entire_feed

Public Model / gpt-image

GPT Image 2.5 Flare API pricing

The Flare variant of GPT Image 2.5, available for generation and editing.

Get started Estimation guide
Availability
Available
Tasks
Create Image, Edit Image
Published rates from
$0.00474

Request calculator

Configure GPT Image 2.5 Flare

Controls and rates come directly from the checked public catalog.

Interactive calculator

Price a direct generation

Choose a task, configure its inputs, and see the current catalog price.

Step 1

Choose a generation type

Step 2

Configure generation

Model
GPT Image 2.5 Flare
Size1024x1024
Qualitylow
Prompt length (UTF-8 bytes)256
1128000
Input images0
Outputs1

Step 3

Estimated reservation

$0.007161 output at $0.00716 each
Generation
$0.005881 image x $0.00588
Prompt allowance
$0.00128256 prompt bytes x $0.000005
Input media
$0.000 images x $0.065536
Minimum request
$0.004745

Estimated reservation, not a fixed price. Includes estimated output tokens, one text token per UTF-8 prompt byte, and an 8,192-token allowance per reference image. Final charges use reported usage: text input $5/M tokens, image input $8/M, image output $30/M; cached text $1.25/M and cached images $2/M. Actual usage may be lower or higher. Unused reservation is released.

Get started

The API estimate for your exact request is authoritative before paid work starts.

Best fit

Use Flare to try another GPT Image 2.5 variant with the same size, quality, and reference-image controls.

Use cases

  • Campaign image variations
  • Reference-guided product edits

Know before building

  • Shares Sunburst's token rates, but actual token usage can differ. Auto size and quality are not exposed in the public API.

Generated contract

Tasks, controls, and rates

Published rates

image.create
Varies by size, quality, prompt length (utf-8 bytes), input images
$0.00474 / image$0.004745 minimum
image.edit
Varies by size, quality, prompt length (utf-8 bytes), input images
$0.00474 / image$0.070281 minimum

Request controls

image.createPromptText input
image.createQualitylow · medium · high · xhigh · max
image.createReference imagesUp to 16 items
image.createSize1024x1024 · 1536x1024 · 1024x1536 · 2048x2048 · 3840x2160 · 2160x3840
image.editImagesUp to 16 items
image.editPromptText input
image.editQualitylow · medium · high · xhigh · max
image.editSize1024x1024 · 1536x1024 · 1024x1536 · 2048x2048 · 3840x2160 · 2160x3840

Lifecycle: queued -> running -> succeeded -> failed -> cancelled -> manual_review

Output fields: assets

Runnable examples

Estimate first, then create

Both requests use the same normalized task, model, and input payload. Creating work requires an API key and idempotency key.

1. Estimate

curl https://api.entirefeed.com/v1/estimate \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
  "task": "image.create",
  "model": "gpt-image-2.5-flare",
  "input": {
    "quality": "low",
    "size": "1024x1024",
    "prompt": "A colorful product campaign still with clean typography and precise lighting"
  }
}'

2. Create

curl https://api.entirefeed.com/v1/generations \
  -X POST \
  -H "Authorization: Bearer $ENTIREFEED_API_KEY" \
  -H "Idempotency-Key: gpt-image-2.5-flare-example-001" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "image.create",
  "model": "gpt-image-2.5-flare",
  "input": {
    "quality": "low",
    "size": "1024x1024",
    "prompt": "A colorful product campaign still with clean typography and precise lighting"
  }
}'