Ideogram 4.6 Edit API

Edit image regions precisely with legible text, rest unchanged

PlaygroundAPI
Pricing
~25.28s
POST /v2/ideogram-4.6-edit · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "ideogram-4.6-edit",
 9    image="https://segmind-resources.s3.amazonaws.com/input/ideogram-4.6-edit-poster-src.jpg",
10    prompt="Set the headline 'IDEOGRAM 4.6' in bold condensed vintage letterpress capitals across the blank banner at the top, with a smaller sub-line 'NATIVE 4K' beneath it in spaced caps, inked in deep teal; keep the steam train, the stone viaduct, the snowy alpine peaks, the cream paper texture and the art-deco border unchanged",
11    quality="medium",
12)
13print(result["status"])                      # COMPLETED
14print(result.get("output"))                  # model output (e.g. media URL)
15print(result["metrics"]["inference_time"])   # server compute seconds
16
17# --- Or submit + poll manually (track request_id, control the cadence) ---
18from segmind import SegmindClient, InferenceFailed, InferenceTimeout
19
20client = SegmindClient()                      # reads SEGMIND_API_KEY
21payload = {
22    "image": "https://segmind-resources.s3.amazonaws.com/input/ideogram-4.6-edit-poster-src.jpg",
23    "prompt": "Set the headline 'IDEOGRAM 4.6' in bold condensed vintage letterpress capitals across the blank banner at the top, with a smaller sub-line 'NATIVE 4K' beneath it in spaced caps, inked in deep teal; keep the steam train, the stone viaduct, the snowy alpine peaks, the cream paper texture and the art-deco border unchanged",
24    "quality": "medium",
25}
26job = client.submit_async("ideogram-4.6-edit", **payload)
27print(job.request_id)                         # available immediately
28try:
29    result = job.wait(timeout=600, interval=1.0)
30except InferenceTimeout as e:
31    print("still running:", e.request_id)
32except InferenceFailed as e:
33    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/ideogram-4.6-edit

Parameters

imagerequired
string (uri)

The image to edit (JPEG, PNG or WebP, up to 25MB, aspect 1:6 to 6:1). The result keeps its size; inputs over 2048x2048 are billed at the 4K price.

Default: "https://segmind-resources.s3.amazonaws.com/input/ideogram-4.6-edit-poster-src.jpg"
promptrequired
string

Describe only the change, not the mask. Put exact text in quotes and name the lettering style for legible results.

Default: "Set the headline 'IDEOGRAM 4.6' in bold condensed vintage letterpress capitals across the blank banner at the top, with a smaller sub-line 'NATIVE 4K' beneath it in spaced caps, inked in deep teal; keep the steam train, the stone viaduct, the snowy alpine peaks, the cream paper texture and the art-deco border unchanged"
context_windowoptional
string

Region to edit at full resolution: auto fits it around the mask, none edits the whole image, or y_min,x_min,y_max,x_max in pixels (up to 4096x4096).

enable_copyright_detectionoptional
boolean

Runs a post-generation copyright check (adds latency). Leave off unless flagged images must be withheld.

Default: false
maskoptional
string (uri)

Optional mask the same size as the image: black marks the area to edit, white keeps the rest. A mask limits reference images to 3.

qualityoptional
string

Render quality and price tier. Medium for most edits, high for print-grade or dense text; very_low renders at up to 2K.

Default: "medium"
Allowed values :
Very Low→"very_low"
Low→"low"
Medium→"medium"
High→"high"
reference_imagesoptional
string[]

Up to 4 images (3 with a mask) to bring in a product, logo, pattern or style; they are never edited themselves.

Default: []
seedoptional
integer

Random seed (0 to 2147483647) for reproducible edits. Omit for a new variation each run.

Range: 0 - 2147483647

Response Type

Returns: Image

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/ideogram-4.6-edit

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out