cli/resources/images/methods/edit/index.md

Create image edit

$ openai images edit

post /images/edits

Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini, and chatgpt-image-latest) and dall-e-2.

Parameters

--image: string or array of string

The image(s) to edit. Must be a supported image file or an array of images.

For the GPT image models (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, and chatgpt-image-latest), each image should be a png, webp, or jpg file less than 50MB. You can provide up to 16 images.

For dall-e-2, you can only provide one image, and it should be a square png file less than 4MB.
--prompt: string

A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2, and 32000 characters for the GPT image models.
--background: optional "transparent" or "opaque" or "auto"

Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.

gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.

If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
--input-fidelity: optional "high" or "low"

Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
--mask: optional string

An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.
--model: optional string or ImageModel

The model to use for image generation. One of dall-e-2 or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, or chatgpt-image-latest). Defaults to gpt-image-1.5.
--n: optional number

The number of images to generate. Must be between 1 and 10.
--output-compression: optional number

The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the webp or jpeg output formats, and defaults to 100.
--output-format: optional "png" or "jpeg" or "webp"

The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of png, jpeg, or webp. The default value is png.
--partial-images: optional number

The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event.

Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly.
--quality: optional "standard" or "low" or "medium" or 2 more

The quality of the image that will be generated for GPT image models. Defaults to auto.
--response-format: optional "url" or "b64_json"

The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for dall-e-2 (default is url for dall-e-2), as GPT image models always return base64-encoded images.
--size: optional string or "256x256" or "512x512" or "1024x1024" or 3 more

The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
--user: optional string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

images_response: object { created, background, data, 4 more }

The response from the image generation endpoint.
- created: number
  
  The Unix timestamp (in seconds) of when the image was created.
- background: optional "transparent" or "opaque"
  
  The background parameter used for the image generation. Either transparent or opaque.
  - "transparent"
  - "opaque"
- data: optional array of Image
  
  The list of generated images.
  - b64_json: optional string
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - revised_prompt: optional string
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - url: optional string
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- output_format: optional "png" or "webp" or "jpeg"
  
  The output format of the image generation. Either png, webp, or jpeg.
  - "png"
  - "webp"
  - "jpeg"
- quality: optional "low" or "medium" or "high"
  
  The quality of the image generated. Either low, medium, or high.
  - "low"
  - "medium"
  - "high"
- size: optional "1024x1024" or "1024x1536" or "1536x1024"
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
- usage: optional object { input_tokens, input_tokens_details, output_tokens, 2 more }
  
  For gpt-image-1 only, the token usage information for the image generation.
  - input_tokens: number
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: object { image_tokens, text_tokens }
    
    The input tokens detailed information for the image generation.
    - image_tokens: number
      
      The number of image tokens in the input prompt.
    - text_tokens: number
      
      The number of text tokens in the input prompt.
  - output_tokens: number
    
    The number of output tokens generated by the model.
  - total_tokens: number
    
    The total number of tokens (images and text) used for the image generation.
  - output_tokens_details: optional object { image_tokens, text_tokens }
    
    The output token details for the image generation.
    - image_tokens: number
      
      The number of image output tokens generated by the model.
    - text_tokens: number
      
      The number of text output tokens generated by the model.

Example

openai images edit \
  --api-key 'My API Key' \
  --image 'Example data' \
  --prompt 'A cute baby sea otter wearing a beret'

Response

{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

cli/resources/images/methods/edit/index.md +239 −0 created

1## Create image edit

3`$ openai images edit`

5**post** `/images/edits`

7Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models (`gpt-image-1.5`, `gpt-image-1`, `gpt-image-1-mini`, and `chatgpt-image-latest`) and `dall-e-2`.

9### Parameters

11- `--image: string or array of string`

13 The image(s) to edit. Must be a supported image file or an array of images.

15 For the GPT image models (`gpt-image-1`, `gpt-image-1-mini`,

16 `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, and

17 `chatgpt-image-latest`), each image should be a `png`, `webp`, or

18 `jpg` file less than 50MB. You can provide up to 16 images.

20 For `dall-e-2`, you can only provide one image, and it should be a

21 square `png` file less than 4MB.

23- `--prompt: string`

25 A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for the GPT image models.

27- `--background: optional "transparent" or "opaque" or "auto"`

29 Allows to set transparency for the background of the generated image(s).

30 This parameter is only supported for GPT image models that support

31 transparent backgrounds. Must be one of `transparent`, `opaque`, or

32 `auto` (default value). When `auto` is used, the model will

33 automatically determine the best background for the image.

35 `gpt-image-2` and `gpt-image-2-2026-04-21` do not support

36 transparent backgrounds. Requests with `background` set to

37 `transparent` will return an error for these models; use `opaque` or

38 `auto` instead.

40 If `transparent`, the output format needs to support transparency,

41 so it should be set to either `png` (default value) or `webp`.

43- `--input-fidelity: optional "high" or "low"`

45 Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`.

47- `--mask: optional string`

49 An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.

51- `--model: optional string or ImageModel`

53 The model to use for image generation. One of `dall-e-2` or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, or `chatgpt-image-latest`). Defaults to `gpt-image-1.5`.

55- `--n: optional number`

57 The number of images to generate. Must be between 1 and 10.

59- `--output-compression: optional number`

61 The compression level (0-100%) for the generated images. This parameter

62 is only supported for the GPT image models with the `webp` or `jpeg` output

63 formats, and defaults to 100.

65- `--output-format: optional "png" or "jpeg" or "webp"`

67 The format in which the generated images are returned. This parameter is

68 only supported for the GPT image models. Must be one of `png`, `jpeg`, or `webp`.

69 The default value is `png`.

71- `--partial-images: optional number`

73 The number of partial images to generate. This parameter is used for

74 streaming responses that return partial images. Value must be between 0 and 3.

75 When set to 0, the response will be a single image sent in one streaming event.

77 Note that the final image may be sent before the full number of partial images

78 are generated if the full image is generated more quickly.

80- `--quality: optional "standard" or "low" or "medium" or 2 more`

82 The quality of the image that will be generated for GPT image models. Defaults to `auto`.

84- `--response-format: optional "url" or "b64_json"`

86 The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2` (default is `url` for `dall-e-2`), as GPT image models always return base64-encoded images.

88- `--size: optional string or "256x256" or "512x512" or "1024x1024" or 3 more`

90 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

92- `--user: optional string`

94 A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

96### Returns

98- `images_response: object { created, background, data, 4 more }`

100 The response from the image generation endpoint.

101

102 - `created: number`

103

104 The Unix timestamp (in seconds) of when the image was created.

105

106 - `background: optional "transparent" or "opaque"`

107

108 The background parameter used for the image generation. Either `transparent` or `opaque`.

109

110 - `"transparent"`

111

112 - `"opaque"`

113

114 - `data: optional array of Image`

115

116 The list of generated images.

117

118 - `b64_json: optional string`

119

120 The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if `response_format` is set to `b64_json` for `dall-e-2` and `dall-e-3`.

121

122 - `revised_prompt: optional string`

123

124 For `dall-e-3` only, the revised prompt that was used to generate the image.

125

126 - `url: optional string`

127

128 When using `dall-e-2` or `dall-e-3`, the URL of the generated image if `response_format` is set to `url` (default value). Unsupported for the GPT image models.

129

130 - `output_format: optional "png" or "webp" or "jpeg"`

131

132 The output format of the image generation. Either `png`, `webp`, or `jpeg`.

133

134 - `"png"`

135

136 - `"webp"`

137

138 - `"jpeg"`

139

140 - `quality: optional "low" or "medium" or "high"`

141

142 The quality of the image generated. Either `low`, `medium`, or `high`.

143

144 - `"low"`

145

146 - `"medium"`

147

148 - `"high"`

149

150 - `size: optional "1024x1024" or "1024x1536" or "1536x1024"`

151

152 The size of the image generated. Either `1024x1024`, `1024x1536`, or `1536x1024`.

153

154 - `"1024x1024"`

155

156 - `"1024x1536"`

157

158 - `"1536x1024"`

159

160 - `usage: optional object { input_tokens, input_tokens_details, output_tokens, 2 more }`

161

162 For `gpt-image-1` only, the token usage information for the image generation.

163

164 - `input_tokens: number`

165

166 The number of tokens (images and text) in the input prompt.

167

168 - `input_tokens_details: object { image_tokens, text_tokens }`

169

170 The input tokens detailed information for the image generation.

171

172 - `image_tokens: number`

173

174 The number of image tokens in the input prompt.

175

176 - `text_tokens: number`

177

178 The number of text tokens in the input prompt.

179

180 - `output_tokens: number`

181

182 The number of output tokens generated by the model.

183

184 - `total_tokens: number`

185

186 The total number of tokens (images and text) used for the image generation.

187

188 - `output_tokens_details: optional object { image_tokens, text_tokens }`

189

190 The output token details for the image generation.

191

192 - `image_tokens: number`

193

194 The number of image output tokens generated by the model.

195

196 - `text_tokens: number`

197

198 The number of text output tokens generated by the model.

199

200### Example

201

202```cli

203openai images edit \

204 --api-key 'My API Key' \

205 --image 'Example data' \

206 --prompt 'A cute baby sea otter wearing a beret'

207```

208

209#### Response

210

211```json

212{

213 "created": 0,

214 "background": "transparent",

215 "data": [

216 {

217 "b64_json": "b64_json",

218 "revised_prompt": "revised_prompt",

219 "url": "https://example.com"

220 }

221 ],

222 "output_format": "png",

223 "quality": "low",

224 "size": "1024x1024",

225 "usage": {

226 "input_tokens": 0,

227 "input_tokens_details": {

228 "image_tokens": 0,

229 "text_tokens": 0

230 },

231 "output_tokens": 0,

232 "total_tokens": 0,

233 "output_tokens_details": {

234 "image_tokens": 0,

235 "text_tokens": 0

236 }

237 }

238}

239```