# GPT Image 2.5 Flare - Core.Today AI API

> OpenAI's fastest model for high-quality, everyday image generation. Generate images from text or edit existing images with strong instruction following and sharp text rendering — tuned for high-volume work where speed matters. For the most precise edits, use GPT Image 2.5 Sunburst.

- **Provider**: OpenAI
- **Model ID**: openai/gpt-image-2.5-flare
- **Category**: Image Generation
- **Credits**: 580 per image (default quality=auto) × number_of_images — low 28 / medium 109 / high 298 / xhigh·auto 581 / max 1,163 credits per image
- **Speed**: Fast
- **Quality**: High

## Features
- Fastest model in the GPT Image 2.5 line
- Text-to-image and image editing in one model — just add input_images
- Sharp text rendering for infographics, UI mockups and marketing copy
- Six quality tiers: low / medium / high / xhigh / max / auto
- Up to 10 images per request (billed per image)
- Transparent or opaque background, webp / png / jpeg output

## Use Cases
- High-volume marketing visuals and social media creatives
- Infographics, logos and UI mockups with legible text
- Product mockups, virtual try-ons and quick photo edits
- Fast drafting and A/B variations before a final render

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - What you want to generate, or how to edit the input images. Put exact text in "quotes".

### Optional
- **input_images**: array - Reference images for editing or composition. Pass one image to edit it, or several to combine subjects and styles. Processed at high fidelity automatically.
- **quality**: string (default: auto) - Quality tier. Higher tiers take longer and cost more per image: low 28, medium 109, high 298, xhigh 581, max 1,163 credits. auto is billed at the xhigh rate.
  Options: low, medium, high, xhigh, max, auto
- **aspect_ratio**: string (default: 1:1) - Named ratio, explicit size, or auto to let the model pick. Sizes above 2560x1440 are experimental and may give more variable results.
  Options: 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, auto, 1024x1024, 1536x1024, 1024x1536, 1536x1152, 1152x1536, 2048x2048, 2048x1152, 1152x2048, 3840x2160, 2160x3840
- **number_of_images**: integer (default: 1) - Number of images to generate (1-10). Billed per image.
- **background**: string (default: auto) - Background mode. For a transparent background use png or webp output.
  Options: auto, transparent, opaque
- **output_format**: string (default: webp) - Output image format
  Options: png, jpeg, webp
- **output_compression**: integer (default: 90) - Compression level (0-100) for webp/jpeg output
- **moderation**: string (default: auto) - Content moderation level — low applies less strict filtering
  Options: auto, low
- **user_id**: string - An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
- **openai_api_key**: string - Your own OpenAI API key (optional — leave empty to use the gateway)

## Examples

### Photorealistic Interior
Warm, photorealistic scene at the high quality tier
```json
{
  "model": "openai/gpt-image-2.5-flare",
  "input": {
    "prompt": "A cozy bookstore cafe interior at golden hour, warm lighting, photorealistic",
    "quality": "high",
    "aspect_ratio": "3:2"
  }
}
```

### Marketing Banner with Text
Exact copy in quotes plus a typography description
```json
{
  "model": "openai/gpt-image-2.5-flare",
  "input": {
    "prompt": "A clean summer sale banner for a coffee brand. Large bold sans-serif headline \"SUMMER COLD BREW\" and smaller text \"20% OFF · Aug 1-31\" below, iced coffee glass on a pastel blue background, minimal flat style",
    "quality": "high",
    "aspect_ratio": "16:9",
    "output_format": "png"
  }
}
```

### Edit an Existing Photo
Pass input_images and state what must stay the same
```json
{
  "model": "openai/gpt-image-2.5-flare",
  "input": {
    "prompt": "Change only the background to a snowy mountain cabin at dusk. Preserve the person's face, pose, clothing and lighting direction.",
    "input_images": [
      "https://example.com/your-photo.jpg"
    ],
    "quality": "high"
  }
}
```

### Cheap Drafts in Bulk
Explore 4 variations at the low tier (28 credits each)
```json
{
  "model": "openai/gpt-image-2.5-flare",
  "input": {
    "prompt": "Minimal flat logo concept for a bakery named \"Crumb\", warm brown and cream palette",
    "quality": "low",
    "number_of_images": 4
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Always set quality — the default auto is billed like xhigh (581 credits per image)
- Draft at low or medium, then re-render the winner at high
- Put exact on-image text in "quotes" and describe the typography
- When editing, say what must not change: "change only the lighting, preserve the face and pose"
- Use photo language for realism: lens, lighting and framing (e.g. "50mm lens, soft daylight")
- Need the most precise edits? Switch to openai/gpt-image-2.5-sunburst — same parameters and pricing