# GPT Image 1.5 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/gpt-image/gpt-image-api

## Model & Pricing

gpt-image-1.5 bills by output tokens at $32 / 1M output tokens.
Estimated per-image cost (docs cost matrix):

- 1024x1024: low ~$0.009 / medium ~$0.034 / high ~$0.133
- 1024x1536: low ~$0.013 / medium ~$0.051 / high ~$0.200
- 1536x1024: low ~$0.013 / medium ~$0.051 / high ~$0.200

Up to 4x faster generation than gpt-image-1 with higher quality and
enhanced text rendering. Supports text-to-image and image editing.

## Create Task (async)

POST /api/v1/images/generations/async
{
  "model": "gpt-image-1.5",
  "prompt": "A modern city street at night with neon signs, cinematic street photography",
  "size": "1024x1024",
  "quality": "medium"
}

quality: "low" | "medium" | "high"
size: "1024x1024" | "1024x1536" | "1536x1024"
Image edits: POST /api/v1/images/edits/async (multipart: image + model + prompt + size + quality)

## Get Task Result

GET /api/v1/task/{task_id}

Status: "pending" → "processing" → "completed" or "failed"
Image: response.data.output.data[0].b64_json (base64-encoded PNG)
Billing: response.data.output.usage.output_tokens × $32 / 1M tokens

## Quick Start

1. Get API key: https://piapi.ai/workspace/key
2. Top up: https://piapi.ai/workspace/billing
3. POST /api/v1/images/generations/async
4. Poll GET /api/v1/task/{task_id} until "completed"
5. Decode the image from response.data.output.data[0].b64_json