chore: remove deprecated /openai/v1/ routes

Removed all 39 deprecated /openai/v1/* routes across the API layer. These were duplicate routes that have equivalent non-OpenAI paths (e.g., /batches instead of /openai/v1/batches). The standard routes remain fully functional.

client-sdks/stainless/openapi.yml

@@ -1129,31 +1129,6 @@ paths:
               $ref: '#/components/schemas/RunModerationRequest'
         required: true
       deprecated: false
-  /v1/openai/v1/models:
-    get:
-      responses:
-        '200':
-          description: A OpenAIListModelsResponse.
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/OpenAIListModelsResponse'
-        '400':
-          $ref: '#/components/responses/BadRequest400'
-        '429':
-          $ref: >-
-            #/components/responses/TooManyRequests429
-        '500':
-          $ref: >-
-            #/components/responses/InternalServerError500
-        default:
-          $ref: '#/components/responses/DefaultError'
-      tags:
-        - Models
-      summary: List models using the OpenAI API.
-      description: List models using the OpenAI API.
-      parameters: []
-      deprecated: false
   /v1/prompts:
     get:
       responses:
@@ -7020,48 +6995,6 @@ components:
         - metadata
       title: ModerationObjectResults
       description: A moderation object.
-    OpenAIModel:
-      type: object
-      properties:
-        id:
-          type: string
-        object:
-          type: string
-          const: model
-          default: model
-        created:
-          type: integer
-        owned_by:
-          type: string
-        custom_metadata:
-          type: object
-          additionalProperties:
-            oneOf:
-              - type: 'null'
-              - type: boolean
-              - type: number
-              - type: string
-              - type: array
-              - type: object
-      additionalProperties: false
-      required:
-        - id
-        - object
-        - created
-        - owned_by
-      title: OpenAIModel
-      description: A model from OpenAI.
-    OpenAIListModelsResponse:
-      type: object
-      properties:
-        data:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAIModel'
-      additionalProperties: false
-      required:
-        - data
-      title: OpenAIListModelsResponse
     Prompt:
       type: object
       properties:

docs/static/llama-stack-spec.yaml

@@ -1126,31 +1126,6 @@ paths:
               $ref: '#/components/schemas/RunModerationRequest'
         required: true
       deprecated: false
-  /v1/openai/v1/models:
-    get:
-      responses:
-        '200':
-          description: A OpenAIListModelsResponse.
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/OpenAIListModelsResponse'
-        '400':
-          $ref: '#/components/responses/BadRequest400'
-        '429':
-          $ref: >-
-            #/components/responses/TooManyRequests429
-        '500':
-          $ref: >-
-            #/components/responses/InternalServerError500
-        default:
-          $ref: '#/components/responses/DefaultError'
-      tags:
-        - Models
-      summary: List models using the OpenAI API.
-      description: List models using the OpenAI API.
-      parameters: []
-      deprecated: false
   /v1/prompts:
     get:
       responses:
@@ -5807,48 +5782,6 @@ components:
         - metadata
       title: ModerationObjectResults
       description: A moderation object.
-    OpenAIModel:
-      type: object
-      properties:
-        id:
-          type: string
-        object:
-          type: string
-          const: model
-          default: model
-        created:
-          type: integer
-        owned_by:
-          type: string
-        custom_metadata:
-          type: object
-          additionalProperties:
-            oneOf:
-              - type: 'null'
-              - type: boolean
-              - type: number
-              - type: string
-              - type: array
-              - type: object
-      additionalProperties: false
-      required:
-        - id
-        - object
-        - created
-        - owned_by
-      title: OpenAIModel
-      description: A model from OpenAI.
-    OpenAIListModelsResponse:
-      type: object
-      properties:
-        data:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAIModel'
-      additionalProperties: false
-      required:
-        - data
-      title: OpenAIListModelsResponse
     Prompt:
       type: object
       properties:

docs/static/stainless-llama-stack-spec.yaml

@@ -1129,31 +1129,6 @@ paths:
               $ref: '#/components/schemas/RunModerationRequest'
         required: true
       deprecated: false
-  /v1/openai/v1/models:
-    get:
-      responses:
-        '200':
-          description: A OpenAIListModelsResponse.
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/OpenAIListModelsResponse'
-        '400':
-          $ref: '#/components/responses/BadRequest400'
-        '429':
-          $ref: >-
-            #/components/responses/TooManyRequests429
-        '500':
-          $ref: >-
-            #/components/responses/InternalServerError500
-        default:
-          $ref: '#/components/responses/DefaultError'
-      tags:
-        - Models
-      summary: List models using the OpenAI API.
-      description: List models using the OpenAI API.
-      parameters: []
-      deprecated: false
   /v1/prompts:
     get:
       responses:
@@ -7020,48 +6995,6 @@ components:
         - metadata
       title: ModerationObjectResults
       description: A moderation object.
-    OpenAIModel:
-      type: object
-      properties:
-        id:
-          type: string
-        object:
-          type: string
-          const: model
-          default: model
-        created:
-          type: integer
-        owned_by:
-          type: string
-        custom_metadata:
-          type: object
-          additionalProperties:
-            oneOf:
-              - type: 'null'
-              - type: boolean
-              - type: number
-              - type: string
-              - type: array
-              - type: object
-      additionalProperties: false
-      required:
-        - id
-        - object
-        - created
-        - owned_by
-      title: OpenAIModel
-      description: A model from OpenAI.
-    OpenAIListModelsResponse:
-      type: object
-      properties:
-        data:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAIModel'
-      additionalProperties: false
-      required:
-        - data
-      title: OpenAIListModelsResponse
     Prompt:
       type: object
       properties:

src/llama_stack/apis/agents/agents.py

@@ -787,12 +787,6 @@ class Agents(Protocol):
     #
     # Both of these APIs are inherently stateful.
 
-    @webmethod(
-        route="/openai/v1/responses/{response_id}",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_openai_response(
         self,
@@ -805,7 +799,6 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
     async def create_openai_response(
         self,
@@ -842,7 +835,6 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_responses(
         self,
@@ -861,9 +853,6 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
-    )
     @webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_response_input_items(
         self,
@@ -886,7 +875,6 @@ class Agents(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
         """Delete a response.

src/llama_stack/apis/batches/batches.py

@@ -43,7 +43,6 @@ class Batches(Protocol):
     Note: This API is currently under active development and may undergo changes.
     """
 
-    @webmethod(route="/openai/v1/batches", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches", method="POST", level=LLAMA_STACK_API_V1)
     async def create_batch(
         self,
@@ -64,7 +63,6 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def retrieve_batch(self, batch_id: str) -> BatchObject:
         """Retrieve information about a specific batch.
@@ -74,7 +72,6 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
     async def cancel_batch(self, batch_id: str) -> BatchObject:
         """Cancel a batch that is in progress.
@@ -84,7 +81,6 @@ class Batches(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches", method="GET", level=LLAMA_STACK_API_V1)
     async def list_batches(
         self,

src/llama_stack/apis/files/files.py

@@ -110,7 +110,6 @@ class Files(Protocol):
     """
 
     # OpenAI Files API Endpoints
-    @webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_upload_file(
         self,
@@ -134,7 +133,6 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_files(
         self,
@@ -155,7 +153,6 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file(
         self,
@@ -170,7 +167,6 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_file(
         self,
@@ -183,7 +179,6 @@ class Files(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file_content(
         self,

src/llama_stack/apis/inference/inference.py

@@ -1189,7 +1189,6 @@ class InferenceProvider(Protocol):
         raise NotImplementedError("Reranking is not implemented")
         return  # this is so mypy's safe-super rule will consider the method concrete
 
-    @webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_completion(
         self,
@@ -1202,7 +1201,6 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_chat_completion(
         self,
@@ -1215,7 +1213,6 @@ class InferenceProvider(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_embeddings(
         self,
@@ -1240,7 +1237,6 @@ class Inference(InferenceProvider):
     - Rerank models: these models reorder the documents based on their relevance to a query.
     """
 
-    @webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
     async def list_chat_completions(
         self,
@@ -1259,9 +1255,6 @@ class Inference(InferenceProvider):
         """
         raise NotImplementedError("List chat completions is not implemented")
 
-    @webmethod(
-        route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
-    )
     @webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
         """Get chat completion.

src/llama_stack/apis/models/models.py

@@ -115,7 +115,6 @@ class Models(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_models(self) -> OpenAIListModelsResponse:
         """List models using the OpenAI API.
 

src/llama_stack/apis/safety/safety.py

@@ -121,7 +121,6 @@ class Safety(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/moderations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/moderations", method="POST", level=LLAMA_STACK_API_V1)
     async def run_moderation(self, input: str | list[str], model: str | None = None) -> ModerationObject:
         """Create moderation.

src/llama_stack/apis/vector_io/vector_io.py

@@ -545,7 +545,6 @@ class VectorIO(Protocol):
         ...
 
     # OpenAI Vector Stores API endpoints
-    @webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_create_vector_store(
         self,
@@ -558,7 +557,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_vector_stores(
         self,
@@ -577,9 +575,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
-    )
     @webmethod(route="/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_vector_store(
         self,
@@ -592,9 +587,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}",
         method="POST",
@@ -617,9 +609,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}",
         method="DELETE",
@@ -636,12 +625,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/search",
-        method="POST",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/search",
         method="POST",
@@ -674,12 +657,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files",
-        method="POST",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files",
         method="POST",
@@ -702,12 +679,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files",
         method="GET",
@@ -734,12 +705,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="GET",
@@ -758,12 +723,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}/content",
         method="GET",
@@ -782,12 +741,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
-        method="POST",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="POST",
@@ -808,12 +761,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
-        method="DELETE",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="DELETE",
@@ -837,12 +784,6 @@ class VectorIO(Protocol):
         method="POST",
         level=LLAMA_STACK_API_V1,
     )
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/file_batches",
-        method="POST",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     async def openai_create_vector_store_file_batch(
         self,
         vector_store_id: str,
@@ -861,12 +802,6 @@ class VectorIO(Protocol):
         method="GET",
         level=LLAMA_STACK_API_V1,
     )
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     async def openai_retrieve_vector_store_file_batch(
         self,
         batch_id: str,
@@ -880,12 +815,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
-        method="GET",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
         method="GET",
@@ -914,12 +843,6 @@ class VectorIO(Protocol):
         """
         ...
 
-    @webmethod(
-        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
-        method="POST",
-        level=LLAMA_STACK_API_V1,
-        deprecated=True,
-    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
         method="POST",