GPT Image 1.5 Edit Serverless API

Precise image editing via natural language instructions.

~43.95s
POST /v2/gpt-image-1.5-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    "gpt-image-1.5-edit",
 9    prompt="A photorealistic wide drone shot of a colossal man (exact face/body from the reference) casually sitting across a London street, one knee raised, hand resting. He wears a navy overcoat, knit sweater, dark trousers, boots, and a minimalist beanie. Tiny cars, buses, bikes, and pedestrians move around him, with classic London red-brick buildings, black lamps, and cobblestone streets dwarfed by his size. Soft overcast London daylight highlights wet pavement.",
10    image_urls=["https://segmind-resources.s3.amazonaws.com/input/92a8e420-2d12-48c0-97f5-73c6c4820c34-black-man-image.jpeg"],
11    mask=None,
12    size="auto",
13    quality="high",
14    background="opaque",
15    output_compression=100,
16    output_format="png",
17    moderation="auto",
18)
19print(result["status"])                      # COMPLETED
20print(result.get("output"))                  # model output (e.g. media URL)
21print(result["metrics"]["inference_time"])   # server compute seconds
22
23# --- Or submit + poll manually (track request_id, control the cadence) ---
24from segmind import SegmindClient, InferenceFailed, InferenceTimeout
25
26client = SegmindClient()                      # reads SEGMIND_API_KEY
27payload = {
28    "prompt": "A photorealistic wide drone shot of a colossal man (exact face/body from the reference) casually sitting across a London street, one knee raised, hand resting. He wears a navy overcoat, knit sweater, dark trousers, boots, and a minimalist beanie. Tiny cars, buses, bikes, and pedestrians move around him, with classic London red-brick buildings, black lamps, and cobblestone streets dwarfed by his size. Soft overcast London daylight highlights wet pavement.",
29    "image_urls": ["https://segmind-resources.s3.amazonaws.com/input/92a8e420-2d12-48c0-97f5-73c6c4820c34-black-man-image.jpeg"],
30    "mask": None,
31    "size": "auto",
32    "quality": "high",
33    "background": "opaque",
34    "output_compression": 100,
35    "output_format": "png",
36    "moderation": "auto",
37}
38job = client.submit_async("gpt-image-1.5-edit", **payload)
39print(job.request_id)                         # available immediately
40try:
41    result = job.wait(timeout=600, interval=1.0)
42except InferenceTimeout as e:
43    print("still running:", e.request_id)
44except InferenceFailed as e:
45    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/gpt-image-1.5-edit

Parameters

image_urlsrequired
string[]

Links to reference images.

maskrequired
string (uri)

Image to be used as a base. Leave null to upload later.

promptrequired
string

Text prompt guides image generation. Example: 'A cyberpunk city skyline at night.'

Default: ""
backgroundoptional
string

Background type for the image. Transparent is useful for overlays.

Default: "opaque"
Allowed values :
"transparent""opaque"
moderationoptional
string

Sets moderation strictness. 'low' relaxes content restrictions.

Default: "auto"
Allowed values :
"low""auto"
output_compressionoptional
integer

Defines output image compression level. Use 100 for best quality.

Default: 95
output_formatoptional
string

Specifies the output image format. Use 'png' for high-quality needs.

Default: "png"
Allowed values :
"png""jpeg""webp"
qualityoptional
string

Sets visual quality. 'auto' balances detail and performance.

Default: "high"
Allowed values :
"low""medium""high""auto"
sizeoptional
string

Choose image resolution. 'auto' balances speed and quality.

Default: "auto"
Allowed values :
"1024x1024""1536x1024""1024x1536""auto"

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/gpt-image-1.5-edit

    Submitreturns request_id, status_url, response_url

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

    Polluntil COMPLETED or FAILED

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

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (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