feat(api): gpt 5.1

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 135
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-eeba8addf3a5f412e5ce8d22031e60c61650cee3f5d9e587a2533f6818a249ea.yml
-openapi_spec_hash: 0a4d8ad2469823ce24a3fd94f23f1c2b
-config_hash: 630eea84bb3067d25640419af058ed56
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-ca24bc4d8125b5153514ce643c4e3220f25971b7d67ca384d56d493c72c0d977.yml
+openapi_spec_hash: c6f048c7b3d29f4de48fde0e845ba33f
+config_hash: b876221dfb213df9f0a999e75d38a65e

README.md

@@ -30,7 +30,10 @@ openai = OpenAI::Client.new(
   api_key: ENV["OPENAI_API_KEY"] # This is the default and can be omitted
 )
 
-chat_completion = openai.chat.completions.create(messages: [{role: "user", content: "Say this is a test"}], model: :"gpt-5")
+chat_completion = openai.chat.completions.create(
+  messages: [{role: "user", content: "Say this is a test"}],
+  model: :"gpt-5.1"
+)
 
 puts(chat_completion)
 ```
@@ -42,7 +45,7 @@ We provide support for streaming responses using Server-Sent Events (SSE).
 ```ruby
 stream = openai.responses.stream(
   input: "Write a haiku about OpenAI.",
-  model: :"gpt-5"
+  model: :"gpt-5.1"
 )
 
 stream.each do |event|
@@ -340,7 +343,7 @@ openai = OpenAI::Client.new(
 # Or, configure per-request:
 openai.chat.completions.create(
   messages: [{role: "user", content: "How can I get the name of the current day in JavaScript?"}],
-  model: :"gpt-5",
+  model: :"gpt-5.1",
   request_options: {max_retries: 5}
 )
 ```
@@ -358,7 +361,7 @@ openai = OpenAI::Client.new(
 # Or, configure per-request:
 openai.chat.completions.create(
   messages: [{role: "user", content: "How can I list all files in a directory using Python?"}],
-  model: :"gpt-5",
+  model: :"gpt-5.1",
   request_options: {timeout: 5}
 )
 ```
@@ -393,7 +396,7 @@ Note: the `extra_` parameters of the same name overrides the documented paramete
 chat_completion =
   openai.chat.completions.create(
     messages: [{role: "user", content: "How can I get the name of the current day in JavaScript?"}],
-    model: :"gpt-5",
+    model: :"gpt-5.1",
     request_options: {
       extra_query: {my_query_parameter: value},
       extra_body: {my_body_parameter: value},
@@ -441,20 +444,23 @@ You can provide typesafe request parameters like so:
 ```ruby
 openai.chat.completions.create(
   messages: [OpenAI::Chat::ChatCompletionUserMessageParam.new(content: "Say this is a test")],
-  model: :"gpt-5"
+  model: :"gpt-5.1"
 )
 ```
 
 Or, equivalently:
 
 ```ruby
 # Hashes work, but are not typesafe:
-openai.chat.completions.create(messages: [{role: "user", content: "Say this is a test"}], model: :"gpt-5")
+openai.chat.completions.create(
+  messages: [{role: "user", content: "Say this is a test"}],
+  model: :"gpt-5.1"
+)
 
 # You can also splat a full Params class:
 params = OpenAI::Chat::CompletionCreateParams.new(
   messages: [OpenAI::Chat::ChatCompletionUserMessageParam.new(content: "Say this is a test")],
-  model: :"gpt-5"
+  model: :"gpt-5.1"
 )
 openai.chat.completions.create(**params)
 ```
@@ -464,25 +470,25 @@ openai.chat.completions.create(**params)
 Since this library does not depend on `sorbet-runtime`, it cannot provide [`T::Enum`](https://sorbet.org/docs/tenum) instances. Instead, we provide "tagged symbols" instead, which is always a primitive at runtime:
 
 ```ruby
-# :minimal
-puts(OpenAI::ReasoningEffort::MINIMAL)
+# :"in-memory"
+puts(OpenAI::Chat::CompletionCreateParams::PromptCacheRetention::IN_MEMORY)
 
-# Revealed type: `T.all(OpenAI::ReasoningEffort, Symbol)`
-T.reveal_type(OpenAI::ReasoningEffort::MINIMAL)
+# Revealed type: `T.all(OpenAI::Chat::CompletionCreateParams::PromptCacheRetention, Symbol)`
+T.reveal_type(OpenAI::Chat::CompletionCreateParams::PromptCacheRetention::IN_MEMORY)
 ```
 
 Enum parameters have a "relaxed" type, so you can either pass in enum constants or their literal value:
 
 ```ruby
 # Using the enum constants preserves the tagged type information:
 openai.chat.completions.create(
-  reasoning_effort: OpenAI::ReasoningEffort::MINIMAL,
+  prompt_cache_retention: OpenAI::Chat::CompletionCreateParams::PromptCacheRetention::IN_MEMORY,
   # …
 )
 
 # Literal values are also permissible:
 openai.chat.completions.create(
-  reasoning_effort: :minimal,
+  prompt_cache_retention: :"in-memory",
   # …
 )
 ```

lib/openai.rb

@@ -528,15 +528,19 @@
 require_relative "openai/models/response_format_text"
 require_relative "openai/models/response_format_text_grammar"
 require_relative "openai/models/response_format_text_python"
+require_relative "openai/models/responses/apply_patch_tool"
 require_relative "openai/models/responses/computer_tool"
 require_relative "openai/models/responses/custom_tool"
 require_relative "openai/models/responses/easy_input_message"
 require_relative "openai/models/responses/file_search_tool"
+require_relative "openai/models/responses/function_shell_tool"
 require_relative "openai/models/responses/function_tool"
 require_relative "openai/models/responses/input_item_list_params"
 require_relative "openai/models/responses/input_token_count_params"
 require_relative "openai/models/responses/input_token_count_response"
 require_relative "openai/models/responses/response"
+require_relative "openai/models/responses/response_apply_patch_tool_call"
+require_relative "openai/models/responses/response_apply_patch_tool_call_output"
 require_relative "openai/models/responses/response_audio_delta_event"
 require_relative "openai/models/responses/response_audio_done_event"
 require_relative "openai/models/responses/response_audio_transcript_delta_event"
@@ -576,6 +580,9 @@
 require_relative "openai/models/responses/response_function_call_arguments_done_event"
 require_relative "openai/models/responses/response_function_call_output_item"
 require_relative "openai/models/responses/response_function_call_output_item_list"
+require_relative "openai/models/responses/response_function_shell_call_output_content"
+require_relative "openai/models/responses/response_function_shell_tool_call"
+require_relative "openai/models/responses/response_function_shell_tool_call_output"
 require_relative "openai/models/responses/response_function_tool_call_item"
 require_relative "openai/models/responses/response_function_tool_call_output_item"
 require_relative "openai/models/responses/response_function_web_search"
@@ -634,10 +641,12 @@
 require_relative "openai/models/responses/response_web_search_call_searching_event"
 require_relative "openai/models/responses/tool"
 require_relative "openai/models/responses/tool_choice_allowed"
+require_relative "openai/models/responses/tool_choice_apply_patch"
 require_relative "openai/models/responses/tool_choice_custom"
 require_relative "openai/models/responses/tool_choice_function"
 require_relative "openai/models/responses/tool_choice_mcp"
 require_relative "openai/models/responses/tool_choice_options"
+require_relative "openai/models/responses/tool_choice_shell"
 require_relative "openai/models/responses/tool_choice_types"
 require_relative "openai/models/responses/web_search_preview_tool"
 require_relative "openai/models/responses/web_search_tool"

lib/openai/internal/type/enum.rb

@@ -19,23 +19,23 @@ module Type
       # @example
       #   # `chat_model` is a `OpenAI::ChatModel`
       #   case chat_model
-      #   when OpenAI::ChatModel::GPT_5
+      #   when OpenAI::ChatModel::GPT_5_1
       #     # ...
-      #   when OpenAI::ChatModel::GPT_5_MINI
+      #   when OpenAI::ChatModel::GPT_5_1_2025_11_13
       #     # ...
-      #   when OpenAI::ChatModel::GPT_5_NANO
+      #   when OpenAI::ChatModel::GPT_5_1_CODEX
       #     # ...
       #   else
       #     puts(chat_model)
       #   end
       #
       # @example
       #   case chat_model
-      #   in :"gpt-5"
+      #   in :"gpt-5.1"
       #     # ...
-      #   in :"gpt-5-mini"
+      #   in :"gpt-5.1-2025-11-13"
       #     # ...
-      #   in :"gpt-5-nano"
+      #   in :"gpt-5.1-codex"
       #     # ...
       #   else
       #     puts(chat_model)

lib/openai/models/batch_create_params.rb

@@ -16,9 +16,10 @@ class BatchCreateParams < OpenAI::Internal::Type::BaseModel
 
       # @!attribute endpoint
       #   The endpoint to be used for all requests in the batch. Currently
-      #   `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions`
-      #   are supported. Note that `/v1/embeddings` batches are also restricted to a
-      #   maximum of 50,000 embedding inputs across all requests in the batch.
+      #   `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, `/v1/completions`,
+      #   and `/v1/moderations` are supported. Note that `/v1/embeddings` batches are also
+      #   restricted to a maximum of 50,000 embedding inputs across all requests in the
+      #   batch.
       #
       #   @return [Symbol, OpenAI::Models::BatchCreateParams::Endpoint]
       required :endpoint, enum: -> { OpenAI::BatchCreateParams::Endpoint }
@@ -83,16 +84,18 @@ module CompletionWindow
       end
 
       # The endpoint to be used for all requests in the batch. Currently
-      # `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions`
-      # are supported. Note that `/v1/embeddings` batches are also restricted to a
-      # maximum of 50,000 embedding inputs across all requests in the batch.
+      # `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, `/v1/completions`,
+      # and `/v1/moderations` are supported. Note that `/v1/embeddings` batches are also
+      # restricted to a maximum of 50,000 embedding inputs across all requests in the
+      # batch.
       module Endpoint
         extend OpenAI::Internal::Type::Enum
 
         V1_RESPONSES = :"/v1/responses"
         V1_CHAT_COMPLETIONS = :"/v1/chat/completions"
         V1_EMBEDDINGS = :"/v1/embeddings"
         V1_COMPLETIONS = :"/v1/completions"
+        V1_MODERATIONS = :"/v1/moderations"
 
         # @!method self.values
         #   @return [Array<Symbol>]

lib/openai/models/beta/assistant_create_params.rb

@@ -51,12 +51,16 @@ class AssistantCreateParams < OpenAI::Internal::Type::BaseModel
         # @!attribute reasoning_effort
         #   Constrains effort on reasoning for
         #   [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-        #   supported values are `minimal`, `low`, `medium`, and `high`. Reducing reasoning
-        #   effort can result in faster responses and fewer tokens used on reasoning in a
-        #   response.
+        #   supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+        #   reasoning effort can result in faster responses and fewer tokens used on
+        #   reasoning in a response.
         #
-        #   Note: The `gpt-5-pro` model defaults to (and only supports) `high` reasoning
-        #   effort.
+        #   - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+        #     reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+        #     calls are supported for all reasoning values in gpt-5.1.
+        #   - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+        #     support `none`.
+        #   - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
         #
         #   @return [Symbol, OpenAI::Models::ReasoningEffort, nil]
         optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true

lib/openai/models/beta/assistant_update_params.rb

@@ -51,12 +51,16 @@ class AssistantUpdateParams < OpenAI::Internal::Type::BaseModel
         # @!attribute reasoning_effort
         #   Constrains effort on reasoning for
         #   [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-        #   supported values are `minimal`, `low`, `medium`, and `high`. Reducing reasoning
-        #   effort can result in faster responses and fewer tokens used on reasoning in a
-        #   response.
+        #   supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+        #   reasoning effort can result in faster responses and fewer tokens used on
+        #   reasoning in a response.
         #
-        #   Note: The `gpt-5-pro` model defaults to (and only supports) `high` reasoning
-        #   effort.
+        #   - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+        #     reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+        #     calls are supported for all reasoning values in gpt-5.1.
+        #   - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+        #     support `none`.
+        #   - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
         #
         #   @return [Symbol, OpenAI::Models::ReasoningEffort, nil]
         optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true

lib/openai/models/beta/threads/run_create_params.rb

@@ -109,12 +109,16 @@ class RunCreateParams < OpenAI::Internal::Type::BaseModel
           # @!attribute reasoning_effort
           #   Constrains effort on reasoning for
           #   [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-          #   supported values are `minimal`, `low`, `medium`, and `high`. Reducing reasoning
-          #   effort can result in faster responses and fewer tokens used on reasoning in a
-          #   response.
-          #
-          #   Note: The `gpt-5-pro` model defaults to (and only supports) `high` reasoning
-          #   effort.
+          #   supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+          #   reasoning effort can result in faster responses and fewer tokens used on
+          #   reasoning in a response.
+          #
+          #   - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+          #     reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+          #     calls are supported for all reasoning values in gpt-5.1.
+          #   - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+          #     support `none`.
+          #   - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
           #
           #   @return [Symbol, OpenAI::Models::ReasoningEffort, nil]
           optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true

lib/openai/models/chat/completion_create_params.rb

@@ -190,15 +190,30 @@ class CompletionCreateParams < OpenAI::Internal::Type::BaseModel
         #   @return [String, nil]
         optional :prompt_cache_key, String
 
+        # @!attribute prompt_cache_retention
+        #   The retention policy for the prompt cache. Set to `24h` to enable extended
+        #   prompt caching, which keeps cached prefixes active for longer, up to a maximum
+        #   of 24 hours.
+        #   [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+        #
+        #   @return [Symbol, OpenAI::Models::Chat::CompletionCreateParams::PromptCacheRetention, nil]
+        optional :prompt_cache_retention,
+                 enum: -> { OpenAI::Chat::CompletionCreateParams::PromptCacheRetention },
+                 nil?: true
+
         # @!attribute reasoning_effort
         #   Constrains effort on reasoning for
         #   [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-        #   supported values are `minimal`, `low`, `medium`, and `high`. Reducing reasoning
-        #   effort can result in faster responses and fewer tokens used on reasoning in a
-        #   response.
+        #   supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
+        #   reasoning effort can result in faster responses and fewer tokens used on
+        #   reasoning in a response.
         #
-        #   Note: The `gpt-5-pro` model defaults to (and only supports) `high` reasoning
-        #   effort.
+        #   - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
+        #     reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
+        #     calls are supported for all reasoning values in gpt-5.1.
+        #   - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
+        #     support `none`.
+        #   - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
         #
         #   @return [Symbol, OpenAI::Models::ReasoningEffort, nil]
         optional :reasoning_effort, enum: -> { OpenAI::ReasoningEffort }, nil?: true
@@ -368,7 +383,7 @@ class CompletionCreateParams < OpenAI::Internal::Type::BaseModel
         #   @return [OpenAI::Models::Chat::CompletionCreateParams::WebSearchOptions, nil]
         optional :web_search_options, -> { OpenAI::Chat::CompletionCreateParams::WebSearchOptions }
 
-        # @!method initialize(messages:, model:, audio: nil, frequency_penalty: nil, function_call: nil, functions: nil, logit_bias: nil, logprobs: nil, max_completion_tokens: nil, max_tokens: nil, metadata: nil, modalities: nil, n: nil, parallel_tool_calls: nil, prediction: nil, presence_penalty: nil, prompt_cache_key: nil, reasoning_effort: nil, response_format: nil, safety_identifier: nil, seed: nil, service_tier: nil, stop: nil, store: nil, stream_options: nil, temperature: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, user: nil, verbosity: nil, web_search_options: nil, request_options: {})
+        # @!method initialize(messages:, model:, audio: nil, frequency_penalty: nil, function_call: nil, functions: nil, logit_bias: nil, logprobs: nil, max_completion_tokens: nil, max_tokens: nil, metadata: nil, modalities: nil, n: nil, parallel_tool_calls: nil, prediction: nil, presence_penalty: nil, prompt_cache_key: nil, prompt_cache_retention: nil, reasoning_effort: nil, response_format: nil, safety_identifier: nil, seed: nil, service_tier: nil, stop: nil, store: nil, stream_options: nil, temperature: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, user: nil, verbosity: nil, web_search_options: nil, request_options: {})
         #   Some parameter documentations has been truncated, see
         #   {OpenAI::Models::Chat::CompletionCreateParams} for more details.
         #
@@ -406,6 +421,8 @@ class CompletionCreateParams < OpenAI::Internal::Type::BaseModel
         #
         #   @param prompt_cache_key [String] Used by OpenAI to cache responses for similar requests to optimize your cache hi
         #
+        #   @param prompt_cache_retention [Symbol, OpenAI::Models::Chat::CompletionCreateParams::PromptCacheRetention, nil] The retention policy for the prompt cache. Set to `24h` to enable extended promp
+        #
         #   @param reasoning_effort [Symbol, OpenAI::Models::ReasoningEffort, nil] Constrains effort on reasoning for
         #
         #   @param response_format [OpenAI::Models::ResponseFormatText, OpenAI::Models::ResponseFormatJSONSchema, OpenAI::StructuredOutput::JsonSchemaConverter, OpenAI::Models::ResponseFormatJSONObject] An object specifying the format that the model must output.
@@ -551,6 +568,20 @@ module Modality
           #   @return [Array<Symbol>]
         end
 
+        # The retention policy for the prompt cache. Set to `24h` to enable extended
+        # prompt caching, which keeps cached prefixes active for longer, up to a maximum
+        # of 24 hours.
+        # [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+        module PromptCacheRetention
+          extend OpenAI::Internal::Type::Enum
+
+          IN_MEMORY = :"in-memory"
+          PROMPT_CACHE_RETENTION_24H = :"24h"
+
+          # @!method self.values
+          #   @return [Array<Symbol>]
+        end
+
         # An object specifying the format that the model must output.
         #
         # Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured

lib/openai/models/chat_model.rb

@@ -5,6 +5,11 @@ module Models
     module ChatModel
       extend OpenAI::Internal::Type::Enum
 
+      GPT_5_1 = :"gpt-5.1"
+      GPT_5_1_2025_11_13 = :"gpt-5.1-2025-11-13"
+      GPT_5_1_CODEX = :"gpt-5.1-codex"
+      GPT_5_1_MINI = :"gpt-5.1-mini"
+      GPT_5_1_CHAT_LATEST = :"gpt-5.1-chat-latest"
       GPT_5 = :"gpt-5"
       GPT_5_MINI = :"gpt-5-mini"
       GPT_5_NANO = :"gpt-5-nano"