Skip to content
English

FLUX 1.1 Pro

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name flux-1.1-pro
Type Image generation
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

FLUX 1.1 Pro is suited to photorealistic images, commercial posters, product shots, and optional reference guidance.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Photorealistic products

Product, still-life, and commercial visuals with a photographic feel.

promptaspect_ratio
Reference guidance

Use image_prompt to guide the result from an existing asset.

image_prompt
Custom dimensions

Select custom and specify width and height.

aspect_ratiowidthheight
Output quality control

Tune format and quality for handoff.

output_formatoutput_quality

Request parameters

model string required

Fixed value flux-1.1-pro.

example flux-1.1-pro
input object required

Business parameters for photorealistic image control.

prompt string required

Image generation prompt.

image_prompt string optional

Optional reference image URL. Supports jpeg, png, gif, and webp. SVG is not supported.

aspect_ratio enum optional

Output image ratio. Use custom to drive width and height.

default 1:1 enum: custom1:116:93:22:34:55:49:163:44:3
width integer optional

Custom width, only used when aspect_ratio=custom. Range 256-1440.

height integer optional

Custom height, only used when aspect_ratio=custom. Range 256-1440.

safety_tolerance integer optional

Safety tolerance. 1 is strictest and 6 is most permissive.

default 2
seed integer optional

Random seed for reproducible generation.

prompt_upsampling boolean optional

Whether to automatically enhance the prompt.

default false
output_format enum optional

Output format.

default webp enum: webpjpgpng
output_quality integer optional

Output quality, 0-100. Not relevant for png.

default 80
callback object optional

Optional callback configuration. In production, pass callback.url so HiAPI can notify your service when the task reaches a terminal state.

url string required

HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final for terminal-state notifications.

default final enum: final

Example requests

Basic photorealistic image

Product or still-life image generation.

Request body
{
  "model": "flux-1.1-pro",
  "input": {
    "prompt": "A small red apple on a white table",
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 80,
    "prompt_upsampling": false,
    "safety_tolerance": 2
  }
}
Custom dimensions

Pass width and height only when aspect_ratio=custom.

Request body
{
  "model": "flux-1.1-pro",
  "input": {
    "prompt": "A realistic hero image of a glass bottle on a metal table",
    "aspect_ratio": "custom",
    "width": 1024,
    "height": 768,
    "output_format": "jpg",
    "output_quality": 85
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated image from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

Next steps