"mode": "default"
}
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/ideogram-ai/ideogram-vector/image-to-vector" \
-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 |
|---|---|---|---|---|---|
| image | string | Yes | 1 ~ unlimited characters · pattern: ^https?:// | Image to convert. JPEG, PNG or WebP, up to 50 MB. | |
| mode | string | No | default | default, simple | Default preserves finer details; simple uses fewer, simpler shapes. |
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 |