Generations（Image generation）

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 Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Success

application/json

Body

Example

{
    "background": "opaque",
    "created": 1765956636,
    "data": [
        {
            "url": "https://file.302.ai/gpt/imgs/20251217/cf55103f979340a0b3e92ddf38d33478.png"
        }
    ],
    "output_format": "png",
    "quality": "medium",
    "size": "1024x1024",
    "usage": {
        "input_tokens": 12,
        "input_tokens_details": {
            "image_tokens": 0,
            "text_tokens": 12
        },
        "output_tokens": 1414,
        "output_tokens_details": {
            "image_tokens": 1056,
            "text_tokens": 358
        },
        "total_tokens": 1426
    }
}

Generations（Image generation）

1. Function Introduction#

2. Request Parameters#

3. Precautions#