API

Example request

Set your FLUX_API_KEY before running. See the parameters below for supported settings.

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedream-5-5",
  "input": {
    "prompt": "Editorial portrait in natural light",
    "resolution": "2K",
    "aspect_ratio": "3:4"
  }
}'

Parameters

Set model to seedream-5-5. These fields belong inside input.

Reference media

Use your own publicly accessible HTTPS media URLs. Links must remain valid throughout queueing and generation. Base64 and file upload bodies are not supported by this endpoint.

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedream-5-5",
  "input": {
    "prompt": "Editorial portrait in natural light",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "image_urls": [
      "https://example.com/front.jpg",
      "https://example.com/back.jpg"
    ]
  }
}'

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedream-5-5",
  "input": {
    "mode": "layer-decomposition",
    "image_urls": [
      "https://example.com/front.jpg"
    ],
    "max_images": 10,
    "text_recognition": true
  }
}'

curl https://api.flux-context.org/api/v1/generations \
  -H "Authorization: Bearer $FLUX_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "seedream-5-5",
  "input": {
    "prompt": "Editorial portrait in natural light",
    "resolution": "2K",
    "aspect_ratio": "3:4",
    "background": "transparent",
    "output_format": "png"
  }
}'

Credits

Precharge uses the requested size and maximum output count. Final billing uses each archived image’s verified dimensions; unused credits are refunded. Final charge never exceeds precharge. Unverifiable output remains processing pending settlement.

Constraints

Omitted mode follows image_urls: no images means text-to-image; otherwise image-to-image. Default preset is 2K with automatic aspect ratio.

Custom size accepts 921,600–4,624,220 pixels, ratio 1:16–16:1; cannot combine with resolution or aspect_ratio.

Transparent output requires PNG. Layer decomposition requires exactly one image, automatic aspect ratio and no custom size; max_images includes the base image, defaults to 10 and accepts 2–100.

Successful decomposition may include layer_decomposition: canvas width/height and layers with result_index (zero-based into results), name, x/y, width/height, is_base and optional recognized text. These fields describe placement, not billing dimensions. Missing provider metadata is omitted.

Layer prompt is optional; an empty prompt uses a default layer separation instruction. Layer sizing is automatic unless resolution is supplied or auto_resolution is false. text_recognition defaults to false.

max_images, auto_resolution and text_recognition are layer-only options. Ordinary generation returns one image.

Use returned dimensions when available.

Response

A successful submission returns HTTP 202 and a request ID. Response excerpt:

{
  "id": "REQUEST_ID",
  "model": "seedream-5-5",
  "status": "processing"
}