GPT-4o Image Generation API

Use Cases

gpt-4o native image generation for text-to-image, image-to-image and conversational-image-editing!!

Far more advanced text rendering than Midjourney or Dalle-3

Two Image Generation Models That We Provide

Model Name	`gpt-4o-image`	`gpt-image-1`
API Type	This is a reverse engineered version of ChatGPT image generation feature. It uses LLM API	This is a relayed version of openai `gpt-image-1`, it uses Images API and just alter the domain name and auth key
Stream Mode	Can only be used in `stream` mode	Can only be used in `stream` mode
Pricing	• $0.02 per successful generation • $0 for 4xx or 5xx errors • $0.00066 if response contains no image	Low Quality: • 1024×1024: $0.011 • 1024×1536: $0.016 • 1536×1024: $0.016 Medium Quality: • 1024×1024: $0.042 • 1024×1536: $0.063 • 1536×1024: $0.063 High Quality: • 1024×1024: $0.167 • 1024×1536: $0.25 • 1536×1024: $0.25
Implementation	Stream handling required and read below for code examples	Stream handling required, with altered domain name and keys
Notes	No image response may indicate content policy violation or downgrade to DALLE-3	Refer to OpenAI official pricing for complete details

Important Notes

For gpt-4o-image: Image generation failures that return 4xx or 5xx errors are not charged

For gpt-image-1: Implementation follows the same pattern as the standard OpenAI Images API with modified domain and auth headers

Request Examples For `gpt-4o-image` Model

Here are the examples for gpt-4o-image model, if you are looking for examples around gpt-image-1 model, go to openai offical guid Images API

Simple Text to Image

curl --location 'https://api.piapi.ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {your-api-key}' \
--data '{
    "model": "gpt-4o-image",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "draw a cyberpunk city"
                }
            ]
        }
    ],
    "stream": true
}'

Simple Image to Image

curl --location 'https://api.piapi.ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {your-api-key}' \
--data '{
    "model": "gpt-4o-image",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://images.ctfassets.net/kftzwdyauwt9/21orfxKx8HXXGKH8cTOq60/1eb34535ddce9c9e91fab0fad77bc158/minnias_cat_input.png?w=640&q=90&fm=webp"
                    }
                },
                {
                    "type": "text",
                    "text": "Give this cat a detective hat and a monocle"
                }
            ]
        }
    ],
    "stream": true
}'

Multiple Images Input

curl --location 'https://api.piapi.ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {your-api-key}' \
--data '{
    "model": "gpt-4o-image",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.moegirl.org.cn/common/thumb/5/53/Rei_Ayanami.jpg/280px-Rei_Ayanami.jpg"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://moegirl.uk/images/e/ef/OP_C057_asuka.jpg"
                    }
                },
                {
                    "type": "text",
                    "text": "merge two image"
                }
            ]
        }
    ],
    "stream": true
}'

Multiple Rounds Conversation

Different from legacy gpt-4o-image-preview, gpt-4o-image does not have multi rounds feature. It's a WIP feature for gpt-4o-image.

GPT-4o Image Generation API

Use Cases#

Two Image Generation Models That We Provide#

Important Notes#

Request Examples For gpt-4o-image Model#

Simple Text to Image#

Simple Image to Image#

Multiple Images Input#

Multiple Rounds Conversation#