Seedream 4.5 Serverless API

Photorealistic image generation with precise text understanding.

PlaygroundHistory
API
Pricing
~31.85s
POST /v2/seedream-4.5 · 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    "seedream-4.5",
 9    size="2K",
10    width=2048,
11    height=2048,
12    prompt="Create a professional H&M clothing brand photoshoot of the man wearing all the reference clothes, striking confident model poses against an urban city street background with skyscrapers and vibrant daylight.",
13    max_images=1,
14    image_input=["https://segmind-inference-inputs.s3.amazonaws.com/273f368e-3274-4a6e-8a2c-2cdd5881948e-d61283c9-839e-4107-9185-4ea883ecaded.webp", "https://segmind-inference-inputs.s3.amazonaws.com/d47c85b4-f584-45e7-97ea-2ae0eeae4880-548c2fcfa1e14e301329ef45b8e093af.jpg", "https://segmind-inference-inputs.s3.amazonaws.com/d4545759-47ba-4c92-afa3-49fb260e8c51-IMG_7135.webp", "https://segmind-inference-inputs.s3.amazonaws.com/2d803ba1-7c89-4d54-996f-11c9572d8db9-IMG_7137.webp", "https://segmind-inference-inputs.s3.amazonaws.com/a461a78b-6db9-443a-8882-69ed7ccc2390-IMG_7138.webp"],
15    aspect_ratio="match_input_image",
16    sequential_image_generation="disabled",
17)
18print(result["status"])                      # COMPLETED
19print(result.get("output"))                  # model output (e.g. media URL)
20print(result["metrics"]["inference_time"])   # server compute seconds
21
22# --- Or submit + poll manually (track request_id, control the cadence) ---
23from segmind import SegmindClient, InferenceFailed, InferenceTimeout
24
25client = SegmindClient()                      # reads SEGMIND_API_KEY
26payload = {
27    "size": "2K",
28    "width": 2048,
29    "height": 2048,
30    "prompt": "Create a professional H&M clothing brand photoshoot of the man wearing all the reference clothes, striking confident model poses against an urban city street background with skyscrapers and vibrant daylight.",
31    "max_images": 1,
32    "image_input": ["https://segmind-inference-inputs.s3.amazonaws.com/273f368e-3274-4a6e-8a2c-2cdd5881948e-d61283c9-839e-4107-9185-4ea883ecaded.webp", "https://segmind-inference-inputs.s3.amazonaws.com/d47c85b4-f584-45e7-97ea-2ae0eeae4880-548c2fcfa1e14e301329ef45b8e093af.jpg", "https://segmind-inference-inputs.s3.amazonaws.com/d4545759-47ba-4c92-afa3-49fb260e8c51-IMG_7135.webp", "https://segmind-inference-inputs.s3.amazonaws.com/2d803ba1-7c89-4d54-996f-11c9572d8db9-IMG_7137.webp", "https://segmind-inference-inputs.s3.amazonaws.com/a461a78b-6db9-443a-8882-69ed7ccc2390-IMG_7138.webp"],
33    "aspect_ratio": "match_input_image",
34    "sequential_image_generation": "disabled",
35}
36job = client.submit_async("seedream-4.5", **payload)
37print(job.request_id)                         # available immediately
38try:
39    result = job.wait(timeout=600, interval=1.0)
40except InferenceTimeout as e:
41    print("still running:", e.request_id)
42except InferenceFailed as e:
43    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/seedream-4.5

Parameters

promptrequired
string

Describe the image. Include subjects like 'serene evening at the beach'.

aspect_ratiooptional
string

Image proportions. 'match_input_image' (recommended with image_input) lets API match input aspect ratio and optimize quality. Other ratios (1:1, 16:9, 9:16, etc.) calculate dimensions from size preset. Note: Non-square ratios with 4K may produce lower pixel counts than maximum (e.g., 9:16 gives ~9M pixels vs 16.7M max). Ignored when size is set to custom and both height and width are provided

Default: "match_input_image"
Allowed values :
"match_input_image""1:1""4:3""3:4""16:9""9:16""3:2""2:3""21:9"
heightoptional
integer

Custom height in pixels (only when size='custom'). Range: 1024-4096. Total pixels (width × height) must be 3.7M-16.7M. Dimensions rounded to 64-pixel increments. Images below 3.7M pixels will be auto-scaled up.

Default: 2048Range: 1024 - 4096
image_inputoptional
string[]

Input images to guide creation, use 1-3 URLs for reference.

max_imagesoptional
integer

Limit generated images: 1 for single output, 5 for more variety.

Default: 1Range: 1 - 15
sequential_image_generationoptional
string

Choose sequence: 'auto' for batch, 'disabled' for individual images.

Default: "disabled"
Allowed values :
"disabled""auto"
sizeoptional
string

Image resolution quality level. '2K' for standard (8-9M pixels), '4K' for high-res (up to 16.7M pixels). When used alone, API optimizes dimensions. When combined with aspect_ratio, dimensions are calculated but may not reach full 4K quality for extreme ratios (e.g., 9:16). Use 'custom' for exact control.

Default: "2K"
Allowed values :
"1K""2K""4K""custom"
widthoptional
integer

Custom width in pixels (only when size='custom'). Range: 1024-4096. Total pixels (width × height) must be 3.7M-16.7M. Dimensions rounded to 64-pixel increments. For maximum 4K quality with aspect ratios, calculate dimensions manually.

Default: 2048Range: 1024 - 4096

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/seedream-4.5

    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