Skip to main content
Core.Today
|
Billing note The default quality=auto is billed at the xhigh rate (581 credits per image). Set quality explicitly โ€” low (28) or medium (109) for drafts, high (298) for most final images โ€” to control cost.
OpenAIFastHigh

GPT Image 2.5 Flare

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 โ€” tuned for high-volume work where speed matters. For the most precise edits, use GPT Image 2.5 Sunburst.

580 credits
per image (default quality=auto) ร— number_of_images โ€” low 28 / medium 109 / high 298 / xhighยทauto 581 / max 1,163 credits per image
Fastest model in the GPT Image 2.5 line
Text-to-image and image editing in one model โ€” 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

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes-What you want to generate, or how to edit the input images. Put exact text in "quotes".
input_imagesarrayNo-Reference images for editing or composition. Pass one image to edit it, or several to combine subjects and styles. Processed at high fidelity automatically.
qualitystringNoautoQuality 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.
lowmediumhighxhighmaxauto
aspect_ratiostringNo1:1Named ratio, explicit size, or auto to let the model pick. Sizes above 2560x1440 are experimental and may give more variable results.
1:13:22:34:33:416:99:16auto1024x10241536x10241024x15361536x11521152x15362048x20482048x11521152x20483840x21602160x3840
number_of_imagesintegerNo1Number of images to generate (1-10). Billed per image.
backgroundstringNoautoBackground mode. For a transparent background use png or webp output.
autotransparentopaque
output_formatstringNowebpOutput image format
pngjpegwebp
output_compressionintegerNo90Compression level (0-100) for webp/jpeg output
moderationstringNoautoContent moderation level โ€” low applies less strict filtering
autolow
user_idstringNo-An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
openai_api_keystringNo-Your own OpenAI API key (optional โ€” leave empty to use the gateway)

How to Provide File Input

There are 3 ways to provide files for the input_images parameter:

Recommended

Image URL

Pass a publicly accessible URL directly. With the Storage API (POST /v1/files/upload-url) the file uploads straight to S3 (50MB per file) and you pass the returned file_url.

{
  "model": "openai/gpt-image-2.5-flare",
  "input": {
    "prompt": "your prompt here",
    "input_images": ["https://example.com/image.jpg"]
  }
}

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step, but the bytes pass through the API server so the whole request is capped at 10MB.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=openai/gpt-image-2.5-flare" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:input_images=@your_file.png"
See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Photorealistic Interior

Warm, photorealistic scene at the high quality tier

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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 ยท 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

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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)

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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
  }
}'

Tips & Best Practices

1Always set quality โ€” the default auto is billed like xhigh (581 credits per image)
2Draft at low or medium, then re-render the winner at high
3Put exact on-image text in "quotes" and describe the typography
4When editing, say what must not change: "change only the lighting, preserve the face and pose"
5Use photo language for realism: lens, lighting and framing (e.g. "50mm lens, soft daylight")
6Need the most precise edits? Switch to openai/gpt-image-2.5-sunburst โ€” same parameters and pricing

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