# Seedream 4.0 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/overview
(Seedream 4.0 does not have a dedicated docs page yet; pricing is TBA —
new accounts start with free credits upon sign up.)

## Model

- Seedream 4.0 by ByteDance: unified text-to-image generation and image
  editing, photorealistic output up to 4K, up to 10 reference images per
  request.

## Text to Image (unified task schema)

POST /api/v1/task
{
  "model": "seedream",
  "task_type": "seedream-4-0",
  "input": {
    "prompt": "A futuristic city skyline under glowing auroras",
    "aspect_ratio": "16:9",
    "size": "2K",
    "output_format": "png"
  }
}

## Image Edit (reference images)

POST /api/v1/task
{
  "model": "seedream",
  "task_type": "seedream-4-0",
  "input": {
    "prompt": "Replace the smartphone's screen text with 'PiAPI Studio'",
    "image_urls": ["https://example.com/reference.jpg"],
    "aspect_ratio": "1:1",
    "size": "2K"
  }
}

Up to 10 reference image URLs in one request; the prompt describes the edit.

## Get Task Result

GET /api/v1/task/{task_id}

Status: "pending" → "processing" → "completed" or "failed"
Image URL: response.data.output.image_urls[0]

## Quick Start

1. Get API key: https://piapi.ai/workspace/key
2. New accounts start with free credits upon sign up (per-image pricing TBA)
3. POST /api/v1/task
4. Poll GET /api/v1/task/{task_id} until "completed"
5. Get image from response.data.output.image_urls