Ideogram 4.6 API

Render exact in-image text and logos at native 4K.

PlaygroundAPI
Pricing
~20.07s
POST /v2/ideogram-4.6 · 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",
 9    prompt="A vintage letterpress travel poster for a mountain railway. Bold headline text reads 'IDEOGRAM 4.6' and a smaller line reads 'NATIVE 4K'. Warm cream paper texture, deep teal and burnt orange inks, a steam train crossing a stone viaduct at sunrise.",
10    size="auto",
11    quality="medium",
12    background="auto",
13    magic_prompt="auto",
14    enable_copyright_detection=False,
15)
16print(result["status"])                      # COMPLETED
17print(result.get("output"))                  # model output (e.g. media URL)
18print(result["metrics"]["inference_time"])   # server compute seconds
19
20# --- Or submit + poll manually (track request_id, control the cadence) ---
21from segmind import SegmindClient, InferenceFailed, InferenceTimeout
22
23client = SegmindClient()                      # reads SEGMIND_API_KEY
24payload = {
25    "prompt": "A vintage letterpress travel poster for a mountain railway. Bold headline text reads 'IDEOGRAM 4.6' and a smaller line reads 'NATIVE 4K'. Warm cream paper texture, deep teal and burnt orange inks, a steam train crossing a stone viaduct at sunrise.",
26    "size": "auto",
27    "quality": "medium",
28    "background": "auto",
29    "magic_prompt": "auto",
30    "enable_copyright_detection": False,
31}
32job = client.submit_async("ideogram-4.6", **payload)
33print(job.request_id)                         # available immediately
34try:
35    result = job.wait(timeout=600, interval=1.0)
36except InferenceTimeout as e:
37    print("still running:", e.request_id)
38except InferenceFailed as e:
39    print("failed:", e.detail)

API Endpoint

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

Parameters

promptrequired
string

Describe the image and quote exact text to render in any language. Lead with the subject; keep in-image words short.

Default: "A vintage letterpress travel poster for a mountain railway. Bold headline text reads 'IDEOGRAM 4.6' and a smaller line reads 'NATIVE 4K'. Warm cream paper texture, deep teal and burnt orange inks, a steam train crossing a stone viaduct at sunrise."
backgroundoptional
string

transparent returns a PNG with an alpha background (logos, stickers); auto lets the model decide.

Default: "auto"
Allowed values :
Auto→"auto"
Opaque→"opaque"
Transparent→"transparent"
enable_copyright_detectionoptional
boolean

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

Default: false
magic_promptoptional
string

Prompt expansion: auto or on rewrite it, off keeps it verbatim. Use off for strictly exact wording.

Default: "auto"
Allowed values :
Auto→"auto"
On→"on"
Off→"off"
qualityoptional
string

Render quality and price tier. Medium for most work, high for dense small text; very_low drafts at up to 2K.

Default: "medium"
Allowed values :
Very Low→"very_low"
Low→"low"
Medium→"medium"
High→"high"
seedoptional
integer

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

Range: 0 - 2147483647
sizeoptional
string

auto and auto_2k render at 2K; auto_4k and any size over 2048x2048 render at 4K and cost the 4K price. Any WIDTHxHEIGHT works: sides a multiple of 32, 256 to 8192px, at most 4096x4096 pixels, aspect up to 6:1.

Default: "auto"
Allowed values (20 total):
"auto""auto_2k""auto_4k""1024x1024""2048x2048""2048x1152""1152x2048""2048x1376""1376x2048""4096x4096"+10 more

Response Type

Returns: Text/JSON

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

    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