Commit dfdcf571

Stainless Bot <dev+git@stainlessapi.com>
2024-11-05 06:47:52
feat(api): add support for predicted outputs (#1847)
1 parent cb88c2f
src/openai/resources/audio/speech.py
@@ -70,13 +70,13 @@ class Speech(SyncAPIResource):
           input: The text to generate audio for. The maximum length is 4096 characters.
 
           model:
-              One of the available [TTS models](https://platform.openai.com/docs/models/tts):
+              One of the available [TTS models](https://platform.openai.com/docs/models#tts):
               `tts-1` or `tts-1-hd`
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`,
               `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
               available in the
-              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech/voice-options).
+              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
 
           response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
               `wav`, and `pcm`.
@@ -154,13 +154,13 @@ class AsyncSpeech(AsyncAPIResource):
           input: The text to generate audio for. The maximum length is 4096 characters.
 
           model:
-              One of the available [TTS models](https://platform.openai.com/docs/models/tts):
+              One of the available [TTS models](https://platform.openai.com/docs/models#tts):
               `tts-1` or `tts-1-hd`
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`,
               `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are
               available in the
-              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech/voice-options).
+              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
 
           response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
               `wav`, and `pcm`.
src/openai/resources/audio/transcriptions.py
@@ -143,7 +143,7 @@ class Transcriptions(SyncAPIResource):
 
           prompt: An optional text to guide the model's style or continue a previous audio
               segment. The
-              [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
               should match the audio language.
 
           response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
@@ -307,7 +307,7 @@ class AsyncTranscriptions(AsyncAPIResource):
 
           prompt: An optional text to guide the model's style or continue a previous audio
               segment. The
-              [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
               should match the audio language.
 
           response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
src/openai/resources/audio/translations.py
@@ -130,7 +130,7 @@ class Translations(SyncAPIResource):
 
           prompt: An optional text to guide the model's style or continue a previous audio
               segment. The
-              [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
               should be in English.
 
           response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
@@ -273,7 +273,7 @@ class AsyncTranslations(AsyncAPIResource):
 
           prompt: An optional text to guide the model's style or continue a previous audio
               segment. The
-              [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
               should be in English.
 
           response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
src/openai/resources/beta/threads/runs/runs.py
@@ -122,7 +122,7 @@ class Runs(SyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -158,12 +158,12 @@ class Runs(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -266,7 +266,7 @@ class Runs(SyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -302,12 +302,12 @@ class Runs(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -406,7 +406,7 @@ class Runs(SyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -442,12 +442,12 @@ class Runs(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -674,8 +674,8 @@ class Runs(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
@@ -1484,7 +1484,7 @@ class AsyncRuns(AsyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -1520,12 +1520,12 @@ class AsyncRuns(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1628,7 +1628,7 @@ class AsyncRuns(AsyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -1664,12 +1664,12 @@ class AsyncRuns(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1768,7 +1768,7 @@ class AsyncRuns(AsyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           additional_instructions: Appends additional instructions at the end of the instructions for the run. This
@@ -1804,12 +1804,12 @@ class AsyncRuns(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -2037,8 +2037,8 @@ class AsyncRuns(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
src/openai/resources/beta/threads/runs/steps.py
@@ -68,7 +68,7 @@ class Steps(SyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           extra_headers: Send extra headers
@@ -126,15 +126,15 @@ class Steps(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           include: A list of additional fields to include in the response. Currently the only
               supported value is `step_details.tool_calls[*].file_search.results[*].content`
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
@@ -222,7 +222,7 @@ class AsyncSteps(AsyncAPIResource):
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           extra_headers: Send extra headers
@@ -280,15 +280,15 @@ class AsyncSteps(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           include: A list of additional fields to include in the response. Currently the only
               supported value is `step_details.tool_calls[*].file_search.results[*].content`
               to fetch the file search result content.
 
               See the
-              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+              [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
               for more information.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
src/openai/resources/beta/threads/messages.py
@@ -221,8 +221,8 @@ class Messages(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
@@ -495,8 +495,8 @@ class AsyncMessages(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
src/openai/resources/beta/threads/threads.py
@@ -326,12 +326,12 @@ class Threads(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -460,12 +460,12 @@ class Threads(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -590,12 +590,12 @@ class Threads(SyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1160,12 +1160,12 @@ class AsyncThreads(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1294,12 +1294,12 @@ class AsyncThreads(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1424,12 +1424,12 @@ class AsyncThreads(AsyncAPIResource):
               assistant will be used.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/resources/beta/vector_stores/file_batches.py
@@ -227,8 +227,8 @@ class FileBatches(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           filter: Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
 
@@ -556,8 +556,8 @@ class AsyncFileBatches(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           filter: Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
 
src/openai/resources/beta/vector_stores/files.py
@@ -164,8 +164,8 @@ class Files(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           filter: Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
 
@@ -476,8 +476,8 @@ class AsyncFiles(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           filter: Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.
 
src/openai/resources/beta/vector_stores/vector_stores.py
@@ -251,8 +251,8 @@ class VectorStores(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
@@ -529,8 +529,8 @@ class AsyncVectorStores(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
src/openai/resources/beta/assistants.py
@@ -79,8 +79,8 @@ class Assistants(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           description: The description of the assistant. The maximum length is 512 characters.
 
@@ -95,8 +95,8 @@ class Assistants(SyncAPIResource):
           name: The name of the assistant. The maximum length is 256 characters.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -239,14 +239,14 @@ class Assistants(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           name: The name of the assistant. The maximum length is 256 characters.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -344,8 +344,8 @@ class Assistants(SyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
@@ -465,8 +465,8 @@ class AsyncAssistants(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           description: The description of the assistant. The maximum length is 512 characters.
 
@@ -481,8 +481,8 @@ class AsyncAssistants(AsyncAPIResource):
           name: The name of the assistant. The maximum length is 256 characters.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -625,14 +625,14 @@ class AsyncAssistants(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           name: The name of the assistant. The maximum length is 256 characters.
 
           response_format: Specifies the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
               and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -730,8 +730,8 @@ class AsyncAssistants(AsyncAPIResource):
 
           before: A cursor for use in pagination. `before` is an object ID that defines your place
               in the list. For instance, if you make a list request and receive 100 objects,
-              ending with obj_foo, your subsequent call can include before=obj_foo in order to
-              fetch the previous page of the list.
+              starting with obj_foo, your subsequent call can include before=obj_foo in order
+              to fetch the previous page of the list.
 
           limit: A limit on the number of objects to be returned. Limit can range between 1 and
               100, and the default is 20.
src/openai/resources/chat/completions.py
@@ -33,6 +33,7 @@ from ...types.chat.chat_completion_tool_param import ChatCompletionToolParam
 from ...types.chat.chat_completion_audio_param import ChatCompletionAudioParam
 from ...types.chat.chat_completion_message_param import ChatCompletionMessageParam
 from ...types.chat.chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
+from ...types.chat.chat_completion_prediction_content_param import ChatCompletionPredictionContentParam
 from ...types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
 
 __all__ = ["Completions", "AsyncCompletions"]
@@ -76,6 +77,7 @@ class Completions(SyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -113,7 +115,7 @@ class Completions(SyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           audio: Parameters for audio output. Required when audio output is requested with
@@ -124,7 +126,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -185,19 +187,22 @@ class Completions(SyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -284,7 +289,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -315,6 +320,7 @@ class Completions(SyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -351,7 +357,7 @@ class Completions(SyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           stream: If set, partial message deltas will be sent, like in ChatGPT. Tokens will be
@@ -369,7 +375,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -430,19 +436,22 @@ class Completions(SyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -522,7 +531,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -553,6 +562,7 @@ class Completions(SyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -589,7 +599,7 @@ class Completions(SyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           stream: If set, partial message deltas will be sent, like in ChatGPT. Tokens will be
@@ -607,7 +617,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -668,19 +678,22 @@ class Completions(SyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -760,7 +773,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -790,6 +803,7 @@ class Completions(SyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -830,6 +844,7 @@ class Completions(SyncAPIResource):
                     "modalities": modalities,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
                     "presence_penalty": presence_penalty,
                     "response_format": response_format,
                     "seed": seed,
@@ -894,6 +909,7 @@ class AsyncCompletions(AsyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -931,7 +947,7 @@ class AsyncCompletions(AsyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           audio: Parameters for audio output. Required when audio output is requested with
@@ -942,7 +958,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -1003,19 +1019,22 @@ class AsyncCompletions(AsyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1102,7 +1121,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -1133,6 +1152,7 @@ class AsyncCompletions(AsyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -1169,7 +1189,7 @@ class AsyncCompletions(AsyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           stream: If set, partial message deltas will be sent, like in ChatGPT. Tokens will be
@@ -1187,7 +1207,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -1248,19 +1268,22 @@ class AsyncCompletions(AsyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1340,7 +1363,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -1371,6 +1394,7 @@ class AsyncCompletions(AsyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -1407,7 +1431,7 @@ class AsyncCompletions(AsyncAPIResource):
               [audio](https://platform.openai.com/docs/guides/audio).
 
           model: ID of the model to use. See the
-              [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+              [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
               table for details on which models work with the Chat API.
 
           stream: If set, partial message deltas will be sent, like in ChatGPT. Tokens will be
@@ -1425,7 +1449,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           function_call: Deprecated in favor of `tool_choice`.
 
@@ -1486,19 +1510,22 @@ class AsyncCompletions(AsyncAPIResource):
               choices. Keep `n` as `1` to minimize costs.
 
           parallel_tool_calls: Whether to enable
-              [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+              [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          prediction: Static predicted output content, such as the content of a text file that is
+              being regenerated.
+
           presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           response_format: An object specifying the format that the model must output. Compatible with
-              [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-              [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-              [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+              [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+              [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+              [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
               all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
               Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -1578,7 +1605,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -1608,6 +1635,7 @@ class AsyncCompletions(AsyncAPIResource):
         modalities: Optional[List[ChatCompletionModality]] | NotGiven = NOT_GIVEN,
         n: Optional[int] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        prediction: Optional[ChatCompletionPredictionContentParam] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: completion_create_params.ResponseFormat | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
@@ -1648,6 +1676,7 @@ class AsyncCompletions(AsyncAPIResource):
                     "modalities": modalities,
                     "n": n,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
                     "presence_penalty": presence_penalty,
                     "response_format": response_format,
                     "seed": seed,
src/openai/resources/fine_tuning/jobs/jobs.py
@@ -88,7 +88,7 @@ class Jobs(SyncAPIResource):
 
         Args:
           model: The name of the model to fine-tune. You can select one of the
-              [supported models](https://platform.openai.com/docs/guides/fine-tuning/which-models-can-be-fine-tuned).
+              [supported models](https://platform.openai.com/docs/guides/fine-tuning#which-models-can-be-fine-tuned).
 
           training_file: The ID of an uploaded file that contains training data.
 
@@ -379,7 +379,7 @@ class AsyncJobs(AsyncAPIResource):
 
         Args:
           model: The name of the model to fine-tune. You can select one of the
-              [supported models](https://platform.openai.com/docs/guides/fine-tuning/which-models-can-be-fine-tuned).
+              [supported models](https://platform.openai.com/docs/guides/fine-tuning#which-models-can-be-fine-tuned).
 
           training_file: The ID of an uploaded file that contains training data.
 
src/openai/resources/uploads/uploads.py
@@ -196,7 +196,7 @@ class Uploads(SyncAPIResource):
         For certain `purpose`s, the correct `mime_type` must be specified. Please refer
         to documentation for the supported MIME types for your use case:
 
-        - [Assistants](https://platform.openai.com/docs/assistants/tools/file-search/supported-files)
+        - [Assistants](https://platform.openai.com/docs/assistants/tools/file-search#supported-files)
 
         For guidance on the proper filename extensions for each purpose, please follow
         the documentation on
@@ -500,7 +500,7 @@ class AsyncUploads(AsyncAPIResource):
         For certain `purpose`s, the correct `mime_type` must be specified. Please refer
         to documentation for the supported MIME types for your use case:
 
-        - [Assistants](https://platform.openai.com/docs/assistants/tools/file-search/supported-files)
+        - [Assistants](https://platform.openai.com/docs/assistants/tools/file-search#supported-files)
 
         For guidance on the proper filename extensions for each purpose, please follow
         the documentation on
src/openai/resources/completions.py
@@ -84,8 +84,8 @@ class Completions(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -110,7 +110,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -150,7 +150,7 @@ class Completions(SyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -189,7 +189,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -237,8 +237,8 @@ class Completions(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -270,7 +270,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -310,7 +310,7 @@ class Completions(SyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -342,7 +342,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -390,8 +390,8 @@ class Completions(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -423,7 +423,7 @@ class Completions(SyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -463,7 +463,7 @@ class Completions(SyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -495,7 +495,7 @@ class Completions(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -626,8 +626,8 @@ class AsyncCompletions(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -652,7 +652,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -692,7 +692,7 @@ class AsyncCompletions(AsyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -731,7 +731,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -779,8 +779,8 @@ class AsyncCompletions(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -812,7 +812,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -852,7 +852,7 @@ class AsyncCompletions(AsyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -884,7 +884,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -932,8 +932,8 @@ class AsyncCompletions(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           prompt: The prompt(s) to generate completions for, encoded as a string, array of
               strings, array of tokens, or array of token arrays.
@@ -965,7 +965,7 @@ class AsyncCompletions(AsyncAPIResource):
               existing frequency in the text so far, decreasing the model's likelihood to
               repeat the same line verbatim.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           logit_bias: Modify the likelihood of specified tokens appearing in the completion.
 
@@ -1005,7 +1005,7 @@ class AsyncCompletions(AsyncAPIResource):
               whether they appear in the text so far, increasing the model's likelihood to
               talk about new topics.
 
-              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+              [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
 
           seed: If specified, our system will make a best effort to sample deterministically,
               such that repeated requests with the same `seed` and parameters should return
@@ -1037,7 +1037,7 @@ class AsyncCompletions(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
src/openai/resources/embeddings.py
@@ -73,8 +73,8 @@ class Embeddings(SyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           dimensions: The number of dimensions the resulting output embeddings should have. Only
               supported in `text-embedding-3` and later models.
@@ -84,7 +84,7 @@ class Embeddings(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -185,8 +185,8 @@ class AsyncEmbeddings(AsyncAPIResource):
           model: ID of the model to use. You can use the
               [List models](https://platform.openai.com/docs/api-reference/models/list) API to
               see all of your available models, or see our
-              [Model overview](https://platform.openai.com/docs/models/overview) for
-              descriptions of them.
+              [Model overview](https://platform.openai.com/docs/models) for descriptions of
+              them.
 
           dimensions: The number of dimensions the resulting output embeddings should have. Only
               supported in `text-embedding-3` and later models.
@@ -196,7 +196,7 @@ class AsyncEmbeddings(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
src/openai/resources/files.py
@@ -5,6 +5,7 @@ from __future__ import annotations
 import time
 import typing_extensions
 from typing import Mapping, cast
+from typing_extensions import Literal
 
 import httpx
 
@@ -27,11 +28,8 @@ from .._response import (
     to_custom_streamed_response_wrapper,
     async_to_custom_streamed_response_wrapper,
 )
-from ..pagination import SyncPage, AsyncPage
-from .._base_client import (
-    AsyncPaginator,
-    make_request_options,
-)
+from ..pagination import SyncCursorPage, AsyncCursorPage
+from .._base_client import AsyncPaginator, make_request_options
 from ..types.file_object import FileObject
 from ..types.file_deleted import FileDeleted
 from ..types.file_purpose import FilePurpose
@@ -172,6 +170,9 @@ class Files(SyncAPIResource):
     def list(
         self,
         *,
+        after: str | NotGiven = NOT_GIVEN,
+        limit: int | NotGiven = NOT_GIVEN,
+        order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
         purpose: str | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -179,11 +180,23 @@ class Files(SyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> SyncPage[FileObject]:
-        """
-        Returns a list of files that belong to the user's organization.
+    ) -> SyncCursorPage[FileObject]:
+        """Returns a list of files.
 
         Args:
+          after: A cursor for use in pagination.
+
+        `after` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              ending with obj_foo, your subsequent call can include after=obj_foo in order to
+              fetch the next page of the list.
+
+          limit: A limit on the number of objects to be returned. Limit can range between 1 and
+              10,000, and the default is 10,000.
+
+          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
+              order and `desc` for descending order.
+
           purpose: Only return files with the given purpose.
 
           extra_headers: Send extra headers
@@ -196,13 +209,21 @@ class Files(SyncAPIResource):
         """
         return self._get_api_list(
             "/files",
-            page=SyncPage[FileObject],
+            page=SyncCursorPage[FileObject],
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
                 extra_body=extra_body,
                 timeout=timeout,
-                query=maybe_transform({"purpose": purpose}, file_list_params.FileListParams),
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "limit": limit,
+                        "order": order,
+                        "purpose": purpose,
+                    },
+                    file_list_params.FileListParams,
+                ),
             ),
             model=FileObject,
         )
@@ -465,6 +486,9 @@ class AsyncFiles(AsyncAPIResource):
     def list(
         self,
         *,
+        after: str | NotGiven = NOT_GIVEN,
+        limit: int | NotGiven = NOT_GIVEN,
+        order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
         purpose: str | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -472,11 +496,23 @@ class AsyncFiles(AsyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> AsyncPaginator[FileObject, AsyncPage[FileObject]]:
-        """
-        Returns a list of files that belong to the user's organization.
+    ) -> AsyncPaginator[FileObject, AsyncCursorPage[FileObject]]:
+        """Returns a list of files.
 
         Args:
+          after: A cursor for use in pagination.
+
+        `after` is an object ID that defines your place
+              in the list. For instance, if you make a list request and receive 100 objects,
+              ending with obj_foo, your subsequent call can include after=obj_foo in order to
+              fetch the next page of the list.
+
+          limit: A limit on the number of objects to be returned. Limit can range between 1 and
+              10,000, and the default is 10,000.
+
+          order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
+              order and `desc` for descending order.
+
           purpose: Only return files with the given purpose.
 
           extra_headers: Send extra headers
@@ -489,13 +525,21 @@ class AsyncFiles(AsyncAPIResource):
         """
         return self._get_api_list(
             "/files",
-            page=AsyncPage[FileObject],
+            page=AsyncCursorPage[FileObject],
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
                 extra_body=extra_body,
                 timeout=timeout,
-                query=maybe_transform({"purpose": purpose}, file_list_params.FileListParams),
+                query=maybe_transform(
+                    {
+                        "after": after,
+                        "limit": limit,
+                        "order": order,
+                        "purpose": purpose,
+                    },
+                    file_list_params.FileListParams,
+                ),
             ),
             model=FileObject,
         )
src/openai/resources/images.py
@@ -84,7 +84,7 @@ class Images(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -165,7 +165,7 @@ class Images(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -251,7 +251,7 @@ class Images(SyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -341,7 +341,7 @@ class AsyncImages(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -422,7 +422,7 @@ class AsyncImages(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
@@ -508,7 +508,7 @@ class AsyncImages(AsyncAPIResource):
 
           user: 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).
+              [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
 
           extra_headers: Send extra headers
 
src/openai/resources/moderations.py
@@ -68,7 +68,7 @@ class Moderations(SyncAPIResource):
           model: The content moderation model you would like to use. Learn more in
               [the moderation guide](https://platform.openai.com/docs/guides/moderation), and
               learn about available models
-              [here](https://platform.openai.com/docs/models/moderation).
+              [here](https://platform.openai.com/docs/models#moderation).
 
           extra_headers: Send extra headers
 
@@ -138,7 +138,7 @@ class AsyncModerations(AsyncAPIResource):
           model: The content moderation model you would like to use. Learn more in
               [the moderation guide](https://platform.openai.com/docs/guides/moderation), and
               learn about available models
-              [here](https://platform.openai.com/docs/models/moderation).
+              [here](https://platform.openai.com/docs/models#moderation).
 
           extra_headers: Send extra headers
 
src/openai/types/audio/speech_create_params.py
@@ -16,7 +16,7 @@ class SpeechCreateParams(TypedDict, total=False):
 
     model: Required[Union[str, SpeechModel]]
     """
-    One of the available [TTS models](https://platform.openai.com/docs/models/tts):
+    One of the available [TTS models](https://platform.openai.com/docs/models#tts):
     `tts-1` or `tts-1-hd`
     """
 
@@ -25,7 +25,7 @@ class SpeechCreateParams(TypedDict, total=False):
 
     Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`.
     Previews of the voices are available in the
-    [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech/voice-options).
+    [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
     """
 
     response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"]
src/openai/types/audio/transcription_create_params.py
@@ -38,7 +38,7 @@ class TranscriptionCreateParams(TypedDict, total=False):
     """An optional text to guide the model's style or continue a previous audio
     segment.
 
-    The [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+    The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
     should match the audio language.
     """
 
src/openai/types/audio/translation_create_params.py
@@ -30,7 +30,7 @@ class TranslationCreateParams(TypedDict, total=False):
     """An optional text to guide the model's style or continue a previous audio
     segment.
 
-    The [prompt](https://platform.openai.com/docs/guides/speech-to-text/prompting)
+    The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
     should be in English.
     """
 
src/openai/types/beta/threads/runs/step_list_params.py
@@ -26,7 +26,7 @@ class StepListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
@@ -39,7 +39,7 @@ class StepListParams(TypedDict, total=False):
     search result content.
 
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
src/openai/types/beta/threads/runs/step_retrieve_params.py
@@ -23,6 +23,6 @@ class StepRetrieveParams(TypedDict, total=False):
     search result content.
 
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
src/openai/types/beta/threads/message_list_params.py
@@ -21,7 +21,7 @@ class MessageListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/beta/threads/run.py
@@ -154,7 +154,7 @@ class Run(BaseModel):
     parallel_tool_calls: bool
     """
     Whether to enable
-    [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+    [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
     during tool use.
     """
 
@@ -167,8 +167,8 @@ class Run(BaseModel):
     response_format: Optional[AssistantResponseFormatOption] = None
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/threads/run_create_params.py
@@ -41,7 +41,7 @@ class RunCreateParamsBase(TypedDict, total=False):
     search result content.
 
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
@@ -99,15 +99,15 @@ class RunCreateParamsBase(TypedDict, total=False):
     parallel_tool_calls: bool
     """
     Whether to enable
-    [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+    [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
     during tool use.
     """
 
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/threads/run_list_params.py
@@ -21,7 +21,7 @@ class RunListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/beta/vector_stores/file_batch_list_files_params.py
@@ -23,7 +23,7 @@ class FileBatchListFilesParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/beta/vector_stores/file_list_params.py
@@ -21,7 +21,7 @@ class FileListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/beta/assistant.py
@@ -65,8 +65,8 @@ class Assistant(BaseModel):
     You can use the
     [List models](https://platform.openai.com/docs/api-reference/models/list) API to
     see all of your available models, or see our
-    [Model overview](https://platform.openai.com/docs/models/overview) for
-    descriptions of them.
+    [Model overview](https://platform.openai.com/docs/models) for descriptions of
+    them.
     """
 
     name: Optional[str] = None
@@ -85,8 +85,8 @@ class Assistant(BaseModel):
     response_format: Optional[AssistantResponseFormatOption] = None
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/assistant_create_params.py
@@ -26,8 +26,8 @@ class AssistantCreateParams(TypedDict, total=False):
     You can use the
     [List models](https://platform.openai.com/docs/api-reference/models/list) API to
     see all of your available models, or see our
-    [Model overview](https://platform.openai.com/docs/models/overview) for
-    descriptions of them.
+    [Model overview](https://platform.openai.com/docs/models) for descriptions of
+    them.
     """
 
     description: Optional[str]
@@ -53,8 +53,8 @@ class AssistantCreateParams(TypedDict, total=False):
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/assistant_list_params.py
@@ -21,7 +21,7 @@ class AssistantListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/beta/assistant_update_params.py
@@ -35,8 +35,8 @@ class AssistantUpdateParams(TypedDict, total=False):
     You can use the
     [List models](https://platform.openai.com/docs/api-reference/models/list) API to
     see all of your available models, or see our
-    [Model overview](https://platform.openai.com/docs/models/overview) for
-    descriptions of them.
+    [Model overview](https://platform.openai.com/docs/models) for descriptions of
+    them.
     """
 
     name: Optional[str]
@@ -45,8 +45,8 @@ class AssistantUpdateParams(TypedDict, total=False):
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/file_search_tool.py
@@ -31,7 +31,7 @@ class FileSearch(BaseModel):
 
     Note that the file search tool may output fewer than `max_num_results` results.
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
@@ -42,7 +42,7 @@ class FileSearch(BaseModel):
     score_threshold of 0.
 
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
src/openai/types/beta/file_search_tool_param.py
@@ -30,7 +30,7 @@ class FileSearch(TypedDict, total=False):
 
     Note that the file search tool may output fewer than `max_num_results` results.
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
@@ -41,7 +41,7 @@ class FileSearch(TypedDict, total=False):
     score_threshold of 0.
 
     See the
-    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search/customizing-file-search-settings)
+    [file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
     for more information.
     """
 
src/openai/types/beta/thread_create_and_run_params.py
@@ -86,15 +86,15 @@ class ThreadCreateAndRunParamsBase(TypedDict, total=False):
     parallel_tool_calls: bool
     """
     Whether to enable
-    [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+    [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
     during tool use.
     """
 
     response_format: Optional[AssistantResponseFormatOptionParam]
     """Specifies the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4),
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
     and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
src/openai/types/beta/vector_store_list_params.py
@@ -21,7 +21,7 @@ class VectorStoreListParams(TypedDict, total=False):
     """A cursor for use in pagination.
 
     `before` is an object ID that defines your place in the list. For instance, if
-    you make a list request and receive 100 objects, ending with obj_foo, your
+    you make a list request and receive 100 objects, starting with obj_foo, your
     subsequent call can include before=obj_foo in order to fetch the previous page
     of the list.
     """
src/openai/types/chat/__init__.py
@@ -46,6 +46,9 @@ from .chat_completion_named_tool_choice_param import (
 from .chat_completion_content_part_image_param import (
     ChatCompletionContentPartImageParam as ChatCompletionContentPartImageParam,
 )
+from .chat_completion_prediction_content_param import (
+    ChatCompletionPredictionContentParam as ChatCompletionPredictionContentParam,
+)
 from .chat_completion_tool_choice_option_param import (
     ChatCompletionToolChoiceOptionParam as ChatCompletionToolChoiceOptionParam,
 )
src/openai/types/chat/chat_completion_content_part_image_param.py
@@ -15,7 +15,7 @@ class ImageURL(TypedDict, total=False):
     """Specifies the detail level of the image.
 
     Learn more in the
-    [Vision guide](https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding).
+    [Vision guide](https://platform.openai.com/docs/guides/vision#low-or-high-fidelity-image-understanding).
     """
 
 
src/openai/types/chat/chat_completion_prediction_content_param.py
@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union, Iterable
+from typing_extensions import Literal, Required, TypedDict
+
+from .chat_completion_content_part_text_param import ChatCompletionContentPartTextParam
+
+__all__ = ["ChatCompletionPredictionContentParam"]
+
+
+class ChatCompletionPredictionContentParam(TypedDict, total=False):
+    content: Required[Union[str, Iterable[ChatCompletionContentPartTextParam]]]
+    """
+    The content that should be matched when generating a model response. If
+    generated tokens would match this content, the entire model response can be
+    returned much more quickly.
+    """
+
+    type: Required[Literal["content"]]
+    """The type of the predicted content you want to provide.
+
+    This type is currently always `content`.
+    """
src/openai/types/chat/completion_create_params.py
@@ -13,6 +13,7 @@ from .chat_completion_message_param import ChatCompletionMessageParam
 from ..shared_params.function_parameters import FunctionParameters
 from ..shared_params.response_format_text import ResponseFormatText
 from .chat_completion_stream_options_param import ChatCompletionStreamOptionsParam
+from .chat_completion_prediction_content_param import ChatCompletionPredictionContentParam
 from .chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
 from ..shared_params.response_format_json_object import ResponseFormatJSONObject
 from ..shared_params.response_format_json_schema import ResponseFormatJSONSchema
@@ -43,7 +44,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     """ID of the model to use.
 
     See the
-    [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+    [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility)
     table for details on which models work with the Chat API.
     """
 
@@ -60,7 +61,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     Positive values penalize new tokens based on their existing frequency in the
     text so far, decreasing the model's likelihood to repeat the same line verbatim.
 
-    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
     """
 
     function_call: FunctionCall
@@ -148,25 +149,31 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     parallel_tool_calls: bool
     """
     Whether to enable
-    [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling)
+    [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
     during tool use.
     """
 
+    prediction: Optional[ChatCompletionPredictionContentParam]
+    """
+    Static predicted output content, such as the content of a text file that is
+    being regenerated.
+    """
+
     presence_penalty: Optional[float]
     """Number between -2.0 and 2.0.
 
     Positive values penalize new tokens based on whether they appear in the text so
     far, increasing the model's likelihood to talk about new topics.
 
-    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
     """
 
     response_format: ResponseFormat
     """An object specifying the format that the model must output.
 
-    Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o),
-    [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini),
-    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+    Compatible with [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
+    [GPT-4o mini](https://platform.openai.com/docs/models#gpt-4o-mini),
+    [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4) and
     all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
 
     Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured
@@ -276,7 +283,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
 
 
src/openai/types/fine_tuning/job_create_params.py
@@ -13,7 +13,7 @@ class JobCreateParams(TypedDict, total=False):
     """The name of the model to fine-tune.
 
     You can select one of the
-    [supported models](https://platform.openai.com/docs/guides/fine-tuning/which-models-can-be-fine-tuned).
+    [supported models](https://platform.openai.com/docs/guides/fine-tuning#which-models-can-be-fine-tuned).
     """
 
     training_file: Required[str]
src/openai/types/completion_create_params.py
@@ -17,8 +17,8 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     You can use the
     [List models](https://platform.openai.com/docs/api-reference/models/list) API to
     see all of your available models, or see our
-    [Model overview](https://platform.openai.com/docs/models/overview) for
-    descriptions of them.
+    [Model overview](https://platform.openai.com/docs/models) for descriptions of
+    them.
     """
 
     prompt: Required[Union[str, List[str], Iterable[int], Iterable[Iterable[int]], None]]
@@ -53,7 +53,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     Positive values penalize new tokens based on their existing frequency in the
     text so far, decreasing the model's likelihood to repeat the same line verbatim.
 
-    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
     """
 
     logit_bias: Optional[Dict[str, int]]
@@ -106,7 +106,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     Positive values penalize new tokens based on whether they appear in the text so
     far, increasing the model's likelihood to talk about new topics.
 
-    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation)
     """
 
     seed: Optional[int]
@@ -156,7 +156,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
 
 
src/openai/types/completion_usage.py
@@ -8,12 +8,26 @@ __all__ = ["CompletionUsage", "CompletionTokensDetails", "PromptTokensDetails"]
 
 
 class CompletionTokensDetails(BaseModel):
+    accepted_prediction_tokens: Optional[int] = None
+    """
+    When using Predicted Outputs, the number of tokens in the prediction that
+    appeared in the completion.
+    """
+
     audio_tokens: Optional[int] = None
     """Audio input tokens generated by the model."""
 
     reasoning_tokens: Optional[int] = None
     """Tokens generated by the model for reasoning."""
 
+    rejected_prediction_tokens: Optional[int] = None
+    """
+    When using Predicted Outputs, the number of tokens in the prediction that did
+    not appear in the completion. However, like reasoning tokens, these tokens are
+    still counted in the total completion tokens for purposes of billing, output,
+    and context window limits.
+    """
+
 
 class PromptTokensDetails(BaseModel):
     audio_tokens: Optional[int] = None
src/openai/types/embedding_create_params.py
@@ -28,8 +28,8 @@ class EmbeddingCreateParams(TypedDict, total=False):
     You can use the
     [List models](https://platform.openai.com/docs/api-reference/models/list) API to
     see all of your available models, or see our
-    [Model overview](https://platform.openai.com/docs/models/overview) for
-    descriptions of them.
+    [Model overview](https://platform.openai.com/docs/models) for descriptions of
+    them.
     """
 
     dimensions: int
@@ -48,5 +48,5 @@ class EmbeddingCreateParams(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
src/openai/types/file_list_params.py
@@ -2,11 +2,32 @@
 
 from __future__ import annotations
 
-from typing_extensions import TypedDict
+from typing_extensions import Literal, TypedDict
 
 __all__ = ["FileListParams"]
 
 
 class FileListParams(TypedDict, total=False):
+    after: str
+    """A cursor for use in pagination.
+
+    `after` is an object ID that defines your place in the list. For instance, if
+    you make a list request and receive 100 objects, ending with obj_foo, your
+    subsequent call can include after=obj_foo in order to fetch the next page of the
+    list.
+    """
+
+    limit: int
+    """A limit on the number of objects to be returned.
+
+    Limit can range between 1 and 10,000, and the default is 10,000.
+    """
+
+    order: Literal["asc", "desc"]
+    """Sort order by the `created_at` timestamp of the objects.
+
+    `asc` for ascending order and `desc` for descending order.
+    """
+
     purpose: str
     """Only return files with the given purpose."""
src/openai/types/image_create_variation_params.py
@@ -47,5 +47,5 @@ class ImageCreateVariationParams(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
src/openai/types/image_edit_params.py
@@ -58,5 +58,5 @@ class ImageEditParams(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
src/openai/types/image_generate_params.py
@@ -61,5 +61,5 @@ class ImageGenerateParams(TypedDict, total=False):
     """
     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).
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
     """
src/openai/types/moderation_create_params.py
@@ -25,5 +25,5 @@ class ModerationCreateParams(TypedDict, total=False):
     Learn more in
     [the moderation guide](https://platform.openai.com/docs/guides/moderation), and
     learn about available models
-    [here](https://platform.openai.com/docs/models/moderation).
+    [here](https://platform.openai.com/docs/models#moderation).
     """
tests/api_resources/chat/test_completions.py
@@ -65,6 +65,10 @@ class TestCompletions:
             modalities=["text", "audio"],
             n=1,
             parallel_tool_calls=True,
+            prediction={
+                "content": "string",
+                "type": "content",
+            },
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=-9007199254740991,
@@ -193,6 +197,10 @@ class TestCompletions:
             modalities=["text", "audio"],
             n=1,
             parallel_tool_calls=True,
+            prediction={
+                "content": "string",
+                "type": "content",
+            },
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=-9007199254740991,
@@ -340,6 +348,10 @@ class TestAsyncCompletions:
             modalities=["text", "audio"],
             n=1,
             parallel_tool_calls=True,
+            prediction={
+                "content": "string",
+                "type": "content",
+            },
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=-9007199254740991,
@@ -468,6 +480,10 @@ class TestAsyncCompletions:
             modalities=["text", "audio"],
             n=1,
             parallel_tool_calls=True,
+            prediction={
+                "content": "string",
+                "type": "content",
+            },
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=-9007199254740991,
tests/api_resources/test_files.py
@@ -13,7 +13,7 @@ import openai._legacy_response as _legacy_response
 from openai import OpenAI, AsyncOpenAI
 from tests.utils import assert_matches_type
 from openai.types import FileObject, FileDeleted
-from openai.pagination import SyncPage, AsyncPage
+from openai.pagination import SyncCursorPage, AsyncCursorPage
 
 # pyright: reportDeprecated=false
 
@@ -98,14 +98,17 @@ class TestFiles:
     @parametrize
     def test_method_list(self, client: OpenAI) -> None:
         file = client.files.list()
-        assert_matches_type(SyncPage[FileObject], file, path=["response"])
+        assert_matches_type(SyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     def test_method_list_with_all_params(self, client: OpenAI) -> None:
         file = client.files.list(
-            purpose="string",
+            after="after",
+            limit=0,
+            order="asc",
+            purpose="purpose",
         )
-        assert_matches_type(SyncPage[FileObject], file, path=["response"])
+        assert_matches_type(SyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     def test_raw_response_list(self, client: OpenAI) -> None:
@@ -114,7 +117,7 @@ class TestFiles:
         assert response.is_closed is True
         assert response.http_request.headers.get("X-Stainless-Lang") == "python"
         file = response.parse()
-        assert_matches_type(SyncPage[FileObject], file, path=["response"])
+        assert_matches_type(SyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     def test_streaming_response_list(self, client: OpenAI) -> None:
@@ -123,7 +126,7 @@ class TestFiles:
             assert response.http_request.headers.get("X-Stainless-Lang") == "python"
 
             file = response.parse()
-            assert_matches_type(SyncPage[FileObject], file, path=["response"])
+            assert_matches_type(SyncCursorPage[FileObject], file, path=["response"])
 
         assert cast(Any, response.is_closed) is True
 
@@ -334,14 +337,17 @@ class TestAsyncFiles:
     @parametrize
     async def test_method_list(self, async_client: AsyncOpenAI) -> None:
         file = await async_client.files.list()
-        assert_matches_type(AsyncPage[FileObject], file, path=["response"])
+        assert_matches_type(AsyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     async def test_method_list_with_all_params(self, async_client: AsyncOpenAI) -> None:
         file = await async_client.files.list(
-            purpose="string",
+            after="after",
+            limit=0,
+            order="asc",
+            purpose="purpose",
         )
-        assert_matches_type(AsyncPage[FileObject], file, path=["response"])
+        assert_matches_type(AsyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     async def test_raw_response_list(self, async_client: AsyncOpenAI) -> None:
@@ -350,7 +356,7 @@ class TestAsyncFiles:
         assert response.is_closed is True
         assert response.http_request.headers.get("X-Stainless-Lang") == "python"
         file = response.parse()
-        assert_matches_type(AsyncPage[FileObject], file, path=["response"])
+        assert_matches_type(AsyncCursorPage[FileObject], file, path=["response"])
 
     @parametrize
     async def test_streaming_response_list(self, async_client: AsyncOpenAI) -> None:
@@ -359,7 +365,7 @@ class TestAsyncFiles:
             assert response.http_request.headers.get("X-Stainless-Lang") == "python"
 
             file = await response.parse()
-            assert_matches_type(AsyncPage[FileObject], file, path=["response"])
+            assert_matches_type(AsyncCursorPage[FileObject], file, path=["response"])
 
         assert cast(Any, response.is_closed) is True
 
.stats.yml
@@ -1,2 +1,2 @@
 configured_endpoints: 68
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-7b0a5d715d94f75ac7795bd4d2175a0e3243af9b935a86c273f371e45583140f.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-2f8ca92b9b1879fd535b685e4767338413fcd533d42f3baac13a9c41da3fce35.yml
api.md
@@ -54,6 +54,7 @@ from openai.types.chat import (
     ChatCompletionMessageToolCall,
     ChatCompletionModality,
     ChatCompletionNamedToolChoice,
+    ChatCompletionPredictionContent,
     ChatCompletionRole,
     ChatCompletionStreamOptions,
     ChatCompletionSystemMessageParam,
@@ -93,7 +94,7 @@ Methods:
 
 - <code title="post /files">client.files.<a href="./src/openai/resources/files.py">create</a>(\*\*<a href="src/openai/types/file_create_params.py">params</a>) -> <a href="./src/openai/types/file_object.py">FileObject</a></code>
 - <code title="get /files/{file_id}">client.files.<a href="./src/openai/resources/files.py">retrieve</a>(file_id) -> <a href="./src/openai/types/file_object.py">FileObject</a></code>
-- <code title="get /files">client.files.<a href="./src/openai/resources/files.py">list</a>(\*\*<a href="src/openai/types/file_list_params.py">params</a>) -> <a href="./src/openai/types/file_object.py">SyncPage[FileObject]</a></code>
+- <code title="get /files">client.files.<a href="./src/openai/resources/files.py">list</a>(\*\*<a href="src/openai/types/file_list_params.py">params</a>) -> <a href="./src/openai/types/file_object.py">SyncCursorPage[FileObject]</a></code>
 - <code title="delete /files/{file_id}">client.files.<a href="./src/openai/resources/files.py">delete</a>(file_id) -> <a href="./src/openai/types/file_deleted.py">FileDeleted</a></code>
 - <code title="get /files/{file_id}/content">client.files.<a href="./src/openai/resources/files.py">content</a>(file_id) -> HttpxBinaryResponseContent</code>
 - <code title="get /files/{file_id}/content">client.files.<a href="./src/openai/resources/files.py">retrieve_content</a>(file_id) -> str</code>