openai 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d8ca71d5671f3a20cde2fda0eec819c5305ebd9e60aabcc55abf471f1de63b53
-  data.tar.gz: 1de944c9a0ee804f9d15567fec8038368458132183468c81ae42609c036e05ac
+  metadata.gz: 252a9ce9833b0a9f66be94b76081f34716e348ebca732e63c3e16c105ed42ea1
+  data.tar.gz: d4d8b36822ee74af77508ec8e48b472d72d619333e468055695158e242c49760
 SHA512:
-  metadata.gz: 822226e8ebc9b077c242ae0366ec3f5e4b0b413054cbc3e4d9e971347c79ccb9b64006a6af5cc5a88b25472103be1a5c9a2b3c9a5e25396951f454f9f15f2dc4
-  data.tar.gz: 6ed344972114e5c0f098d3e5619dc1548ac61557e7b3b23384d558e2f9ccbe1ee1dd00ee0ffa0f77b17027554c1c46d33bc6eb552695615bf0fd289cf0fb4dc1
+  metadata.gz: f27c40e40df727c8da570a4f6b1e20f72a87baa710efd3957bb0fbbcc23eb1dd78d03b1bcc3c3cf5684d4db4b062c392c1c3d970093c8e0fac89ef85db053db3
+  data.tar.gz: 21fe44d1605c6196d7321dcb7efa7d951a2523ba71859eab1bf242ff3314afe0cce25201c21b141f9f3902b684cb577ba51c520d12602d1279eccb770769e3a4

data/CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## 0.11.0 (2025-06-26)
+
+Full Changelog: [v0.10.0...v0.11.0](https://github.com/openai/openai-ruby/compare/v0.10.0...v0.11.0)
+
+### Features
+
+* **api:** webhook and deep research support ([6228400](https://github.com/openai/openai-ruby/commit/6228400e19aadefc5f87e24b3c104fc0b44d3cee))
+
+
+### Bug Fixes
+
+* **ci:** release-doctor — report correct token name ([c12c991](https://github.com/openai/openai-ruby/commit/c12c9911beaeb8b1c72d7c5cc5f14dcb9cd5452e))
+
+
+### Chores
+
+* **api:** remove unsupported property ([1073c3a](https://github.com/openai/openai-ruby/commit/1073c3a6059f2d1e1ef92937326699e0240503e5))
+* **client:** throw specific errors ([0cf937e](https://github.com/openai/openai-ruby/commit/0cf937ea8abebc05e52a419e19e275a45b5da646))
+* **docs:** update README to include links to docs on Webhooks ([2d8f23e](https://github.com/openai/openai-ruby/commit/2d8f23ecb245c88f3f082f93eb906af857d64c7d))
+
 ## 0.10.0 (2025-06-23)
 
 Full Changelog: [v0.9.0...v0.10.0](https://github.com/openai/openai-ruby/compare/v0.9.0...v0.10.0)

data/README.md

@@ -15,7 +15,7 @@ To use this gem, install via Bundler by adding the following to your application
 <!-- x-release-please-start-version -->
 
 ```ruby
-gem "openai", "~> 0.10.0"
+gem "openai", "~> 0.11.0"
 ```
 
 <!-- x-release-please-end -->
@@ -112,6 +112,84 @@ puts(edited.data.first)
 
 Note that you can also pass a raw `IO` descriptor, but this disables retries, as the library can't be sure if the descriptor is a file or pipe (which cannot be rewound).
 
+## Webhook Verification
+
+Verifying webhook signatures is _optional but encouraged_.
+
+For more information about webhooks, see [the API docs](https://platform.openai.com/docs/guides/webhooks).
+
+### Parsing webhook payloads
+
+For most use cases, you will likely want to verify the webhook and parse the payload at the same time. To achieve this, we provide the method `client.webhooks.unwrap`, which parses a webhook request and verifies that it was sent by OpenAI. This method will raise an error if the signature is invalid.
+
+Note that the `body` parameter must be the raw JSON string sent from the server (do not parse it first). The `unwrap` method will parse this JSON for you into an event object after verifying the webhook was sent from OpenAI.
+
+```ruby
+require 'sinatra'
+require 'openai'
+
+# Set up the client with webhook secret from environment variable
+client = OpenAI::Client.new(webhook_secret: ENV['OPENAI_WEBHOOK_SECRET'])
+
+post '/webhook' do
+  request_body = request.body.read
+  
+  begin
+    event = client.webhooks.unwrap(request_body, request.env)
+    
+    case event.type
+    when 'response.completed'
+      puts "Response completed: #{event.data}"
+    when 'response.failed'
+      puts "Response failed: #{event.data}"
+    else
+      puts "Unhandled event type: #{event.type}"
+    end
+    
+    status 200
+    'ok'
+  rescue StandardError => e
+    puts "Invalid signature: #{e}"
+    status 400
+    'Invalid signature'
+  end
+end
+```
+
+### Verifying webhook payloads directly
+
+In some cases, you may want to verify the webhook separately from parsing the payload. If you prefer to handle these steps separately, we provide the method `client.webhooks.verify_signature` to _only verify_ the signature of a webhook request. Like `unwrap`, this method will raise an error if the signature is invalid.
+
+Note that the `body` parameter must be the raw JSON string sent from the server (do not parse it first). You will then need to parse the body after verifying the signature.
+
+```ruby
+require 'sinatra'
+require 'json'
+require 'openai'
+
+# Set up the client with webhook secret from environment variable
+client = OpenAI::Client.new(webhook_secret: ENV['OPENAI_WEBHOOK_SECRET'])
+
+post '/webhook' do
+  request_body = request.body.read
+  
+  begin
+    client.webhooks.verify_signature(request_body, request.env)
+    
+    # Parse the body after verification
+    event = JSON.parse(request_body)
+    puts "Verified event: #{event}"
+    
+    status 200
+    'ok'
+  rescue StandardError => e
+    puts "Invalid signature: #{e}"
+    status 400
+    'Invalid signature'
+  end
+end
+```
+
 ### [Structured outputs](https://platform.openai.com/docs/guides/structured-outputs) and function calling
 
 This SDK ships with helpers in `OpenAI::BaseModel`, `OpenAI::ArrayOf`, `OpenAI::EnumOf`, and `OpenAI::UnionOf` to help you define the supported JSON schemas used in making structured outputs and function calling requests.

data/lib/openai/client.rb

@@ -24,6 +24,9 @@ module OpenAI
     # @return [String, nil]
     attr_reader :project
 
+    # @return [String, nil]
+    attr_reader :webhook_secret
+
     # @return [OpenAI::Resources::Completions]
     attr_reader :completions
 
@@ -57,6 +60,9 @@ module OpenAI
     # @return [OpenAI::Resources::VectorStores]
     attr_reader :vector_stores
 
+    # @return [OpenAI::Resources::Webhooks]
+    attr_reader :webhooks
+
     # @return [OpenAI::Resources::Beta]
     attr_reader :beta
 
@@ -92,6 +98,8 @@ module OpenAI
     #
     # @param project [String, nil] Defaults to `ENV["OPENAI_PROJECT_ID"]`
     #
+    # @param webhook_secret [String, nil] Defaults to `ENV["OPENAI_WEBHOOK_SECRET"]`
+    #
     # @param base_url [String, nil] Override the default base URL for the API, e.g.,
     # `"https://api.example.com/v2/"`. Defaults to `ENV["OPENAI_BASE_URL"]`
     #
@@ -106,6 +114,7 @@ module OpenAI
       api_key: ENV["OPENAI_API_KEY"],
       organization: ENV["OPENAI_ORG_ID"],
       project: ENV["OPENAI_PROJECT_ID"],
+      webhook_secret: ENV["OPENAI_WEBHOOK_SECRET"],
       base_url: ENV["OPENAI_BASE_URL"],
       max_retries: self.class::DEFAULT_MAX_RETRIES,
       timeout: self.class::DEFAULT_TIMEOUT_IN_SECONDS,
@@ -124,6 +133,7 @@ module OpenAI
       }
 
       @api_key = api_key.to_s
+      @webhook_secret = webhook_secret&.to_s
 
       super(
         base_url: base_url,
@@ -145,6 +155,7 @@ module OpenAI
       @fine_tuning = OpenAI::Resources::FineTuning.new(client: self)
       @graders = OpenAI::Resources::Graders.new(client: self)
       @vector_stores = OpenAI::Resources::VectorStores.new(client: self)
+      @webhooks = OpenAI::Resources::Webhooks.new(client: self)
       @beta = OpenAI::Resources::Beta.new(client: self)
       @batches = OpenAI::Resources::Batches.new(client: self)
       @uploads = OpenAI::Resources::Uploads.new(client: self)

data/lib/openai/errors.rb

@@ -8,6 +8,9 @@ module OpenAI
       #   @return [StandardError, nil]
     end
 
+    class InvalidWebhookSignatureError < OpenAI::Errors::Error
+    end
+
     class ConversionError < OpenAI::Errors::Error
       # @return [StandardError, nil]
       def cause = @cause.nil? ? super : @cause

data/lib/openai/models/all_models.rb

@@ -18,6 +18,10 @@ module OpenAI
         O1_PRO_2025_03_19 = :"o1-pro-2025-03-19"
         O3_PRO = :"o3-pro"
         O3_PRO_2025_06_10 = :"o3-pro-2025-06-10"
+        O3_DEEP_RESEARCH = :"o3-deep-research"
+        O3_DEEP_RESEARCH_2025_06_26 = :"o3-deep-research-2025-06-26"
+        O4_MINI_DEEP_RESEARCH = :"o4-mini-deep-research"
+        O4_MINI_DEEP_RESEARCH_2025_06_26 = :"o4-mini-deep-research-2025-06-26"
         COMPUTER_USE_PREVIEW = :"computer-use-preview"
         COMPUTER_USE_PREVIEW_2025_03_11 = :"computer-use-preview-2025-03-11"
 

data/lib/openai/models/chat/chat_completion.rb

@@ -39,23 +39,23 @@ module OpenAI
         required :object, const: :"chat.completion"
 
         # @!attribute service_tier
-        #   Specifies the latency tier to use for processing the request. This parameter is
-        #   relevant for customers subscribed to the scale tier service:
-        #
-        #   - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #     utilize scale tier credits until they are exhausted.
-        #   - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #     be processed using the default service tier with a lower uptime SLA and no
-        #     latency guarantee.
-        #   - If set to 'default', the request will be processed using the default service
-        #     tier with a lower uptime SLA and no latency guarantee.
-        #   - If set to 'flex', the request will be processed with the Flex Processing
-        #     service tier.
-        #     [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        #   Specifies the processing type used for serving the request.
+        #
+        #   - If set to 'auto', then the request will be processed with the service tier
+        #     configured in the Project settings. Unless otherwise configured, the Project
+        #     will use 'default'.
+        #   - If set to 'default', then the requset will be processed with the standard
+        #     pricing and performance for the selected model.
+        #   - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #     'priority', then the request will be processed with the corresponding service
+        #     tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #     Priority processing.
         #   - When not set, the default behavior is 'auto'.
         #
-        #   When this parameter is set, the response body will include the `service_tier`
-        #   utilized.
+        #   When the `service_tier` parameter is set, the response body will include the
+        #   `service_tier` value based on the processing mode actually used to serve the
+        #   request. This response value may be different from the value set in the
+        #   parameter.
         #
         #   @return [Symbol, OpenAI::Models::Chat::ChatCompletion::ServiceTier, nil]
         optional :service_tier, enum: -> { OpenAI::Chat::ChatCompletion::ServiceTier }, nil?: true
@@ -90,7 +90,7 @@ module OpenAI
         #
         #   @param model [String] The model used for the chat completion.
         #
-        #   @param service_tier [Symbol, OpenAI::Models::Chat::ChatCompletion::ServiceTier, nil] Specifies the latency tier to use for processing the request. This parameter is
+        #   @param service_tier [Symbol, OpenAI::Models::Chat::ChatCompletion::ServiceTier, nil] Specifies the processing type used for serving the request.
         #
         #   @param system_fingerprint [String] This fingerprint represents the backend configuration that the model runs with.
         #
@@ -188,23 +188,23 @@ module OpenAI
           end
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
-        #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # Specifies the processing type used for serving the request.
+        #
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         #
         # @see OpenAI::Models::Chat::ChatCompletion#service_tier
         module ServiceTier
@@ -214,6 +214,7 @@ module OpenAI
           DEFAULT = :default
           FLEX = :flex
           SCALE = :scale
+          PRIORITY = :priority
 
           # @!method self.values
           #   @return [Array<Symbol>]

data/lib/openai/models/chat/chat_completion_chunk.rb

@@ -38,23 +38,23 @@ module OpenAI
         required :object, const: :"chat.completion.chunk"
 
         # @!attribute service_tier
-        #   Specifies the latency tier to use for processing the request. This parameter is
-        #   relevant for customers subscribed to the scale tier service:
+        #   Specifies the processing type used for serving the request.
         #
-        #   - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #     utilize scale tier credits until they are exhausted.
-        #   - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #     be processed using the default service tier with a lower uptime SLA and no
-        #     latency guarantee.
-        #   - If set to 'default', the request will be processed using the default service
-        #     tier with a lower uptime SLA and no latency guarantee.
-        #   - If set to 'flex', the request will be processed with the Flex Processing
-        #     service tier.
-        #     [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        #   - If set to 'auto', then the request will be processed with the service tier
+        #     configured in the Project settings. Unless otherwise configured, the Project
+        #     will use 'default'.
+        #   - If set to 'default', then the requset will be processed with the standard
+        #     pricing and performance for the selected model.
+        #   - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #     'priority', then the request will be processed with the corresponding service
+        #     tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #     Priority processing.
         #   - When not set, the default behavior is 'auto'.
         #
-        #   When this parameter is set, the response body will include the `service_tier`
-        #   utilized.
+        #   When the `service_tier` parameter is set, the response body will include the
+        #   `service_tier` value based on the processing mode actually used to serve the
+        #   request. This response value may be different from the value set in the
+        #   parameter.
         #
         #   @return [Symbol, OpenAI::Models::Chat::ChatCompletionChunk::ServiceTier, nil]
         optional :service_tier, enum: -> { OpenAI::Chat::ChatCompletionChunk::ServiceTier }, nil?: true
@@ -95,7 +95,7 @@ module OpenAI
         #
         #   @param model [String] The model to generate the completion.
         #
-        #   @param service_tier [Symbol, OpenAI::Models::Chat::ChatCompletionChunk::ServiceTier, nil] Specifies the latency tier to use for processing the request. This parameter is
+        #   @param service_tier [Symbol, OpenAI::Models::Chat::ChatCompletionChunk::ServiceTier, nil] Specifies the processing type used for serving the request.
         #
         #   @param system_fingerprint [String] This fingerprint represents the backend configuration that the model runs with.
         #
@@ -371,23 +371,23 @@ module OpenAI
           end
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
+        # Specifies the processing type used for serving the request.
         #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         #
         # @see OpenAI::Models::Chat::ChatCompletionChunk#service_tier
         module ServiceTier
@@ -397,6 +397,7 @@ module OpenAI
           DEFAULT = :default
           FLEX = :flex
           SCALE = :scale
+          PRIORITY = :priority
 
           # @!method self.values
           #   @return [Array<Symbol>]

data/lib/openai/models/chat/completion_create_params.rb

@@ -219,23 +219,23 @@ module OpenAI
         optional :seed, Integer, nil?: true
 
         # @!attribute service_tier
-        #   Specifies the latency tier to use for processing the request. This parameter is
-        #   relevant for customers subscribed to the scale tier service:
-        #
-        #   - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #     utilize scale tier credits until they are exhausted.
-        #   - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #     be processed using the default service tier with a lower uptime SLA and no
-        #     latency guarantee.
-        #   - If set to 'default', the request will be processed using the default service
-        #     tier with a lower uptime SLA and no latency guarantee.
-        #   - If set to 'flex', the request will be processed with the Flex Processing
-        #     service tier.
-        #     [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        #   Specifies the processing type used for serving the request.
+        #
+        #   - If set to 'auto', then the request will be processed with the service tier
+        #     configured in the Project settings. Unless otherwise configured, the Project
+        #     will use 'default'.
+        #   - If set to 'default', then the requset will be processed with the standard
+        #     pricing and performance for the selected model.
+        #   - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #     'priority', then the request will be processed with the corresponding service
+        #     tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #     Priority processing.
         #   - When not set, the default behavior is 'auto'.
         #
-        #   When this parameter is set, the response body will include the `service_tier`
-        #   utilized.
+        #   When the `service_tier` parameter is set, the response body will include the
+        #   `service_tier` value based on the processing mode actually used to serve the
+        #   request. This response value may be different from the value set in the
+        #   parameter.
         #
         #   @return [Symbol, OpenAI::Models::Chat::CompletionCreateParams::ServiceTier, nil]
         optional :service_tier, enum: -> { OpenAI::Chat::CompletionCreateParams::ServiceTier }, nil?: true
@@ -254,6 +254,8 @@ module OpenAI
         #   our [model distillation](https://platform.openai.com/docs/guides/distillation)
         #   or [evals](https://platform.openai.com/docs/guides/evals) products.
         #
+        #   Supports text and image inputs. Note: image inputs over 10MB will be dropped.
+        #
         #   @return [Boolean, nil]
         optional :store, OpenAI::Internal::Type::Boolean, nil?: true
 
@@ -375,7 +377,7 @@ module OpenAI
         #
         #   @param seed [Integer, nil] This feature is in Beta.
         #
-        #   @param service_tier [Symbol, OpenAI::Models::Chat::CompletionCreateParams::ServiceTier, nil] Specifies the latency tier to use for processing the request. This parameter is
+        #   @param service_tier [Symbol, OpenAI::Models::Chat::CompletionCreateParams::ServiceTier, nil] Specifies the processing type used for serving the request.
         #
         #   @param stop [String, Array<String>, nil] Not supported with latest reasoning models `o3` and `o4-mini`.
         #
@@ -546,23 +548,23 @@ module OpenAI
           #   @return [Array(OpenAI::Models::ResponseFormatText, OpenAI::Models::ResponseFormatJSONSchema, OpenAI::Models::ResponseFormatJSONObject)]
         end
 
-        # Specifies the latency tier to use for processing the request. This parameter is
-        # relevant for customers subscribed to the scale tier service:
-        #
-        # - If set to 'auto', and the Project is Scale tier enabled, the system will
-        #   utilize scale tier credits until they are exhausted.
-        # - If set to 'auto', and the Project is not Scale tier enabled, the request will
-        #   be processed using the default service tier with a lower uptime SLA and no
-        #   latency guarantee.
-        # - If set to 'default', the request will be processed using the default service
-        #   tier with a lower uptime SLA and no latency guarantee.
-        # - If set to 'flex', the request will be processed with the Flex Processing
-        #   service tier.
-        #   [Learn more](https://platform.openai.com/docs/guides/flex-processing).
+        # Specifies the processing type used for serving the request.
+        #
+        # - If set to 'auto', then the request will be processed with the service tier
+        #   configured in the Project settings. Unless otherwise configured, the Project
+        #   will use 'default'.
+        # - If set to 'default', then the requset will be processed with the standard
+        #   pricing and performance for the selected model.
+        # - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
+        #   'priority', then the request will be processed with the corresponding service
+        #   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
+        #   Priority processing.
         # - When not set, the default behavior is 'auto'.
         #
-        # When this parameter is set, the response body will include the `service_tier`
-        # utilized.
+        # When the `service_tier` parameter is set, the response body will include the
+        # `service_tier` value based on the processing mode actually used to serve the
+        # request. This response value may be different from the value set in the
+        # parameter.
         module ServiceTier
           extend OpenAI::Internal::Type::Enum
 
@@ -570,6 +572,7 @@ module OpenAI
           DEFAULT = :default
           FLEX = :flex
           SCALE = :scale
+          PRIORITY = :priority
 
           # @!method self.values
           #   @return [Array<Symbol>]

data/lib/openai/models/images_response.rb

@@ -10,19 +10,45 @@ module OpenAI
       #   @return [Integer]
       required :created, Integer
 
+      # @!attribute background
+      #   The background parameter used for the image generation. Either `transparent` or
+      #   `opaque`.
+      #
+      #   @return [Symbol, OpenAI::Models::ImagesResponse::Background, nil]
+      optional :background, enum: -> { OpenAI::ImagesResponse::Background }
+
       # @!attribute data
       #   The list of generated images.
       #
       #   @return [Array<OpenAI::Models::Image>, nil]
       optional :data, -> { OpenAI::Internal::Type::ArrayOf[OpenAI::Image] }
 
+      # @!attribute output_format
+      #   The output format of the image generation. Either `png`, `webp`, or `jpeg`.
+      #
+      #   @return [Symbol, OpenAI::Models::ImagesResponse::OutputFormat, nil]
+      optional :output_format, enum: -> { OpenAI::ImagesResponse::OutputFormat }
+
+      # @!attribute quality
+      #   The quality of the image generated. Either `low`, `medium`, or `high`.
+      #
+      #   @return [Symbol, OpenAI::Models::ImagesResponse::Quality, nil]
+      optional :quality, enum: -> { OpenAI::ImagesResponse::Quality }
+
+      # @!attribute size
+      #   The size of the image generated. Either `1024x1024`, `1024x1536`, or
+      #   `1536x1024`.
+      #
+      #   @return [Symbol, OpenAI::Models::ImagesResponse::Size, nil]
+      optional :size, enum: -> { OpenAI::ImagesResponse::Size }
+
       # @!attribute usage
       #   For `gpt-image-1` only, the token usage information for the image generation.
       #
       #   @return [OpenAI::Models::ImagesResponse::Usage, nil]
       optional :usage, -> { OpenAI::ImagesResponse::Usage }
 
-      # @!method initialize(created:, data: nil, usage: nil)
+      # @!method initialize(created:, background: nil, data: nil, output_format: nil, quality: nil, size: nil, usage: nil)
       #   Some parameter documentations has been truncated, see
       #   {OpenAI::Models::ImagesResponse} for more details.
       #
@@ -30,10 +56,75 @@ module OpenAI
       #
       #   @param created [Integer] The Unix timestamp (in seconds) of when the image was created.
       #
+      #   @param background [Symbol, OpenAI::Models::ImagesResponse::Background] The background parameter used for the image generation. Either `transparent` or
+      #
       #   @param data [Array<OpenAI::Models::Image>] The list of generated images.
       #
+      #   @param output_format [Symbol, OpenAI::Models::ImagesResponse::OutputFormat] The output format of the image generation. Either `png`, `webp`, or `jpeg`.
+      #
+      #   @param quality [Symbol, OpenAI::Models::ImagesResponse::Quality] The quality of the image generated. Either `low`, `medium`, or `high`.
+      #
+      #   @param size [Symbol, OpenAI::Models::ImagesResponse::Size] The size of the image generated. Either `1024x1024`, `1024x1536`, or `1536x1024`
+      #
       #   @param usage [OpenAI::Models::ImagesResponse::Usage] For `gpt-image-1` only, the token usage information for the image generation.
 
+      # The background parameter used for the image generation. Either `transparent` or
+      # `opaque`.
+      #
+      # @see OpenAI::Models::ImagesResponse#background
+      module Background
+        extend OpenAI::Internal::Type::Enum
+
+        TRANSPARENT = :transparent
+        OPAQUE = :opaque
+
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+
+      # The output format of the image generation. Either `png`, `webp`, or `jpeg`.
+      #
+      # @see OpenAI::Models::ImagesResponse#output_format
+      module OutputFormat
+        extend OpenAI::Internal::Type::Enum
+
+        PNG = :png
+        WEBP = :webp
+        JPEG = :jpeg
+
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+
+      # The quality of the image generated. Either `low`, `medium`, or `high`.
+      #
+      # @see OpenAI::Models::ImagesResponse#quality
+      module Quality
+        extend OpenAI::Internal::Type::Enum
+
+        LOW = :low
+        MEDIUM = :medium
+        HIGH = :high
+
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+
+      # The size of the image generated. Either `1024x1024`, `1024x1536`, or
+      # `1536x1024`.
+      #
+      # @see OpenAI::Models::ImagesResponse#size
+      module Size
+        extend OpenAI::Internal::Type::Enum
+
+        SIZE_1024X1024 = :"1024x1024"
+        SIZE_1024X1536 = :"1024x1536"
+        SIZE_1536X1024 = :"1536x1024"
+
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+
       # @see OpenAI::Models::ImagesResponse#usage
       class Usage < OpenAI::Internal::Type::BaseModel
         # @!attribute input_tokens