Ideogram 4.6 API
Render exact in-image text and logos at native 4K.
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) 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
https://api.segmind.com/v1/ideogram-4.6Parameters
promptrequiredstringDescribe the image and quote exact text to render in any language. Lead with the subject; keep in-image words short.
"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."backgroundoptionalstringtransparent returns a PNG with an alpha background (logos, stickers); auto lets the model decide.
"auto""auto""opaque""transparent"enable_copyright_detectionoptionalbooleanRuns a post-generation copyright check (adds latency). Leave off unless flagged images must be withheld.
falsemagic_promptoptionalstringPrompt expansion: auto or on rewrite it, off keeps it verbatim. Use off for strictly exact wording.
"auto""auto""on""off"qualityoptionalstringRender quality and price tier. Medium for most work, high for dense small text; very_low drafts at up to 2K.
"medium""very_low""low""medium""high"seedoptionalintegerRandom seed (0 to 2147483647) for reproducible results. Omit for a new variation each run.
sizeoptionalstringauto 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.
"auto""auto""auto_2k""auto_4k""1024x1024""2048x2048""2048x1152""1152x2048""2048x1376""1376x2048""4096x4096"+10 moreResponse 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
POST /v2/ideogram-4.6Submit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- 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.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out