empty commit to trigger [run-tests] workflow

* `open_router.benchmarks.get_benchmarks()`: **Added**
* `open_router.datasets.get_benchmarks_artificial_analysis()`: **Deleted** **Breaking** ⚠️
* `open_router.datasets.get_benchmarks_design_arena()`: **Deleted** **Breaking** ⚠️
* `open_router.chat.send()`:  `response` **Changed**
* `open_router.embeddings.generate()`:  `response.usage` **Changed**
* `open_router.embeddings.list_models()`:  `response.data.[].reasoning` **Added**
* `open_router.models.get()`:  `response.data.reasoning` **Added**
* `open_router.models.list()`:  `response.data.[].reasoning` **Added**
* `open_router.models.list_for_user()`:  `response.data.[].reasoning` **Added**

.speakeasy/gen.lock

@@ -1,7 +1,7 @@
 lockVersion: 2.0.0
 id: c48cf606-fb42-4a45-9c23-8f0555307828
 management:
-  docChecksum: 8a12eb05f6d29e6d4369ce71067b4c27
+  docChecksum: b391df2d82163351d8df7c152db16d55
   docVersion: 1.0.0
   speakeasyVersion: 1.680.0
   generationVersion: 2.788.4
@@ -11,9 +11,9 @@ management:
   installationURL: https://github.com/OpenRouterTeam/python-sdk.git
   published: true
 persistentEdits:
-  generation_id: b1a3cf99-d693-434e-8d7e-e5a1d85ee33d
-  pristine_commit_hash: cd611d4017874cd968979a48e9159baafc137c1b
-  pristine_tree_hash: 7b768060a0f6d7e54a10dda44219006db5253019
+  generation_id: 5b413f59-637c-4b8e-af52-4ce67ebe1508
+  pristine_commit_hash: 39a84a2b48a1853daeb784df3ce2c6bb1cbb4b3a
+  pristine_tree_hash: 2127b8a2fdbdd0e70f0a7ed87d1d4b25ca2e82ed
 features:
   python:
     acceptHeaders: 3.0.0
@@ -874,8 +874,8 @@ trackedFiles:
     pristine_git_object: 13ae40be5e3c883f88789c3b5b74a3b2da4c85c2
   docs/components/chatresult.md:
     id: 212b0f66efd0
-    last_write_checksum: sha1:0a94cfb0c88a0dbf0f0abc5d83ac6fc6c48051b4
-    pristine_git_object: cc04eadd2f48efd93533a3ddae52ad39e91f5dee
+    last_write_checksum: sha1:f40df693ad2d2d8e156aacb218af394f675bfb89
+    pristine_git_object: 41f82f9576591d048a504f29ca19b148ccca02bc
   docs/components/chatresultobject.md:
     id: 668504931d18
     last_write_checksum: sha1:6d550246aa007a5be94a9788ae4cfdfb75006980
@@ -898,8 +898,8 @@ trackedFiles:
     pristine_git_object: 690d74b67239bf7f423039652aea3741c831137e
   docs/components/chatstreamchunk.md:
     id: 404d264ea22c
-    last_write_checksum: sha1:1353c09378850a9810c39cf3198f0fd5e049f610
-    pristine_git_object: 3c64aec72fb2eb9f0cf6eae975dd9c8bb183c6e6
+    last_write_checksum: sha1:096b20b3777fd22cbe9c3ffb26c0d6bf51feedbe
+    pristine_git_object: 5cce75d63c13268740aa9fdb46f5273f77cd1c25
   docs/components/chatstreamchunkobject.md:
     id: 5393918d9606
     last_write_checksum: sha1:0765d94b3d01c811155dce29c20c2ae4bd4abd0e
@@ -998,8 +998,8 @@ trackedFiles:
     pristine_git_object: 7eb1791a9153498d5ffffc6b67d3668df59000c2
   docs/components/chatusage.md:
     id: 72cd0c41ec64
-    last_write_checksum: sha1:9a6a709e2ea8f36c1f55afc3ae364917ab787e5e
-    pristine_git_object: 536fc52c1d3dec20dc3dd38e65714da08779e4d3
+    last_write_checksum: sha1:97805cc7bc61ef57d2279033d8c0b6859cd6e09f
+    pristine_git_object: 206128fbeaf4799b95c46d20265c1143f83a7898
   docs/components/chatusermessage.md:
     id: 4ab205b0030b
     last_write_checksum: sha1:4c87fbc12f54bb5b58526949e3f8ea9c161f8cdf
@@ -3920,6 +3920,10 @@ trackedFiles:
     id: beee40001fda
     last_write_checksum: sha1:45b7b8881a6560a468153662d61b99605a492edf
     pristine_git_object: 2e0839d06f821dd97780dc22f202dedf23e4efe1
+  docs/components/servertoolusedetails.md:
+    id: b14e315828c5
+    last_write_checksum: sha1:2e4e747062c990a502a208c1c90382305e428fe7
+    pristine_git_object: fb12e181963bb9eada3294d7a605b076f695ab58
   docs/components/serviceunavailableresponseerrordata.md:
     id: 6d65ecfd7ad3
     last_write_checksum: sha1:c0e9357b45a58f3da2d3520b502cec7dae5f3446
@@ -4900,6 +4904,10 @@ trackedFiles:
     id: 01cceb61d42f
     last_write_checksum: sha1:7e1d73bd30584d55f4b116737c15d7c73cdf6a3a
     pristine_git_object: 522f4978a3c4e1d1c0d197b541fc57e745b7d4e7
+  docs/operations/costdetails.md:
+    id: 777b240173de
+    last_write_checksum: sha1:b2748fc0cf305791446f5f217947d82bd74a8350
+    pristine_git_object: 58a1aa8485130f8b49c633dfef0439b83a5f239c
   docs/operations/createaudiospeechglobals.md:
     id: c67d64f11ad7
     last_write_checksum: sha1:a0026b1caf2268dd4a79177fa2bb630eca1498b4
@@ -4974,8 +4982,8 @@ trackedFiles:
     pristine_git_object: 1ff75cb8fa59d2b7b756ea07e9f5849995b62435
   docs/operations/createembeddingsusage.md:
     id: 2dc99973f6c7
-    last_write_checksum: sha1:b01ba733f5d1369b21a54b9f3bfb0e4059504b6f
-    pristine_git_object: 007fb235eef4ebb9b3dda14352e9a252004de4c2
+    last_write_checksum: sha1:292de8b3a80697b56a961d2eb7f97d54dd29c4ae
+    pristine_git_object: 639fb7e305ff27786b6ea858b425e36aaaf20252
   docs/operations/createguardrailglobals.md:
     id: 34f5b2a17330
     last_write_checksum: sha1:a43fb357b9c08974befd14a79da7623e72bc3245
@@ -6102,8 +6110,8 @@ trackedFiles:
     pristine_git_object: a1894915bd32aee65f019885634eb7908970a046
   src/openrouter/components/__init__.py:
     id: 81754e97b3f4
-    last_write_checksum: sha1:805bb2df1d5fe49556f426348971e5ccdc08aa56
-    pristine_git_object: eca63a922d8154ae9106e8f8b5aaf16dbc580afd
+    last_write_checksum: sha1:e59a97a36a75c1848f5342f9c3d061dd993855d8
+    pristine_git_object: f2928e99d526cad8e81c673c4c03bc864c14a365
   src/openrouter/components/aabenchmarkentry.py:
     id: e2e0f0b48c82
     last_write_checksum: sha1:1b6b66672fb80dccdc39843a98bdef6d7d804364
@@ -6558,8 +6566,8 @@ trackedFiles:
     pristine_git_object: 2ccba8386486b7a730816a9829b01754935a2e96
   src/openrouter/components/chatusage.py:
     id: f224a054bf45
-    last_write_checksum: sha1:947079d2163225a49e423151de25dc6132df5bf6
-    pristine_git_object: 3a7357d8a6f725ba18b1f15215a197f11e917659
+    last_write_checksum: sha1:e63f9a7b86d0091b0fddf04ee273088b51dd76a6
+    pristine_git_object: 62e2f91566dbcaf0794d927b679552757efe46b1
   src/openrouter/components/chatusermessage.py:
     id: 7777191e729a
     last_write_checksum: sha1:1ecc9101c05178427d73e455de4d679ac8d78015
@@ -8234,8 +8242,8 @@ trackedFiles:
     pristine_git_object: 37ee42a638f5fce69fc7db1e6b86efb51f381582
   src/openrouter/operations/__init__.py:
     id: 9afcea1e7161
-    last_write_checksum: sha1:d0572cc16c500a9dba895239890bc01414b339a6
-    pristine_git_object: 650e7d0faaf2b32b7c96dd196b6e8c412c573795
+    last_write_checksum: sha1:b555b71cf7d07da5aa6b121a740d1ef69e513629
+    pristine_git_object: b9e4c525f346b441e837c4497cc2e8d723a44352
   src/openrouter/operations/bulkaddworkspacemembers.py:
     id: e0ed56117619
     last_write_checksum: sha1:2b9c73dd8a24d6c479d50118a309e4e0969ca7ea
@@ -8278,8 +8286,8 @@ trackedFiles:
     pristine_git_object: 523d24efa869d63a145167b94e811671b84c5cfb
   src/openrouter/operations/createembeddings.py:
     id: fe1160a960e9
-    last_write_checksum: sha1:5307ac65b8a4c3eec3de9158c2a3d10554212e8b
-    pristine_git_object: 4cc4c5c044fa87a8ae21dd7aa0f83d09f4d00f09
+    last_write_checksum: sha1:55a231d6e9a2f2a76c3fbc1f8af893e393e08bc3
+    pristine_git_object: 6459cab7e1a597f5a1b24f690d845b4ee8809236
   src/openrouter/operations/createguardrail.py:
     id: 52ed4b2f5903
     last_write_checksum: sha1:119141c01d19df6b6d090b67f80145e3bf4d4d60
@@ -10057,6 +10065,8 @@ releaseNotes: |
   * `open_router.benchmarks.get_benchmarks()`: **Added**
   * `open_router.datasets.get_benchmarks_artificial_analysis()`: **Deleted** **Breaking** :warning:
   * `open_router.datasets.get_benchmarks_design_arena()`: **Deleted** **Breaking** :warning:
+  * `open_router.chat.send()`:  `response` **Changed**
+  * `open_router.embeddings.generate()`:  `response.usage` **Changed**
   * `open_router.embeddings.list_models()`:  `response.data.[].reasoning` **Added**
   * `open_router.models.get()`:  `response.data.reasoning` **Added**
   * `open_router.models.list()`:  `response.data.[].reasoning` **Added**

.speakeasy/in.openapi.yaml

@@ -5401,6 +5401,9 @@ components:
         prompt_tokens: 10
         prompt_tokens_details:
           cached_tokens: 2
+        server_tool_use_details:
+          tool_calls_executed: 2
+          tool_calls_requested: 2
         total_tokens: 25
       properties:
         completion_tokens:
@@ -5457,6 +5460,28 @@ components:
               description: Video input tokens
               type: integer
           type: object
+        server_tool_use_details:
+          description: Usage for server-side tool execution (e.g., web search)
+          nullable: true
+          properties:
+            tool_calls_executed:
+              description: Number of OpenRouter server tool calls that executed and produced a result
+              nullable: true
+              type: integer
+            tool_calls_requested:
+              description: >-
+                Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types.
+                Provider-native tools (e.g. native web search) are not counted here.
+              nullable: true
+              type: integer
+            web_search_requests:
+              description: >-
+                Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search
+                is also counted in tool_calls_requested; provider-native web search may report web_search_requests only.
+                Do not sum the two.
+              nullable: true
+              type: integer
+          type: object
         total_tokens:
           description: Total number of tokens
           type: integer
@@ -24610,6 +24635,31 @@ paths:
                         example: 0.0001
                         format: double
                         type: number
+                      cost_details:
+                        description: Breakdown of upstream inference costs
+                        example:
+                          upstream_inference_completions_cost: 0.0004
+                          upstream_inference_cost: null
+                          upstream_inference_prompt_cost: 0.0008
+                        nullable: true
+                        properties:
+                          upstream_inference_completions_cost:
+                            format: double
+                            type: number
+                          upstream_inference_cost:
+                            format: double
+                            nullable: true
+                            type: number
+                          upstream_inference_prompt_cost:
+                            format: double
+                            type: number
+                        required:
+                          - upstream_inference_prompt_cost
+                          - upstream_inference_completions_cost
+                        type: object
+                      is_byok:
+                        description: Whether a request was made using a Bring Your Own Key configuration
+                        type: boolean
                       prompt_tokens:
                         description: Number of tokens in the input
                         example: 8

.speakeasy/out.openapi.yaml

@@ -5392,6 +5392,9 @@ components:
         prompt_tokens: 10
         prompt_tokens_details:
           cached_tokens: 2
+        server_tool_use_details:
+          tool_calls_executed: 2
+          tool_calls_requested: 2
         total_tokens: 25
       properties:
         completion_tokens:
@@ -5448,6 +5451,25 @@ components:
               description: Video input tokens
               type: integer
           type: object
+        server_tool_use_details:
+          description: Usage for server-side tool execution (e.g., web search)
+          nullable: true
+          properties:
+            tool_calls_executed:
+              description: Number of OpenRouter server tool calls that executed and produced a result
+              nullable: true
+              type: integer
+            tool_calls_requested:
+              description: >-
+                Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here.
+              nullable: true
+              type: integer
+            web_search_requests:
+              description: >-
+                Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two.
+              nullable: true
+              type: integer
+          type: object
         total_tokens:
           description: Total number of tokens
           type: integer
@@ -24459,6 +24481,31 @@ paths:
                         example: 0.0001
                         format: double
                         type: number
+                      cost_details:
+                        description: Breakdown of upstream inference costs
+                        example:
+                          upstream_inference_completions_cost: 0.0004
+                          upstream_inference_cost: null
+                          upstream_inference_prompt_cost: 0.0008
+                        nullable: true
+                        properties:
+                          upstream_inference_completions_cost:
+                            format: double
+                            type: number
+                          upstream_inference_cost:
+                            format: double
+                            nullable: true
+                            type: number
+                          upstream_inference_prompt_cost:
+                            format: double
+                            type: number
+                        required:
+                          - upstream_inference_prompt_cost
+                          - upstream_inference_completions_cost
+                        type: object
+                      is_byok:
+                        description: Whether a request was made using a Bring Your Own Key configuration
+                        type: boolean
                       prompt_tokens:
                         description: Number of tokens in the input
                         example: 8

.speakeasy/workflow.lock

@@ -2,20 +2,20 @@ speakeasyVersion: 1.680.0
 sources:
     OpenRouter API:
         sourceNamespace: open-router-chat-completions-api
-        sourceRevisionDigest: sha256:6ca77315c3cd31ab7e308e010b26b7c9eb366b11b78ea9c71179facc4daaf97b
-        sourceBlobDigest: sha256:8bada810c7c5ddb302c51dbbbb36dd0c9a45c4ba1c5e44af1646f69fc2a38751
+        sourceRevisionDigest: sha256:1e8bbe0cea645a95cb24c3e0061459d903aca98286d2c74de7cb8359b8c3c29d
+        sourceBlobDigest: sha256:42b4b8df42026cfc885ee4b34e7a30aaa906f40dc6ad99ea9e6c65e4bad495de
         tags:
             - latest
-            - speakeasy-sdk-regen-1781818757
+            - speakeasy-sdk-regen-1781885111
             - 1.0.0
 targets:
     open-router:
         source: OpenRouter API
         sourceNamespace: open-router-chat-completions-api
-        sourceRevisionDigest: sha256:6ca77315c3cd31ab7e308e010b26b7c9eb366b11b78ea9c71179facc4daaf97b
-        sourceBlobDigest: sha256:8bada810c7c5ddb302c51dbbbb36dd0c9a45c4ba1c5e44af1646f69fc2a38751
+        sourceRevisionDigest: sha256:1e8bbe0cea645a95cb24c3e0061459d903aca98286d2c74de7cb8359b8c3c29d
+        sourceBlobDigest: sha256:42b4b8df42026cfc885ee4b34e7a30aaa906f40dc6ad99ea9e6c65e4bad495de
         codeSamplesNamespace: open-router-python-code-samples
-        codeSamplesRevisionDigest: sha256:80ceff338c097e19bf3951fd00e8010fc7c102b916a684eeec33d507b7a3844f
+        codeSamplesRevisionDigest: sha256:a16acd4648a2b2c90df0256551f25bb6515c70ea239dba657f07fce770e459d5
 workflow:
     workflowVersion: 1.0.0
     speakeasyVersion: 1.680.0

RELEASES.md

@@ -30,7 +30,7 @@ Based on:
 ### Releases
 - [PyPI v0.10.0] https://pypi.org/project/openrouter/0.10.0 - .
 
-## 2026-06-18 21:38:57
+## 2026-06-22 00:59:00
 ### Changes
 Based on:
 - OpenAPI Doc  

src/openrouter/components/__init__.py

@@ -527,6 +527,8 @@ if TYPE_CHECKING:
         CompletionTokensDetailsTypedDict,
         PromptTokensDetails,
         PromptTokensDetailsTypedDict,
+        ServerToolUseDetails,
+        ServerToolUseDetailsTypedDict,
     )
     from .chatusermessage import (
         ChatUserMessage,
@@ -4056,6 +4058,8 @@ __all__ = [
     "SearchQualityLevel",
     "Security",
     "SecurityTypedDict",
+    "ServerToolUseDetails",
+    "ServerToolUseDetailsTypedDict",
     "ServiceUnavailableResponseErrorData",
     "ServiceUnavailableResponseErrorDataTypedDict",
     "ShellCallItem",
@@ -4742,6 +4746,8 @@ _dynamic_imports: dict[str, str] = {
     "CompletionTokensDetailsTypedDict": ".chatusage",
     "PromptTokensDetails": ".chatusage",
     "PromptTokensDetailsTypedDict": ".chatusage",
+    "ServerToolUseDetails": ".chatusage",
+    "ServerToolUseDetailsTypedDict": ".chatusage",
     "ChatUserMessage": ".chatusermessage",
     "ChatUserMessageContent": ".chatusermessage",
     "ChatUserMessageContentTypedDict": ".chatusermessage",

src/openrouter/components/chatusage.py

@@ -112,6 +112,68 @@ class PromptTokensDetails(BaseModel):
     r"""Video input tokens"""
 
 
+class ServerToolUseDetailsTypedDict(TypedDict):
+    r"""Usage for server-side tool execution (e.g., web search)"""
+
+    tool_calls_executed: NotRequired[Nullable[int]]
+    r"""Number of OpenRouter server tool calls that executed and produced a result"""
+    tool_calls_requested: NotRequired[Nullable[int]]
+    r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
+    web_search_requests: NotRequired[Nullable[int]]
+    r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
+
+
+class ServerToolUseDetails(BaseModel):
+    r"""Usage for server-side tool execution (e.g., web search)"""
+
+    tool_calls_executed: OptionalNullable[int] = UNSET
+    r"""Number of OpenRouter server tool calls that executed and produced a result"""
+
+    tool_calls_requested: OptionalNullable[int] = UNSET
+    r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
+
+    web_search_requests: OptionalNullable[int] = UNSET
+    r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = [
+            "tool_calls_executed",
+            "tool_calls_requested",
+            "web_search_requests",
+        ]
+        nullable_fields = [
+            "tool_calls_executed",
+            "tool_calls_requested",
+            "web_search_requests",
+        ]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+            serialized.pop(k, None)
+
+            optional_nullable = k in optional_fields and k in nullable_fields
+            is_set = (
+                self.__pydantic_fields_set__.intersection({n})
+                or k in null_default_fields
+            )  # pylint: disable=no-member
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields or (optional_nullable and is_set)
+            ):
+                m[k] = val
+
+        return m
+
+
 class ChatUsageTypedDict(TypedDict):
     r"""Token usage statistics"""
 
@@ -131,6 +193,8 @@ class ChatUsageTypedDict(TypedDict):
     r"""Whether a request was made using a Bring Your Own Key configuration"""
     prompt_tokens_details: NotRequired[Nullable[PromptTokensDetailsTypedDict]]
     r"""Detailed prompt token usage"""
+    server_tool_use_details: NotRequired[Nullable[ServerToolUseDetailsTypedDict]]
+    r"""Usage for server-side tool execution (e.g., web search)"""
 
 
 class ChatUsage(BaseModel):
@@ -160,6 +224,9 @@ class ChatUsage(BaseModel):
     prompt_tokens_details: OptionalNullable[PromptTokensDetails] = UNSET
     r"""Detailed prompt token usage"""
 
+    server_tool_use_details: OptionalNullable[ServerToolUseDetails] = UNSET
+    r"""Usage for server-side tool execution (e.g., web search)"""
+
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = [
@@ -168,12 +235,14 @@ class ChatUsage(BaseModel):
             "cost_details",
             "is_byok",
             "prompt_tokens_details",
+            "server_tool_use_details",
         ]
         nullable_fields = [
             "completion_tokens_details",
             "cost",
             "cost_details",
             "prompt_tokens_details",
+            "server_tool_use_details",
         ]
         null_default_fields = []
 

src/openrouter/operations/__init__.py

@@ -81,6 +81,8 @@ if TYPE_CHECKING:
         ContentText,
         ContentTextTypedDict,
         ContentTypedDict,
+        CostDetails,
+        CostDetailsTypedDict,
         CreateEmbeddingsData,
         CreateEmbeddingsDataTypedDict,
         CreateEmbeddingsGlobals,
@@ -719,6 +721,8 @@ __all__ = [
     "ContentText",
     "ContentTextTypedDict",
     "ContentTypedDict",
+    "CostDetails",
+    "CostDetailsTypedDict",
     "CreateAudioSpeechGlobals",
     "CreateAudioSpeechGlobalsTypedDict",
     "CreateAudioSpeechRequest",
@@ -1263,6 +1267,8 @@ _dynamic_imports: dict[str, str] = {
     "ContentText": ".createembeddings",
     "ContentTextTypedDict": ".createembeddings",
     "ContentTypedDict": ".createembeddings",
+    "CostDetails": ".createembeddings",
+    "CostDetailsTypedDict": ".createembeddings",
     "CreateEmbeddingsData": ".createembeddings",
     "CreateEmbeddingsDataTypedDict": ".createembeddings",
     "CreateEmbeddingsGlobals": ".createembeddings",

src/openrouter/operations/createembeddings.py

@@ -344,6 +344,54 @@ class CreateEmbeddingsData(BaseModel):
 Object = Literal["list",]
 
 
+class CostDetailsTypedDict(TypedDict):
+    r"""Breakdown of upstream inference costs"""
+
+    upstream_inference_completions_cost: float
+    upstream_inference_prompt_cost: float
+    upstream_inference_cost: NotRequired[Nullable[float]]
+
+
+class CostDetails(BaseModel):
+    r"""Breakdown of upstream inference costs"""
+
+    upstream_inference_completions_cost: float
+
+    upstream_inference_prompt_cost: float
+
+    upstream_inference_cost: OptionalNullable[float] = UNSET
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["upstream_inference_cost"]
+        nullable_fields = ["upstream_inference_cost"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+            serialized.pop(k, None)
+
+            optional_nullable = k in optional_fields and k in nullable_fields
+            is_set = (
+                self.__pydantic_fields_set__.intersection({n})
+                or k in null_default_fields
+            )  # pylint: disable=no-member
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields or (optional_nullable and is_set)
+            ):
+                m[k] = val
+
+        return m
+
+
 class PromptTokensDetailsTypedDict(TypedDict):
     r"""Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text + image) and the upstream provider returns modality-level usage data. Only non-zero modality counts are included."""
 
@@ -387,6 +435,10 @@ class CreateEmbeddingsUsageTypedDict(TypedDict):
     r"""Total number of tokens used"""
     cost: NotRequired[float]
     r"""Cost of the request in credits"""
+    cost_details: NotRequired[Nullable[CostDetailsTypedDict]]
+    r"""Breakdown of upstream inference costs"""
+    is_byok: NotRequired[bool]
+    r"""Whether a request was made using a Bring Your Own Key configuration"""
     prompt_tokens_details: NotRequired[PromptTokensDetailsTypedDict]
     r"""Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text + image) and the upstream provider returns modality-level usage data. Only non-zero modality counts are included."""
 
@@ -403,9 +455,45 @@ class CreateEmbeddingsUsage(BaseModel):
     cost: Optional[float] = None
     r"""Cost of the request in credits"""
 
+    cost_details: OptionalNullable[CostDetails] = UNSET
+    r"""Breakdown of upstream inference costs"""
+
+    is_byok: Optional[bool] = None
+    r"""Whether a request was made using a Bring Your Own Key configuration"""
+
     prompt_tokens_details: Optional[PromptTokensDetails] = None
     r"""Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text + image) and the upstream provider returns modality-level usage data. Only non-zero modality counts are included."""
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["cost", "cost_details", "is_byok", "prompt_tokens_details"]
+        nullable_fields = ["cost_details"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+            serialized.pop(k, None)
+
+            optional_nullable = k in optional_fields and k in nullable_fields
+            is_set = (
+                self.__pydantic_fields_set__.intersection({n})
+                or k in null_default_fields
+            )  # pylint: disable=no-member
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields or (optional_nullable and is_set)
+            ):
+                m[k] = val
+
+        return m
+
 
 class CreateEmbeddingsResponseBodyTypedDict(TypedDict):
     r"""Embeddings response containing embedding vectors"""