GPT-Image-2 ｜ Text To Image

Authentication

Sign up for a GPTProto account at https://gptproto.com
Navigate to the API Keys section in your dashboard
Generate a new API key (sk-xxxxx)
Copy and securely store your API key For authentication details, please refer to the Authentication section.

Initiate Request

curl --location 'https://gptproto.com/v1/images/generations' \
--header 'Authorization: GPTPROTO_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
  "model": "gpt-image-2",
  "prompt": "a cat",
  "size": "1024x1024"
}'

Response Example

{
  "created": 1776843003,
  "background": "opaque",
  "data": [
    {
      "b64_json": "<BASE64_DATA>"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 8,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 8
    },
    "output_tokens": 196,
    "output_tokens_details": {
      "image_tokens": 196,
      "text_tokens": 0
    },
    "total_tokens": 204
  }
}

Parameters

Text to Image
Image Edit

Parameter	Type	Required	Default	Range	Description
`model`	string	✅ Yes	`gpt-image-1`	`gpt-image-1` `gpt-image-1-mini` `gpt-image-1.5` `gpt-image-2`	The model to use for image generation. Defaults to gpt-image-1.
`prompt`	string	✅ Yes	-	-	A text description of the desired image(s). The maximum length is 32000 characters.
`n`	integer	❌ No	`1`	`1-10`	The number of images to generate. Must be between 1 and 10.
`size`	string	❌ No	`auto`	`auto` `1024x1024` `1536x1024` `1024x1536` `2048x2048` `2048x1152` `3840x2160` `2160x3840` or any valid custom size	The size of the generated images. For gpt-image-1: one of auto, 1024x1024, 1536x1024, or 1024x1536. For gpt-image-2: supports arbitrary resolutions (max edge ≤ 3840px, both sides must be multiples of 16px, aspect ratio ≤ 3:1, total pixels between 655,360 and 8,294,400). Outputs exceeding 2560×1440 are considered experimental.
`quality`	string	❌ No	`auto`	`auto` `high` `medium` `low`	The quality of the generated images. One of auto, low, medium, or high. Defaults to auto. Not supported by `-plus` suffixed models.
`background`	string	❌ No	`auto`	`opaque` `auto` `transparent`	Allows to set transparency for the background of the generated image(s). `transparent` is only supported by gpt-image-1 (not gpt-image-2) and requires output_format to be png or webp. When auto is used, the model will automatically determine the best background.
`moderation`	string	❌ No	`auto`	`low` `auto`	Content moderation level for generated images. `low` is less restrictive, `auto` is the default.
`output_format`	string	❌ No	`auto`	`auto` `png` `jpeg` `webp`	The output format of the generated image(s). Defaults to auto. jpeg is faster than png for latency-sensitive scenarios.
`output_compression`	integer	❌ No	`100`	`0-100`	The compression level (0-100%) for the output image. Only applicable with webp or jpeg format. Defaults to 100.
`stream`	boolean	❌ No	`false`	`true` `false`	Whether to stream the response in real-time. When enabled, partial images can be received during generation.
`partial_images`	integer	❌ No	-	`0-3`	The number of partial images to receive during streaming. Only used when stream is true. Each partial image incurs an additional 100 image output tokens.
`user`	string	❌ No	-	-	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Parameter	Type	Required	Default	Range	Description
`model`	string	✅ Yes	`gpt-image-1`	`gpt-image-1` `gpt-image-1-mini` `gpt-image-1.5` `gpt-image-2`	The model to use for image editing. Defaults to gpt-image-1.
`prompt`	string	✅ Yes	-	1–32000 chars	A text description of the desired image edit.
`images`	file	✅ Yes	-	max 16 images < 50MB each	The input image(s) to edit. Each image should be a png, webp, or jpg file. You can provide up to 16 images.
`mask`	file	❌ No	-	-	An additional image whose fully transparent areas indicate where the image should be edited.
`input_fidelity`	string	❌ No	-	`high` `low`	Controls how faithfully the model preserves the original input image. Only supported by gpt-image-1. gpt-image-2 always uses high fidelity.
`n`	integer	❌ No	`1`	`1-10`	The number of images to generate. Must be between 1 and 10.
`size`	string	❌ No	`auto`	`auto` `1024x1024` `1536x1024` `1024x1536` `2048x2048` `2048x1152` `3840x2160` `2160x3840` or any valid custom size	The size of the generated images. For gpt-image-1: one of auto, 1024x1024, 1536x1024, or 1024x1536. For gpt-image-2: supports arbitrary resolutions (max edge ≤ 3840px, both sides must be multiples of 16px, aspect ratio ≤ 3:1, total pixels between 655,360 and 8,294,400).
`quality`	string	❌ No	`auto`	`auto` `high` `medium` `low`	The quality of the generated images. One of auto, low, medium, or high. Defaults to auto. Not supported by `-plus` suffixed models.
`background`	string	❌ No	`auto`	`opaque` `auto` `transparent`	Allows to set transparency for the background of the generated image(s). `transparent` is only supported by gpt-image-1 (not gpt-image-2) and requires output_format to be png or webp.
`moderation`	string	❌ No	`auto`	`low` `auto`	Content moderation level for generated images. `low` is less restrictive, `auto` is the default.
`output_format`	string	❌ No	`auto`	`auto` `png` `jpeg` `webp`	The output format of the generated image(s). Defaults to auto. jpeg is faster than png for latency-sensitive scenarios.
`output_compression`	integer	❌ No	`100`	`0-100`	The compression level (0-100%) for the output image. Only applicable with webp or jpeg format. Defaults to 100.
`stream`	boolean	❌ No	`false`	`true` `false`	Whether to stream the response in real-time. When enabled, partial images can be received during generation.
`partial_images`	integer	❌ No	-	`0-3`	The number of partial images to receive during streaming. Only used when stream is true. Set to 0 for a single streaming event with the complete image. Each partial image incurs an additional 100 image output tokens.
`user`	string	❌ No	-	-	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Error Codes

Common Error Codes

Error Code	Error Name	Description
401	Unauthorized	API key is missing or invalid
403	Forbidden	Your API key doesn’t have permission to access this resource, or insufficient balance for the requested operation
429	Too Many Requests	You’ve exceeded your rate limit
500	Internal server error	An internal server error occurred
503	Content policy violation	Content blocked due to safety concerns (actual status code is 400)

API Reference

​Authentication

​Initiate Request

​Parameters

​Error Codes

​Common Error Codes

Authentication

Initiate Request

Parameters

Error Codes

Common Error Codes