# GPT Image 2.5 API Pipeline Fixture via PiAPI

> PiAPI provides GPT Image 2.5 Flare and Sunburst for image generation and editing. Both models share the same USD rates per 1M tokens.

Landing page: https://piapi.ai/pipeline-gpt-image-2-5-fixture
Base URL: https://api.piapi.ai
Authentication: use the API key from your PiAPI workspace.
Documentation: https://piapi.ai/docs/gpt-image/gpt-image-api

## Product details
- Category: image
- Vendor: openai

## Runtime targets

### GPT Image 2.5 Flare / Text to Image
POST https://api.piapi.ai/api/v1/images/generations/async
```json
{
  "model": "gpt-image-2.5-flare",
  "prompt": "YOUR_PROMPT",
  "size": "1024x1024",
  "quality": "low"
}
```
GET https://api.piapi.ai/api/v1/task/{task_id}
Output fields: image_urls, image_url, data
Workspace: https://piapi.ai/workspace/gpt-image?version=gpt-image-2-5-flare&operation=txt2img
Documentation: https://piapi.ai/docs/gpt-image/gpt-image-api
- gpt-image-2.5-flare:text_input: USD 0.00375 / 1k_tokens
- gpt-image-2.5-flare:image_input: USD 0.006 / 1k_tokens
- gpt-image-2.5-flare:output: USD 0.0225 / 1k_tokens

### Facts
- PiAPI model: gpt-image-2.5-flare is the fastest PiAPI option for everyday, high-quality image generation.
- PiAPI model: gpt-image-2.5-sunburst is the strongest PiAPI option for image generation and editing precision.
- PiAPI pricing: Per 1M tokens, both models cost $3.75 text input, $6.00 image input, and $22.50 image output.
- Quality: The quality parameter accepts auto, low, medium, and high. The API rejects xhigh, max, and standard with HTTP 400.

### Related entities
- GPT Image 2.5 API
- OpenAI
- PiAPI

## FAQ
### Which GPT Image 2.5 models are available on PiAPI?

The API supports gpt-image-2.5-flare and gpt-image-2.5-sunburst for image generation and editing.

### How much does GPT Image 2.5 API cost?

Per 1M tokens, both models cost $3.75 text input, $6.00 image input, and $22.50 image output.

### Which quality values does the API accept?

The quality parameter accepts auto, low, medium, and high. The API rejects xhigh, max, and standard with HTTP 400.