# Flux Kontext 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/kontext

## What it is

Flux Kontext is Black Forest Labs' image-to-image editing model: it edits an
input image from a natural-language instruction (style transfer, object /
color changes, background replacement, text replacement, and more).

## Model & Pricing

- model: Qubico/flux1-dev-advanced, task_type: kontext — $0.02/image.
  Pay only for successful generations; full commercial use rights.

## Edit an Image

POST /api/v1/task
{
  "model": "Qubico/flux1-dev-advanced",
  "task_type": "kontext",
  "input": {
    "prompt": "Change the car color to red.",
    "image": "https://example.com/input.png",
    "width": 1024,
    "height": 1024,
    "steps": 28,
    "seed": -1
  }
}

input.image: URL or base64 string (required, under 10MB; JPEG/PNG/WebP).
steps: optional, default 28, max 40. seed: optional, -1 = random.
Optional webhook: config.webhook_config.endpoint + secret
(https://piapi.ai/docs/unified-webhook).

## Get Task Result

GET /api/v1/task/{task_id}

Status: "pending" → "processing" → "completed" or "failed"
Image URL: response.data.output.image_url
Failed calls are not charged.

## Quick Start

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