GPT Image 2.5 Flare

OpenAI's fastest model for high-quality, everyday image generation and editing.

Internal PreviewFast Image GenerationImage Editing

Positioning

Fast everyday generation

Optimized for high-quality, latency-sensitive workflows

Input Types

Text + images

Generate or edit with up to 14 reference images

Quality

6 settings

Low through max, plus automatic selection

Execution

Sync + async

Wait for a direct response, or poll and receive callbacks

Model Codegpt-image-2.5-flare

Playground

Model Code

gpt-image-2.5-flare

Reference inputs

Reference Images0/14

Click or drag

Enter your prompt here...

Resolution

Resolution (sent to backend)

Aspect Ratio

Aspect Ratio (sent to backend)

Quality

Quality (sent to backend)

Output Format

Output format (sent to backend)

Output

No output yet

Pricing

Usage Metric	Standard Price
Text input	$45.9$5 / 1M tokens10% off
Image input	$72.9$8 / 1M tokens10% off
Image output	$270.9$30 / 1M tokens10% off

Text input · $4.5 · 1M tokens

Image input · $7.2 · 1M tokens

Image output · $27 · 1M tokens

README

GPT Image 2.5 Flare combines fast image generation with text and image inputs, six quality settings, flexible output sizes, and both synchronous and asynchronous ReachAPI workflows.

GPT Image 2.5 Flare is OpenAI's fastest model for high-quality everyday image generation. It is the practical starting point when GPT Image 2 already meets the required quality and lower latency is the priority.
The model accepts text and image inputs for generation and editing. ReachAPI supports up to 14 HTTPS reference images, 1K, 2K, and 4K resolution tiers, three standard aspect ratios, and PNG, JPEG, or WebP output.
Quality can be set to low, medium, high, xhigh, max, or auto. Token consumption can differ by quality and image size even though Flare and Sunburst use the same token rates.
This model is currently an Internal Preview on ReachAPI. Use the OpenAI-compatible synchronous API for a direct response, or the asynchronous task API for polling, URL reference images, and optional terminal callbacks.

API

Use the API docs for request format, parameters, and integration details.

OpenAI's fastest model for high-quality, everyday image generation and editing.

Model Code

gpt-image-2.5-flare

View API Docs

API

Endpoint

Synchronous generation

POST https://direct.reachapi.ai/v1/images/generations

Synchronous editing

POST https://direct.reachapi.ai/v1/images/edits

Asynchronous task

POST https://direct.reachapi.ai/v1/images/create

Authentication

Authorization: Bearer YOUR_REACH_API_KEY

Example

Synchronous generation

curl -X POST "https://direct.reachapi.ai/v1/images/generations" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-flare",
    "prompt": "A precise editorial product photograph of a silver watch on slate, soft studio lighting",
    "size": "1536x1024",
    "quality": "high",
    "background": "auto",
    "moderation": "auto",
    "output_format": "png"
  }'

Synchronous editing

curl -X POST "https://direct.reachapi.ai/v1/images/edits" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -F "model=gpt-image-2.5-flare" \
  -F "prompt=Preserve the watch geometry and replace only the background with dark brushed metal" \
  -F "image[]=@/path/to/watch.png" \
  -F "size=1536x1024" \
  -F "quality=xhigh" \
  -F "output_format=png"

Asynchronous task

curl -X POST "https://direct.reachapi.ai/v1/images/create" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-flare",
    "callback_url": "https://example.com/reachapi/callback",
    "input": {
      "prompt": "A precise editorial product photograph of a silver watch on slate, soft studio lighting",
      "resolution": "2k",
      "aspect_ratio": "3:2",
      "quality": "high",
      "background": "auto",
      "moderation": "auto",
      "output_format": "png"
    }
  }'

Related Models

Other models from the same vendor

GPT-6 Astra

OpenAI's flagship model for demanding end-to-end work.

GPT-5.6 Luna

OpenAI's GPT-5.6 model for efficient, cost-sensitive, high-volume workloads.

GPT-5.6 Sol

OpenAI's GPT-5.6 flagship model for the most demanding production reasoning, coding, and agent workflows.

GPT-5.6 Terra

OpenAI's GPT-5.6 model for strong intelligence with a balanced cost profile.

GPT-5.5

OpenAI's newest frontier model for the most complex coding, reasoning, and professional workflows.

GPT-5.4

OpenAI's frontier model for complex professional, coding, and agentic work at scale.

GPT-5.4 Mini

OpenAI's strongest mini model for coding, computer use, and high-volume agent tasks.

GPT-5.3 Codex

OpenAI's most capable agentic coding model to date.

GPT-5.2

OpenAI's stronger GPT-5-family model for professional, general-purpose, and agentic work.

GPT-5.1

OpenAI's flagship model for coding and agentic tasks with configurable reasoning.

GPT-5.1 Codex

OpenAI's GPT-5.1 variant optimized for agentic coding in Codex workflows.

GPT-5

OpenAI's previous intelligent reasoning model for coding and agentic tasks.

GPT-5 Mini

OpenAI's faster, cost-efficient GPT-5 variant for low-latency and high-volume work.

GPT Image 2.5 Sunburst

OpenAI's most capable image model for high-quality generation and precision editing.

GPT Image 2

OpenAI's state-of-the-art image generation model for high-quality creation and editing with text and image inputs.

GPT Image 2 Async

ReachAPI's asynchronous GPT Image 2 workflow for task-based image generation and editing with callback-ready results.