diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 11ee7212d7..318899b64d 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "2.50.0"
+  ".": "2.51.0"
 }
\ No newline at end of file
diff --git a/.stats.yml b/.stats.yml
index f0a6394000..5d31020c16 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 278
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-9152683f2fa71f5555cbbb53123ec013b7c83ee6fed4333e76c22a6f48a05f1c.yml
-openapi_spec_hash: c58a8c1bb1f5bb7245323db9437bd67f
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai/openai-44d4add500460ed21ac9ae1d6dd4047a32a79d3b4c3a9d9754f6ecf8cbdb9eec.yml
+openapi_spec_hash: 8a34ba094583f56e975067493574fa69
 config_hash: ca12d10f1dbe101a81cd0376f868c674
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 906170359d..48e1f8cc72 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,18 @@
 # Changelog
 
+## 2.51.0 (2026-07-30)
+
+Full Changelog: [v2.50.0...v2.51.0](https://github.com/openai/openai-python/compare/v2.50.0...v2.51.0)
+
+### Features
+
+* **api:** fast tier ([8808ed2](https://github.com/openai/openai-python/commit/8808ed27952dae13fb8761f045376af5b3e5bec2))
+
+
+### Bug Fixes
+
+* **api:** add fast tier to helper methods ([6064126](https://github.com/openai/openai-python/commit/60641266ff4b296044a81fe1717c17a70ceadbf1))
+
 ## 2.50.0 (2026-07-28)
 
 Full Changelog: [v2.49.0...v2.50.0](https://github.com/openai/openai-python/compare/v2.49.0...v2.50.0)
diff --git a/pyproject.toml b/pyproject.toml
index 4cc151efcd..b5afe38113 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "openai"
-version = "2.50.0"
+version = "2.51.0"
 description = "The official Python library for the openai API"
 dynamic = ["readme"]
 license = "Apache-2.0"
diff --git a/src/openai/_version.py b/src/openai/_version.py
index 8836067b9e..8438cbcc19 100644
--- a/src/openai/_version.py
+++ b/src/openai/_version.py
@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "2.50.0"  # x-release-please-version
+__version__ = "2.51.0"  # x-release-please-version
diff --git a/src/openai/resources/beta/responses/responses.py b/src/openai/resources/beta/responses/responses.py
index ed244635d1..d926d4bd97 100644
--- a/src/openai/resources/beta/responses/responses.py
+++ b/src/openai/resources/beta/responses/responses.py
@@ -227,7 +227,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -394,9 +394,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -609,7 +613,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -782,9 +786,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -990,7 +998,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -1163,9 +1171,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -1369,7 +1381,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -2109,7 +2121,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -2276,9 +2288,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2491,7 +2507,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -2664,9 +2680,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2872,7 +2892,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -3045,9 +3065,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -3251,7 +3275,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[response_create_params.Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -4995,7 +5019,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[beta_responses_client_event_param.ResponseCreateReasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[bool] | Omit = omit,
         stream_options: Optional[beta_responses_client_event_param.ResponseCreateStreamOptions] | Omit = omit,
@@ -5198,7 +5222,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[beta_responses_client_event_param.ResponseCreateReasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[bool] | Omit = omit,
         stream_options: Optional[beta_responses_client_event_param.ResponseCreateStreamOptions] | Omit = omit,
diff --git a/src/openai/resources/chat/completions/completions.py b/src/openai/resources/chat/completions/completions.py
index 8d75855e3a..2375410600 100644
--- a/src/openai/resources/chat/completions/completions.py
+++ b/src/openai/resources/chat/completions/completions.py
@@ -115,7 +115,7 @@ def parse(
         reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -276,7 +276,7 @@ def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
@@ -489,9 +489,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -605,7 +609,7 @@ def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -826,9 +830,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -933,7 +941,7 @@ def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -1154,9 +1162,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -1260,7 +1272,7 @@ def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
@@ -1559,7 +1571,7 @@ def stream(
         reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -1714,7 +1726,7 @@ async def parse(
         reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -1875,7 +1887,7 @@ async def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
@@ -2088,9 +2100,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2204,7 +2220,7 @@ async def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -2425,9 +2441,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2532,7 +2552,7 @@ async def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
@@ -2753,9 +2773,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2859,7 +2883,7 @@ async def create(
         response_format: completion_create_params.ResponseFormat | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
@@ -3158,7 +3182,7 @@ def stream(
         reasoning_effort: Optional[ReasoningEffort] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
         seed: Optional[int] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         stop: Union[Optional[str], SequenceNotStr[str], None] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[ChatCompletionStreamOptionsParam] | Omit = omit,
diff --git a/src/openai/resources/responses/responses.py b/src/openai/resources/responses/responses.py
index 54ce5ee26c..d0e0bed257 100644
--- a/src/openai/resources/responses/responses.py
+++ b/src/openai/resources/responses/responses.py
@@ -152,7 +152,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -316,9 +316,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -430,7 +434,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -600,9 +604,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -707,7 +715,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -877,9 +885,13 @@ def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -982,7 +994,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -1093,7 +1105,7 @@ def stream(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -1136,7 +1148,7 @@ def stream(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -1298,7 +1310,7 @@ def parse(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -1975,7 +1987,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -2139,9 +2151,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2253,7 +2269,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -2423,9 +2439,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2530,7 +2550,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -2700,9 +2720,13 @@ async def create(
                 will use 'default'.
               - If set to 'default', then the request will be processed with the standard
                 pricing and performance for the selected model.
-              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-                '[priority](https://openai.com/api-priority-processing/)', then the request
-                will be processed with the corresponding service tier.
+              - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+                then the request will be processed with the Flex Processing service tier.
+              - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+                include the `service_tier=fast` or `service_tier=priority` parameter for
+                Responses or Chat Completions. The response will show `service_tier=priority`
+                regardless of if you specify `service_tier=fast` or `priority` in your
+                request.
               - When not set, the default behavior is 'auto'.
 
               When the `service_tier` parameter is set, the response body will include the
@@ -2805,7 +2829,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -2916,7 +2940,7 @@ def stream(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -2959,7 +2983,7 @@ def stream(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
         temperature: Optional[float] | Omit = omit,
@@ -3120,7 +3144,7 @@ async def parse(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
         stream_options: Optional[response_create_params.StreamOptions] | Omit = omit,
@@ -4836,7 +4860,7 @@ def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[bool] | Omit = omit,
         stream_options: Optional[responses_client_event_param.StreamOptions] | Omit = omit,
@@ -4920,7 +4944,7 @@ async def create(
         prompt_cache_retention: Optional[Literal["in_memory", "24h"]] | Omit = omit,
         reasoning: Optional[Reasoning] | Omit = omit,
         safety_identifier: Optional[str] | Omit = omit,
-        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] | Omit = omit,
+        service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] | Omit = omit,
         store: Optional[bool] | Omit = omit,
         stream: Optional[bool] | Omit = omit,
         stream_options: Optional[responses_client_event_param.StreamOptions] | Omit = omit,
diff --git a/src/openai/types/beta/beta_response.py b/src/openai/types/beta/beta_response.py
index f9bea6200b..6633b293ba 100644
--- a/src/openai/types/beta/beta_response.py
+++ b/src/openai/types/beta/beta_response.py
@@ -551,7 +551,7 @@ class BetaResponse(BaseModel):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -559,9 +559,13 @@ class BetaResponse(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/beta/beta_responses_client_event.py b/src/openai/types/beta/beta_responses_client_event.py
index a83f7038b2..af95baf3b7 100644
--- a/src/openai/types/beta/beta_responses_client_event.py
+++ b/src/openai/types/beta/beta_responses_client_event.py
@@ -499,7 +499,7 @@ class ResponseCreate(BaseModel):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -507,9 +507,13 @@ class ResponseCreate(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/beta/beta_responses_client_event_param.py b/src/openai/types/beta/beta_responses_client_event_param.py
index e5d84f2b4e..64ef2d5837 100644
--- a/src/openai/types/beta/beta_responses_client_event_param.py
+++ b/src/openai/types/beta/beta_responses_client_event_param.py
@@ -498,7 +498,7 @@ class ResponseCreate(TypedDict, total=False):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]]
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -506,9 +506,13 @@ class ResponseCreate(TypedDict, total=False):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/beta/response_create_params.py b/src/openai/types/beta/response_create_params.py
index c86103cded..a92fbfa276 100644
--- a/src/openai/types/beta/response_create_params.py
+++ b/src/openai/types/beta/response_create_params.py
@@ -314,7 +314,7 @@ class ResponseCreateParamsBase(TypedDict, total=False):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]]
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -322,9 +322,13 @@ class ResponseCreateParamsBase(TypedDict, total=False):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/chat/chat_completion.py b/src/openai/types/chat/chat_completion.py
index 2c4a78cd35..633d89e26c 100644
--- a/src/openai/types/chat/chat_completion.py
+++ b/src/openai/types/chat/chat_completion.py
@@ -217,7 +217,7 @@ class ChatCompletion(BaseModel):
     completions were requested.
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -225,9 +225,13 @@ class ChatCompletion(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/chat/chat_completion_chunk.py b/src/openai/types/chat/chat_completion_chunk.py
index d983336fab..41fa4bc5c2 100644
--- a/src/openai/types/chat/chat_completion_chunk.py
+++ b/src/openai/types/chat/chat_completion_chunk.py
@@ -291,7 +291,7 @@ class ChatCompletionChunk(BaseModel):
     Present on the moderation chunk when moderated completions are requested.
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -299,9 +299,13 @@ class ChatCompletionChunk(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/chat/completion_create_params.py b/src/openai/types/chat/completion_create_params.py
index ce027e067a..7e06d84f04 100644
--- a/src/openai/types/chat/completion_create_params.py
+++ b/src/openai/types/chat/completion_create_params.py
@@ -270,7 +270,7 @@ class CompletionCreateParamsBase(TypedDict, total=False):
     in the backend.
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]]
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -278,9 +278,13 @@ class CompletionCreateParamsBase(TypedDict, total=False):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/responses/response.py b/src/openai/types/responses/response.py
index e94ad18b34..6503d679b0 100644
--- a/src/openai/types/responses/response.py
+++ b/src/openai/types/responses/response.py
@@ -401,7 +401,7 @@ class Response(BaseModel):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -409,9 +409,13 @@ class Response(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/responses/response_create_params.py b/src/openai/types/responses/response_create_params.py
index 76d3b5fde6..b7282e5e6e 100644
--- a/src/openai/types/responses/response_create_params.py
+++ b/src/openai/types/responses/response_create_params.py
@@ -212,7 +212,7 @@ class ResponseCreateParamsBase(TypedDict, total=False):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]]
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -220,9 +220,13 @@ class ResponseCreateParamsBase(TypedDict, total=False):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/responses/responses_client_event.py b/src/openai/types/responses/responses_client_event.py
index 44606d8201..673c2cc9cc 100644
--- a/src/openai/types/responses/responses_client_event.py
+++ b/src/openai/types/responses/responses_client_event.py
@@ -315,7 +315,7 @@ class ResponsesClientEvent(BaseModel):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]] = None
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]] = None
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -323,9 +323,13 @@ class ResponsesClientEvent(BaseModel):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the
diff --git a/src/openai/types/responses/responses_client_event_param.py b/src/openai/types/responses/responses_client_event_param.py
index 4d7981d2df..32829669fc 100644
--- a/src/openai/types/responses/responses_client_event_param.py
+++ b/src/openai/types/responses/responses_client_event_param.py
@@ -316,7 +316,7 @@ class ResponsesClientEventParam(TypedDict, total=False):
     [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
     """
 
-    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority"]]
+    service_tier: Optional[Literal["auto", "default", "flex", "scale", "priority", "fast"]]
     """Specifies the processing type used for serving the request.
 
     - If set to 'auto', then the request will be processed with the service tier
@@ -324,9 +324,13 @@ class ResponsesClientEventParam(TypedDict, total=False):
       will use 'default'.
     - If set to 'default', then the request will be processed with the standard
       pricing and performance for the selected model.
-    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)' or
-      '[priority](https://openai.com/api-priority-processing/)', then the request
-      will be processed with the corresponding service tier.
+    - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+      then the request will be processed with the Flex Processing service tier.
+    - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+      include the `service_tier=fast` or `service_tier=priority` parameter for
+      Responses or Chat Completions. The response will show `service_tier=priority`
+      regardless of if you specify `service_tier=fast` or `priority` in your
+      request.
     - When not set, the default behavior is 'auto'.
 
     When the `service_tier` parameter is set, the response body will include the