java/resources/images/methods/generate/index.md

Create image

ImagesResponse images().generate(ImageGenerateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())

post /images/generations

Creates an image given a prompt. Learn more.

Parameters

ImageGenerateParams params
- String prompt
  
  A text description of the desired image(s). The maximum length is 32000 characters for the GPT image models, 1000 characters for dall-e-2 and 4000 characters for dall-e-3.
- Optional<Background> background
  
  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.
  - TRANSPARENT("transparent")
  - OPAQUE("opaque")
  - AUTO("auto")
- Optional<ImageModel> model
  
  The model to use for image generation. One of dall-e-2, dall-e-3, or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, or gpt-image-2-2026-04-21). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.
- Optional<Moderation> moderation
  
  Control the content-moderation level for images generated by the GPT image models. Must be either low for less restrictive filtering or auto (default value).
  - LOW("low")
  - AUTO("auto")
- Optional<Long> n
  
  The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
- Optional<Long> outputCompression
  
  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.
- Optional<OutputFormat> outputFormat
  
  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.
  - PNG("png")
  - JPEG("jpeg")
  - WEBP("webp")
- Optional<Long> partialImages
  
  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.
- Optional<Quality> quality
  
  The quality of the image that will be generated.
  - auto (default value) will automatically select the best quality for the given model.
  - high, medium and low are supported for the GPT image models.
  - hd and standard are supported for dall-e-3.
  - standard is the only option for dall-e-2.
  - STANDARD("standard")
  - HD("hd")
  - LOW("low")
  - MEDIUM("medium")
  - HIGH("high")
  - AUTO("auto")
- Optional<ResponseFormat> responseFormat
  
  The format in which generated images with dall-e-2 and dall-e-3 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 isn't supported for the GPT image models, which always return base64-encoded images.
  - URL("url")
  - B64_JSON("b64_json")
- Optional<Size> size
  
  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.
  - AUTO("auto")
  - _1024X1024("1024x1024")
  - _1536X1024("1536x1024")
  - _1024X1536("1024x1536")
  - _256X256("256x256")
  - _512X512("512x512")
  - _1792X1024("1792x1024")
  - _1024X1792("1024x1792")
- Optional<Style> style
  
  The style of the generated images. This parameter is only supported for dall-e-3. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images.
  - VIVID("vivid")
  - NATURAL("natural")
- Optional<String> user
  
  A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

class ImagesResponse:

The response from the image generation endpoint.
- long created
  
  The Unix timestamp (in seconds) of when the image was created.
- Optional<Background> background
  
  The background parameter used for the image generation. Either transparent or opaque.
  - TRANSPARENT("transparent")
  - OPAQUE("opaque")
- Optional<List<Image>> data
  
  The list of generated images.
  - Optional<String> b64Json
    
    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.
  - Optional<String> revisedPrompt
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - Optional<String> url
    
    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.
- Optional<OutputFormat> outputFormat
  
  The output format of the image generation. Either png, webp, or jpeg.
  - PNG("png")
  - WEBP("webp")
  - JPEG("jpeg")
- Optional<Quality> quality
  
  The quality of the image generated. Either low, medium, or high.
  - LOW("low")
  - MEDIUM("medium")
  - HIGH("high")
- Optional<Size> size
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - _1024X1024("1024x1024")
  - _1024X1536("1024x1536")
  - _1536X1024("1536x1024")
- Optional<Usage> usage
  
  For gpt-image-1 only, the token usage information for the image generation.
  - long inputTokens
    
    The number of tokens (images and text) in the input prompt.
  - InputTokensDetails inputTokensDetails
    
    The input tokens detailed information for the image generation.
    - long imageTokens
      
      The number of image tokens in the input prompt.
    - long textTokens
      
      The number of text tokens in the input prompt.
  - long outputTokens
    
    The number of output tokens generated by the model.
  - long totalTokens
    
    The total number of tokens (images and text) used for the image generation.
  - Optional<OutputTokensDetails> outputTokensDetails
    
    The output token details for the image generation.
    - long imageTokens
      
      The number of image output tokens generated by the model.
    - long textTokens
      
      The number of text output tokens generated by the model.

Example

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.ImageGenerateParams;
import com.openai.models.images.ImagesResponse;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        ImageGenerateParams params = ImageGenerateParams.builder()
            .prompt("A cute baby sea otter")
            .build();
        ImagesResponse imagesResponse = client.images().generate(params);
    }
}

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
    }
  }
}

java/resources/images/methods/generate/index.md +297 −0 created

1## Create image

3`ImagesResponse images().generate(ImageGenerateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())`

5**post** `/images/generations`

7Creates an image given a prompt. [Learn more](https://platform.openai.com/docs/guides/images).

9### Parameters

11- `ImageGenerateParams params`

13 - `String prompt`

15 A text description of the desired image(s). The maximum length is 32000 characters for the GPT image models, 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`.

17 - `Optional<Background> background`

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

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

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

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

23 automatically determine the best background for the image.

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

26 transparent backgrounds. Requests with `background` set to

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

28 `auto` instead.

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

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

33 - `TRANSPARENT("transparent")`

35 - `OPAQUE("opaque")`

37 - `AUTO("auto")`

39 - `Optional<ImageModel> model`

41 The model to use for image generation. One of `dall-e-2`, `dall-e-3`, or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, or `gpt-image-2-2026-04-21`). Defaults to `dall-e-2` unless a parameter specific to the GPT image models is used.

43 - `Optional<Moderation> moderation`

45 Control the content-moderation level for images generated by the GPT image models. Must be either `low` for less restrictive filtering or `auto` (default value).

47 - `LOW("low")`

49 - `AUTO("auto")`

51 - `Optional<Long> n`

53 The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported.

55 - `Optional<Long> outputCompression`

57 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.

59 - `Optional<OutputFormat> outputFormat`

61 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`.

63 - `PNG("png")`

65 - `JPEG("jpeg")`

67 - `WEBP("webp")`

69 - `Optional<Long> partialImages`

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

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

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

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

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

78 - `Optional<Quality> quality`

80 The quality of the image that will be generated.

82 - `auto` (default value) will automatically select the best quality for the given model.

83 - `high`, `medium` and `low` are supported for the GPT image models.

84 - `hd` and `standard` are supported for `dall-e-3`.

85 - `standard` is the only option for `dall-e-2`.

87 - `STANDARD("standard")`

89 - `HD("hd")`

91 - `LOW("low")`

93 - `MEDIUM("medium")`

95 - `HIGH("high")`

97 - `AUTO("auto")`

99 - `Optional<ResponseFormat> responseFormat`

100

101 The format in which generated images with `dall-e-2` and `dall-e-3` 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 isn't supported for the GPT image models, which always return base64-encoded images.

102

103 - `URL("url")`

104

105 - `B64_JSON("b64_json")`

106

107 - `Optional<Size> size`

108

109 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`.

110

111 - `AUTO("auto")`

112

113 - `_1024X1024("1024x1024")`

114

115 - `_1536X1024("1536x1024")`

116

117 - `_1024X1536("1024x1536")`

118

119 - `_256X256("256x256")`

120

121 - `_512X512("512x512")`

122

123 - `_1792X1024("1792x1024")`

124

125 - `_1024X1792("1024x1792")`

126

127 - `Optional<Style> style`

128

129 The style of the generated images. This parameter is only supported for `dall-e-3`. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images.

130

131 - `VIVID("vivid")`

132

133 - `NATURAL("natural")`

134

135 - `Optional<String> user`

136

137 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).

138

139### Returns

140

141- `class ImagesResponse:`

142

143 The response from the image generation endpoint.

144

145 - `long created`

146

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

148

149 - `Optional<Background> background`

150

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

152

153 - `TRANSPARENT("transparent")`

154

155 - `OPAQUE("opaque")`

156

157 - `Optional<List<Image>> data`

158

159 The list of generated images.

160

161 - `Optional<String> b64Json`

162

163 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`.

164

165 - `Optional<String> revisedPrompt`

166

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

168

169 - `Optional<String> url`

170

171 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.

172

173 - `Optional<OutputFormat> outputFormat`

174

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

176

177 - `PNG("png")`

178

179 - `WEBP("webp")`

180

181 - `JPEG("jpeg")`

182

183 - `Optional<Quality> quality`

184

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

186

187 - `LOW("low")`

188

189 - `MEDIUM("medium")`

190

191 - `HIGH("high")`

192

193 - `Optional<Size> size`

194

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

196

197 - `_1024X1024("1024x1024")`

198

199 - `_1024X1536("1024x1536")`

200

201 - `_1536X1024("1536x1024")`

202

203 - `Optional<Usage> usage`

204

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

206

207 - `long inputTokens`

208

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

210

211 - `InputTokensDetails inputTokensDetails`

212

213 The input tokens detailed information for the image generation.

214

215 - `long imageTokens`

216

217 The number of image tokens in the input prompt.

218

219 - `long textTokens`

220

221 The number of text tokens in the input prompt.

222

223 - `long outputTokens`

224

225 The number of output tokens generated by the model.

226

227 - `long totalTokens`

228

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

230

231 - `Optional<OutputTokensDetails> outputTokensDetails`

232

233 The output token details for the image generation.

234

235 - `long imageTokens`

236

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

238

239 - `long textTokens`

240

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

242

243### Example

244

245```java

246package com.openai.example;

247

248import com.openai.client.OpenAIClient;

249import com.openai.client.okhttp.OpenAIOkHttpClient;

250import com.openai.models.images.ImageGenerateParams;

251import com.openai.models.images.ImagesResponse;

252

253public final class Main {

254 private Main() {}

255

256 public static void main(String[] args) {

257 OpenAIClient client = OpenAIOkHttpClient.fromEnv();

258

259 ImageGenerateParams params = ImageGenerateParams.builder()

260 .prompt("A cute baby sea otter")

261 .build();

262 ImagesResponse imagesResponse = client.images().generate(params);

263 }

264}

265```

266

267#### Response

268

269```json

270{

271 "created": 0,

272 "background": "transparent",

273 "data": [

274 {

275 "b64_json": "b64_json",

276 "revised_prompt": "revised_prompt",

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

278 }

279 ],

280 "output_format": "png",

281 "quality": "low",

282 "size": "1024x1024",

283 "usage": {

284 "input_tokens": 0,

285 "input_tokens_details": {

286 "image_tokens": 0,

287 "text_tokens": 0

288 },

289 "output_tokens": 0,

290 "total_tokens": 0,

291 "output_tokens_details": {

292 "image_tokens": 0,

293 "text_tokens": 0

294 }

295 }

296}

297```