🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
O

GPT Image 2.5 Flare

OpenAIModel IDgpt-image-2.5-flare
O

GPT Image 2.5 Flare

OpenAIModel IDgpt-image-2.5-flare

GPT Image 2.5 Flare is OpenAI's fastest high-quality image generation and editing model, optimized for everyday creative workflows where speed and visual quality both matter. It supports text-to-image generation, image editing, reference-image workflows, transparent backgrounds, custom resolutions up to 4K, and flexible quality settings for fast production-ready image creation.

ModeText / Image → Image
Input price$5 / 1M tokens
Output price$30 / 1M tokens
Context lengthUnknown

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
OpenAI
Input modality
Text / Image
Output modality
Image
Max output
Unknown

Pricing

ProviderBilling typePrice summary
O
OpenAI-Balanced
Per token
Input price$5per 1M tokens
Completion price$30per 1M tokens
Cache read price$1.25per 1M tokens
Cache write price—
O
OpenAI-Custom
Per token
Input price$5per 1M tokens
Completion price$30per 1M tokens
Cache read price$1.25per 1M tokens
Cache write price—

Integration

Code Example

curl http://127.0.0.1:4179/v1/images/edits \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-flare",
    "prompt": "Describe the image you want"
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
openai-image-edit

Supported Parameters

ParameterTypeDefaultDescription
stringautoControls image rendering quality. Flare is optimized for fast high-quality generation, while higher quality settings may increase latency and image token usage.
stringautoControls output image dimensions. Supports presets and custom WIDTHxHEIGHT resolutions.
stringauto
integer100Controls JPEG or WebP compression quality.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.