Enterprise AI Resource Hub - 302.AI | Pay-as-you-go, Comprehensive AI model API Access, Instant Online App Usage

gpt-image-2.5-flare

Lightweight image generation and editing model developed by OpenAI

2026-09-10

Image Generations

Input:

$5/1M tokensstarting from

Output:

$30/1M tokensstarting from

Bulk order? Contact your manager for exclusive deals

API Overview

GPT-image-2.5-Flare is a lightweight, ultra-fast image generation and editing model developed by OpenAI specifically for high-concurrency workflows, frequent creator applications, and rapid prototyping. As the speed-first version in the GPT Image 2.5 series, it boasts a 50% improvement in generation speed compared to its predecessor while maintaining exceptionally high visual quality and detailed rendering. The model natively supports precise local retouching, preservation of subject consistency, multi-round iterative editing, and transparent background output, making it the industry-leading choice for cost-effective batch image generation, e-commerce product images, and dynamic creative marketing visuals.

───────────────────────────────────────────────────────────────────

Core Capabilities

Ultra-Fast Response and Low Latency: Generation speed is nearly 50% faster than the previous generation, significantly reducing wait times under high-concurrency requests.

Precise Local Editing and Subject Preservation: It enables precise modifications to materials, lighting, shadows, or specific local objects, with exceptional consistency across continuous edits.

Multi-Modal Reference Input: A single request can simultaneously upload up to 16 reference images, accurately replicating target art styles, brand visual identities, and subject details.

Multiple Aspect Ratios and Transparent Backgrounds: It supports mainstream aspect ratios including 1:1, 16:9, 9:16, 2:3, and 3:4, and natively supports exporting images with transparent backgrounds.

API Console

API Analytics

API Reference (2)

API Description API Endpoint Request Method Stability Parameter Description

Generations（Generate image）

https://api.302.ai/v1/images/generations

POST

Stable

View Details

Document Details

1. Function Introduction

Generate one or more high-quality images based on text prompts, supporting:

GPT-Image Series Models (gpt-image-1.5 / gpt-image-1 / gpt-image-1-mini)
Fine-grained control over multi-size, multi-quality, transparent background, streaming output, etc.
Comes with built-in content moderation, allowing customizability of moderation strictness
Asynchronous / Synchronous dual mode, adaptable to different business scenarios

2. Request Parameters

Field	Type	Required	Description	Remarks
prompt	string	✅	Description text	Length ≤ 32k (gpt-image-1.5)
model	string	✅	Model	Optional: gpt-image-1.5 / gpt-image-1 / gpt-image-1-mini
n	int		Number of images to generate	1-10; dall-e-3 only supports 1
size	string		Dimensions	1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), auto. When the dimension selection is `auto`, the model will automatically provide the optimal ratio based on the prompt.
quality	string		Quality	low / medium / high / auto
background	string		Background	transparent / opaque / auto
output_format	string		Output format	png / jpeg / webp
output_compression	int		Compression ratio	0-100; only effective for jpeg/webp
moderation	string		moderation strictness	low (lenient) / auto
stream	bool		Streaming output	Only supported by the GPT-Image series
partial_images	int		Number of streaming shards	0-3; 0 = only return the final image
async	query		Whether asynchronous	Returns task_id when passing `?async=true`

3. Precautions

✅ Please strictly adhere to the prompt character length limit according to the selected model
📏 Different models support different size and quality parameters, so compatibility needs to be confirmed in advance
🔒 Sensitive content will be intercepted by the system, and it is recommended to keep the moderation parameter in the default auto mode
📊 Pricing is calculated based on the Tokens of the generated images, with different models/qualities consuming different amounts of Tokens (see the Pricing section for details)
🔄 The generation progress of asynchronous tasks can be actively checked via the task query interface

4. Price

Model	Text Input	Text Output	Image Output	Remarks
gpt-image-1	5 PTC/1M Tokens		40 PTC/1M Tokens	High-quality model
gpt-image-1-mini	2 PTC/1M Tokens		8 PTC/1M Tokens	Efficient and Economical Model
gpt-image-1.5	5 PTC/1M Tokens	10 PTC/1M Tokens	32 PTC/1M Tokens	Balanced Model

The final price shall be based on the number of Tokens consumed as returned by the request
gpt-image-1: Price Reference

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Query Parameters

response_formatstring

Optional

Example Value:url

asyncstring

Optional

Example Value:false

Request Body application/json

promptstring

Required

A text description of the required image. The more detailed the description, the better the expected result.
Character length limits:

GPT-Image series models: maximum 32000 characters
DALL-E-2: maximum 1000 characters
DALL-E-3: maximum 4000 characters

Writing suggestions:

Include the subject (e.g., “baby sea otter”), action (e.g., “playing”), scene (e.g., “in the ocean waves”)
Specify the style (e.g., “watercolor style”), lighting (e.g., “soft light”), and color (e.g., “blue and white”)
Avoid vague descriptions; use specific words to improve generation accuracy.

sizeenum<string>

Optional

The generated image size varies depending on the model:

GPT-Image series: 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), auto (automatic adaptation)
DALL-E-2: 256x256, 512x512, 1024x1024
DALL-E-3: 1024x1024, 1792x1024 (landscape), 1024x1792 (portrait)

Enum Value:

1024x10241536x10241024x1536auto

backgroundenum<string>

Optional

Image background settings, applicable only to GPT-Image series models:

transparent: Transparent background (PNG/WEBP format only supported)
opaque: Opaque background
auto: Automatic judgment (default, intelligently set according to prompt word scenario)

Note: When transparent is selected, output_format must be set to png or webp

Enum Value:

transparentopaqueauto

moderationenum<string>

Optional

Content moderation level, controlling the compliance of generated images:

low: lenient moderation, allowing slight creative expression
auto: automatic moderation (default), balancing compliance and creativity

Enum Value:

lowauto

ninteger

Optional

Number of images generated:

Value range: 1-10 (GPT-Image/DALL-E-2)
DALL-E-3 only supports n=1

Note: The more images generated, the more tokens are consumed and the longer the generation time

qualityenum<string>

Optional

The generated image quality. ‘auto’ (default) will automatically select the best quality for the given model.

GPT-Image model: Supports high, medium, and low modes.
DALL-E-3: Supports hd and standard image quality.
DALL-E 2: Only standard can be selected.

Enum Value:

autohighmediumlow

modelenum<string>

Required

Enum Value:

gpt-image-1gpt-image-1-minigpt-image-1.5

output_compressioninteger

Optional

Image compression level (GPT-Image only, default 100):

Value range: 0-100 (percentage)
0: No compression (largest file size, best quality)
100: Maximum compression (smallest file size, quality may be compromised)

Only applicable to webp/jpeg formats, png format does not support compression

output_formatenum<string>

Optional

Image output format (GPT-Image only):

png: Supports transparent backgrounds, lossless compression
jpeg: Good compatibility, smaller file size
webp: Balances compression and quality, supports transparency

When selecting transparent background, png or webp format must be used

Enum Value:

webppngjpeg

partial_imagesinteger

Optional

Number of partial images generated (GPT-Image only):

Value range: 0-3
0: Do not return partial images, return the complete image after generation (default)
1-3: Return partial image previews in stages, and finally return the complete image

Only effective when stream=true, suitable for scenarios that require fast preview

streamboolean

Optional

Enable streaming generation (GPT-Image only):

false (default): Return all data at once after generation
true: Return image data in stages as streaming events

Combined with the partial_images parameter, progressive image preview can be achieved

Edit（Modify Image）

https://api.302.ai/v1/images/edits

POST

Stable

View Details

Document Details

1. Function Introduction

Upload the original image and the mask image (optional), combine them with text prompts, and let the AI model replace the content of the specified area in the image to generate an edited image.
Supports GPT-Image series and DALL-E 2 model, suitable for scenarios such as image restoration, content replacement, and style adjustment.

Precise regional editing: Specify the editing area through a mask image to achieve local content replacement
Multi-model adaptation: Supports GPT-Image series (efficient and flexible) and DALL-E 2 (classic and stable)
Rich parameter control: Customizable image size, quality, output format, compression level, etc.
Batch generation: Supports generating 1-10 edited images at once to meet diverse needs
Transparent background support: The GPT-Image model can generate images with transparent backgrounds, suitable for design scenarios

2. Request Parameters

Field	Type	Required	Description	Remarks
Image	File	✅	Original image file	≤ 50 MB; Supports PNG/JPEG/WebP
mask	file		Mask Image	Must be the same size as the original image and contain an alpha channel
prompt	string	✅	Edit prompt	Length ≤ 32 k (gpt-image-1.5)
model	string	✅	Model	gpt-image-1.5 / gpt-image-1 / gpt-image-1-mini
n	int		Number of output sheets	1-10
size	string		Output size	Same as the generation interface, see the size table
quality	string		Quality	low / medium / high / auto
background	string		Background	transparent / opaque / auto
input_fidelity	string		Input Fidelity	low / high; high better preserves face/Logo
output_format	string		Output format	png / jpeg / webp
output_compression	int		Compression ratio	0-100; only for jpeg/webp
moderation	string		moderation strictness	low / auto
stream	bool		Streaming	Only for GPT-Image series
partial_images	int		Streaming sharding	0-3
async	query		Whether asynchronous	?async=true returns task_id

3. Precautions

✅ The original image and mask image must meet the format and size restrictions of the corresponding model (see parameter description for details)
🎭 The mask image must have the same dimensions as the original image, with the transparent area (alpha=0) being the editing area
🔒 Editing sensitive content is not supported, and the system will conduct content moderation
⚠️ APIFOX does not support online debugging of this API and requires testing via code calls
🚫 Uploading infringing or illegal images is prohibited

4. Price

Model	Text Input	Image Input	Image Output
gpt-image-1	5 PTC/1M Tokens	10 PTC/1M Tokens	40 PTC/1M Tokens
gpt-image-1-mini	2 PTC/1M Tokens	2.5 PTC/1M Tokens	8 PTC/1M Tokens
gpt-image-1.5	5 PTC/1M Tokens	8 PTC/1M Tokens	32 PTC/1M Tokens

The final price shall be based on the number of Tokens consumed as returned by the request
gpt-image-1: Price Reference

Request Parameters

Header Parameters

Authorizationstring

Optional

Example Value:Bearer {{YOUR_API_KEY}}

Content-Typestring

Optional

Example Value:multipart/form-data

Query Parameters

response_formatstring

Optional

Example Value:url

Request Body multipart/form-data

imagestring

Required

Original image to be edited (required):

GPT-Image Series (gpt-image-1/1-mini/1.5):
- Supported formats: PNG, WEBP, JPG
- Single file size: ≤50MB
- Quantity limit: up to 16 pieces
DALL-E 2：
- Supported format: only PNG (square)
- Single image size: ≤4MB
- Quantity limit: Only 1 piece

Note: When uploading multiple images, the mask only applies to the first image

promptstring

Required

Text description of the editing effect (required):

Describe details such as the content, style, color, etc. to be replaced
Character length limit:
- GPT-Image Series: Up to 32,000 characters
- DALL-E 2: Up to 1000 characters
Writing Suggestion: Describe clearly and specifically in combination with the original image scene

modelstring

Required

gpt-image-1、gpt-image-1-mini、gpt-image-1.5

Example Value:gpt-image-1.5

maskstring

Optional

Mask Image (Optional):

Function: Transparent area (alpha=0) indicates the position in the original image that needs to be edited
Requirements:
- Format: PNG only (supports transparency)
- Size: ≤4MB (all models)
- Dimensions: Must be exactly the same as the first original image
- Quantity: Only 1 piece; when there are multiple original images, it only applies to the first one
Applicable scenarios: Precisely locating the editing area, such as replacing a specific object in an image.

qualitystring

Optional

Quality level of the generated image:

GPT-Image Series: Supports auto/high/medium/low
DALL-E 2: Only supports standard

Example Value:auto

sizestring

Optional

Size of the generated image:

GPT-Image Series: 1024x1024, 1536x1024, 1024x1536, auto
DALL-E 2：256x256、512x512、1024x1024

Example Value:1024x1024

ninteger

Optional

Number of edited images generated:

Value range: 1-10
The greater the quantity, the more Tokens are consumed, and the longer the generation time

Example Value:1

backgroundstring

Optional

Image background settings (only applicable to GPT-Image model):

transparent: Transparent background (only supported in PNG/WEBP formats)
opaque: opaque background
auto: intelligently set based on the prompt and the original image

Example Value:auto

output_formatstring

Optional

Output image format (only applicable to GPT-Image model):

When choosing a transparent background, you need to use the png or webp format

Example Value:png

output_compressionstring

Optional

Image Compression Level (only applicable to GPT-Image model):

Value range: 0-100 (percentage)
0: No compression (largest file size, best quality)
100: Maximum compression (smallest file size, quality may be compromised)
Only applicable to webp or jpeg formats; png format does not support compression

Example Value:100

partial_imagesinteger

Optional

Partial Image Generation Quantity (only applicable to GPT-Image model):

Value range: 0-3
0: Do not return partial images; return the complete image after generation is completed (default)
1-3: Return partial image previews in stages, and finally return the complete image
Only takes effect when stream=true

streamboolean

Optional

Whether to enable streaming generation (only applicable to GPT-Image model):

false (default): Return all at once after generation is completed
true: Return image data in stages as streaming events

API Pricing

$￥円 ₽

Model	Description	Official Price	302.AI Price	Official Price Gap

Generations（Generate image）

text input

Input $5 / 1M tokens
Output $30 / 1M tokens

Original Price

Generations（Generate image）

Image input

Input $8 / 1M tokens
Output $30 / 1M tokens

Original Price

gpt-image-2.5-flare