# FLUX.1 API via PiAPI

Base URL: https://api.piapi.ai
Auth: X-API-KEY header (get your key at https://piapi.ai/workspace/key)

Documentation: https://piapi.ai/docs/flux-api/text-to-image

## Available Models

- Qubico/flux1-schnell: $0.0015/image (batch_size 1–4; billed batch_size × price). Apache 2.0 — commercial use OK.
- Qubico/flux1-dev: $0.015/image; super-resolution $0.015. Non-commercial license.
- Qubico/flux1-dev-advanced: $0.02/image — LoRA / ControlNet / inpaint / outpaint / redux-variation / Kontext (needs Creator plan or higher for LoRA & ControlNet).

Task types: txt2img, img2img, txt2img-lora, img2img-lora, fill-inpaint,
fill-outpaint, redux-variation, controlnet-lora.

## Text to Image

POST /api/v1/task
{
  "model": "Qubico/flux1-schnell",
  "task_type": "txt2img",
  "input": {
    "prompt": "A beautiful landscape with mountains and a lake at sunrise.",
    "width": 1024,
    "height": 1024
  }
}

width × height must be ≤ 1,048,576. Optional: negative_prompt,
guidance_scale (1.5–5), batch_size (1–4, schnell only), lora_settings,
control_net_settings.

## Image to Image

POST /api/v1/task
{
  "model": "Qubico/flux1-dev",
  "task_type": "img2img",
  "input": {
    "prompt": "Turn the boat red",
    "image": "https://example.com/reference.jpg",
    "denoise": 0.7
  }
}

## Get Task Result

GET /api/v1/task/{task_id}

Status: "pending" → "processing" → "completed" or "failed"
Image URL: response.data.output.image_url

## Quick Start

1. Get API key: https://piapi.ai/workspace/key
2. Top up: https://piapi.ai/workspace/billing
3. POST /api/v1/task
4. Poll GET /api/v1/task/{task_id} until "completed"
5. Get image from response.data.output.image_url