first commit

docs/openapi/paths/inference/async.yaml

@@ -0,0 +1,664 @@
+# Async Inference Endpoints
+
+# --- Submission endpoints ---
+
+async-chat-completions:
+  post:
+    operationId: createAsyncChatCompletion
+    summary: Create async chat completion
+    description: |
+      Submits a chat completion request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/chat.yaml#/ChatCompletionRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-text-completions:
+  post:
+    operationId: createAsyncTextCompletion
+    summary: Create async text completion
+    description: |
+      Submits a text completion request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/text.yaml#/TextCompletionRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-responses:
+  post:
+    operationId: createAsyncResponse
+    summary: Create async response
+    description: |
+      Submits a response request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/responses.yaml#/ResponsesRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-embeddings:
+  post:
+    operationId: createAsyncEmbedding
+    summary: Create async embedding
+    description: |
+      Submits an embedding request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/embeddings.yaml#/EmbeddingRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-speech:
+  post:
+    operationId: createAsyncSpeech
+    summary: Create async speech
+    description: |
+      Submits a speech synthesis request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      SSE streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/speech.yaml#/SpeechRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-transcriptions:
+  post:
+    operationId: createAsyncTranscription
+    summary: Create async transcription
+    description: |
+      Submits a transcription request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/transcription.yaml#/TranscriptionRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-generation:
+  post:
+    operationId: createAsyncImageGeneration
+    summary: Create async image generation
+    description: |
+      Submits an image generation request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageGenerationRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-edit:
+  post:
+    operationId: createAsyncImageEdit
+    summary: Create async image edit
+    description: |
+      Submits an image edit request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+      Streaming is not supported for async requests.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageEditRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-variation:
+  post:
+    operationId: createAsyncImageVariation
+    summary: Create async image variation
+    description: |
+      Submits an image variation request for asynchronous execution. Returns a job ID immediately
+      with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncResultTTL'
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageVariationRequest'
+    responses:
+      '202':
+        description: Job accepted for processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+# --- Retrieval endpoints ---
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-chat-completions-job:
+  get:
+    operationId: getAsyncChatCompletionJob
+    summary: Get async chat completion job
+    description: |
+      Retrieves the status and result of an async chat completion job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-text-completions-job:
+  get:
+    operationId: getAsyncTextCompletionJob
+    summary: Get async text completion job
+    description: |
+      Retrieves the status and result of an async text completion job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-responses-job:
+  get:
+    operationId: getAsyncResponseJob
+    summary: Get async response job
+    description: |
+      Retrieves the status and result of an async response job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-embeddings-job:
+  get:
+    operationId: getAsyncEmbeddingJob
+    summary: Get async embedding job
+    description: |
+      Retrieves the status and result of an async embedding job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-speech-job:
+  get:
+    operationId: getAsyncSpeechJob
+    summary: Get async speech job
+    description: |
+      Retrieves the status and result of an async speech job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-transcriptions-job:
+  get:
+    operationId: getAsyncTranscriptionJob
+    summary: Get async transcription job
+    description: |
+      Retrieves the status and result of an async transcription job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-generation-job:
+  get:
+    operationId: getAsyncImageGenerationJob
+    summary: Get async image generation job
+    description: |
+      Retrieves the status and result of an async image generation job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-edit-job:
+  get:
+    operationId: getAsyncImageEditJob
+    summary: Get async image edit job
+    description: |
+      Retrieves the status and result of an async image edit job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+async-image-variation-job:
+  get:
+    operationId: getAsyncImageVariationJob
+    summary: Get async image variation job
+    description: |
+      Retrieves the status and result of an async image variation job.
+      Returns HTTP 202 if the job is still pending or processing, HTTP 200 if completed or failed.
+    tags:
+    - Async Jobs
+    parameters:
+    - $ref: '#/components/parameters/AsyncJobId'
+    responses:
+      '200':
+        description: Job completed (successfully or with failure)
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '202':
+        description: Job is still pending or processing
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/async.yaml#/AsyncJobResponse'
+      '404':
+        description: Job not found or expired
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+
+# --- Shared parameters ---
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+components:
+  parameters:
+    AsyncJobId:
+      name: job_id
+      in: path
+      required: true
+      description: The unique identifier of the async job
+      schema:
+        type: string
+    AsyncResultTTL:
+      name: x-bf-async-job-result-ttl
+      in: header
+      required: false
+      description: |
+        Time-to-live in seconds for the job result after completion. Defaults to 3600 (1 hour).
+        After expiry, the job result is automatically cleaned up.
+      schema:
+        type: integer
+        default: 3600

docs/openapi/paths/inference/audio.yaml

@@ -0,0 +1,71 @@
+speech:
+  post:
+    operationId: createSpeech
+    summary: Create speech
+    description: |
+      Generates audio from the input text. Returns audio data or streams via SSE.
+    tags:
+    - Audio
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/speech.yaml#/SpeechRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          audio/mpeg:
+            schema:
+              type: string
+              format: binary
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/speech.yaml#/SpeechResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/speech.yaml#/SpeechStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+transcriptions:
+  post:
+    operationId: createTranscription
+    summary: Create transcription
+    description: |
+      Transcribes audio into text in the input language.
+    tags:
+    - Audio
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/transcription.yaml#/TranscriptionRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/transcription.yaml#/TranscriptionResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/transcription.yaml#/TranscriptionStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/batches.yaml

@@ -0,0 +1,190 @@
+batches:
+  post:
+    operationId: createBatch
+    summary: Create a batch job
+    description: |
+      Creates a batch job for asynchronous processing.
+    tags:
+    - Batch
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/batch.yaml#/BatchCreateRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/batch.yaml#/BatchCreateResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  get:
+    operationId: listBatches
+    summary: List batch jobs
+    description: |
+      Lists batch jobs for a provider.
+    tags:
+    - Batch
+    parameters:
+    - name: provider
+      in: query
+      required: true
+      description: Provider to list batches for
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    - name: limit
+      in: query
+      description: Maximum number of batches to return
+      schema:
+        type: integer
+        minimum: 1
+    - name: after
+      in: query
+      description: Cursor for pagination
+      schema:
+        type: string
+    - name: before
+      in: query
+      description: Cursor for pagination
+      schema:
+        type: string
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/batch.yaml#/BatchListResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+batches-by-id:
+  get:
+    operationId: retrieveBatch
+    summary: Retrieve a batch job
+    description: |
+      Retrieves a specific batch job by ID.
+    tags:
+    - Batch
+    parameters:
+    - name: batch_id
+      in: path
+      required: true
+      description: The ID of the batch to retrieve
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the batch
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/batch.yaml#/BatchRetrieveResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+batches-cancel:
+  post:
+    operationId: cancelBatch
+    summary: Cancel a batch job
+    description: |
+      Cancels a batch job.
+    tags:
+    - Batch
+    parameters:
+    - name: batch_id
+      in: path
+      required: true
+      description: The ID of the batch to cancel
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the batch
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/batch.yaml#/BatchCancelResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+batches-results:
+  get:
+    operationId: getBatchResults
+    summary: Get batch results
+    description: |
+      Retrieves results from a completed batch job.
+    tags:
+    - Batch
+    parameters:
+    - name: batch_id
+      in: path
+      required: true
+      description: The ID of the batch
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the batch
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/batch.yaml#/BatchResultsResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/chat-completions.yaml

@@ -0,0 +1,33 @@
+chat-completions:
+  post:
+    operationId: createChatCompletion
+    summary: Create a chat completion
+    description: |
+      Creates a completion for the provided messages. Supports streaming via SSE.
+    tags:
+    - Chat Completions
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/chat.yaml#/ChatCompletionRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/chat.yaml#/ChatCompletionResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/chat.yaml#/ChatCompletionStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/containers.yaml

@@ -0,0 +1,390 @@
+containers:
+  post:
+    operationId: createContainer
+    summary: Create a container
+    description: |
+      Creates a new container for storing files and data.
+    tags:
+    - Containers
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/containers.yaml#/ContainerCreateRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerCreateResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  get:
+    operationId: listContainers
+    summary: List containers
+    description: |
+      Lists containers for a provider.
+    tags:
+    - Containers
+    parameters:
+    - name: provider
+      in: query
+      required: true
+      description: Provider to list containers for
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    - name: limit
+      in: query
+      description: Maximum number of containers to return (1-100, default 20)
+      schema:
+        type: integer
+        minimum: 1
+        limit: 200
+        maximum: 100
+    - name: after
+      in: query
+      description: Cursor for pagination
+      schema:
+        type: string
+    - name: order
+      in: query
+      description: Sort order (asc/desc)
+      schema:
+        type: string
+        enum: [asc, desc]
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerListResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+containers-by-id:
+  get:
+    operationId: retrieveContainer
+    summary: Retrieve a container
+    description: |
+      Retrieves a specific container by ID.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container to retrieve
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerRetrieveResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  delete:
+    operationId: deleteContainer
+    summary: Delete a container
+    description: |
+      Deletes a container.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container to delete
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerDeleteResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+# =============================================================================
+# CONTAINER FILES ENDPOINTS
+# =============================================================================
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+container-files:
+  post:
+    operationId: createContainerFile
+    summary: Create a file in a container
+    description: |
+      Creates a new file in a container. You can either upload file content directly
+      via multipart/form-data or reference an existing file by its ID.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/containers.yaml#/ContainerFileCreateMultipartRequest'
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/containers.yaml#/ContainerFileCreateJsonRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerFileCreateResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  get:
+    operationId: listContainerFiles
+    summary: List files in a container
+    description: |
+      Lists all files in a container.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    - name: limit
+      in: query
+      description: Maximum number of files to return
+      schema:
+        type: integer
+        minimum: 1
+        maximum: 100
+    - name: after
+      in: query
+      description: Cursor for pagination
+      schema:
+        type: string
+    - name: order
+      in: query
+      description: Sort order (asc/desc)
+      schema:
+        type: string
+        enum: [asc, desc]
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerFileListResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+container-files-by-id:
+  get:
+    operationId: retrieveContainerFile
+    summary: Retrieve a file from a container
+    description: |
+      Retrieves metadata for a specific file in a container.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container
+      schema:
+        type: string
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerFileRetrieveResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  delete:
+    operationId: deleteContainerFile
+    summary: Delete a file from a container
+    description: |
+      Deletes a file from a container.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container
+      schema:
+        type: string
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file to delete
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/containers.yaml#/ContainerFileDeleteResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+container-files-content:
+  get:
+    operationId: getContainerFileContent
+    summary: Download file content from a container
+    description: |
+      Downloads the content of a file from a container.
+    tags:
+    - Containers
+    parameters:
+    - name: container_id
+      in: path
+      required: true
+      description: The ID of the container
+      schema:
+        type: string
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the container
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/octet-stream:
+            schema:
+              type: string
+              format: binary
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/count-tokens.yaml

@@ -0,0 +1,30 @@
+count-tokens:
+  post:
+    operationId: countTokens
+    summary: Count tokens
+    description: |
+      Counts the number of tokens in the provided messages.
+    tags:
+    - Count Tokens
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/count-tokens.yaml#/CountTokensRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/count-tokens.yaml#/CountTokensResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/embeddings.yaml

@@ -0,0 +1,30 @@
+embeddings:
+  post:
+    operationId: createEmbedding
+    summary: Create embeddings
+    description: |
+      Creates an embedding vector representing the input text.
+    tags:
+    - Embeddings
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/embeddings.yaml#/EmbeddingRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/embeddings.yaml#/EmbeddingResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/files.yaml

@@ -0,0 +1,201 @@
+files:
+  post:
+    operationId: uploadFile
+    summary: Upload a file
+    description: |
+      Uploads a file to be used with batch operations or other features.
+    tags:
+    - Files
+    parameters:
+    - name: provider
+      in: query
+      description: Provider to upload file to (can also use x-model-provider header)
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/files.yaml#/FileUploadRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/files.yaml#/FileUploadResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  get:
+    operationId: listFiles
+    summary: List files
+    description: |
+      Lists files for a provider.
+    tags:
+    - Files
+    parameters:
+    - name: x-model-provider
+      in: query
+      required: true
+      description: Provider to list files for
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    - name: purpose
+      in: query
+      description: Filter by purpose
+      schema:
+        $ref: '../../schemas/inference/files.yaml#/FilePurpose'
+    - name: limit
+      in: query
+      description: Maximum number of files to return
+      schema:
+        type: integer
+        minimum: 1
+    - name: after
+      in: query
+      description: Cursor for pagination
+      schema:
+        type: string
+    - name: order
+      in: query
+      description: Sort order (asc/desc)
+      schema:
+        type: string
+        enum: [asc, desc]
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/files.yaml#/FileListResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+files-by-id:
+  get:
+    operationId: retrieveFile
+    summary: Retrieve file metadata
+    description: |
+      Retrieves metadata for a specific file.
+    tags:
+    - Files
+    parameters:
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the file
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/files.yaml#/FileRetrieveResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  delete:
+    operationId: deleteFile
+    summary: Delete a file
+    description: |
+      Deletes a file.
+    tags:
+    - Files
+    parameters:
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file to delete
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the file
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/files.yaml#/FileDeleteResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+files-content:
+  get:
+    operationId: getFileContent
+    summary: Download file content
+    description: |
+      Downloads the content of a file.
+    tags:
+    - Files
+    parameters:
+    - name: file_id
+      in: path
+      required: true
+      description: The ID of the file
+      schema:
+        type: string
+    - name: provider
+      in: query
+      required: true
+      description: The provider of the file
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/octet-stream:
+            schema:
+              type: string
+              format: binary
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/images.yaml

@@ -0,0 +1,112 @@
+# Image Generation Endpoints
+
+image-generation:
+  post:
+    operationId: imageGeneration
+    summary: Generate an image
+    description: |
+      Generates images from text prompts using the specified model.
+    tags:
+    - Images
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageGenerationRequest'
+    responses:
+      '200':
+        description: |
+          Successful response. Returns JSON for non-streaming requests, or Server-Sent Events (SSE) stream when `stream=true`.
+          When streaming, events are sent with the following event types:
+          - `image_generation.partial_image`: Intermediate image chunks with base64-encoded image data
+          - `image_generation.completed`: Final event for each image with usage information
+          - `error`: Error events with error details
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/images.yaml#/ImageGenerationResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/images.yaml#/ImageGenerationStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+image-edit:
+  post:
+    operationId: imageEdit
+    summary: Edit an image
+    description: |
+      Edits an image using a text prompt and optional mask. Request must be sent as multipart/form-data
+      with at least `model`, `prompt` (unless `type` is `background_removal`), and `image` (or `image[]`).
+    tags:
+    - Images
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageEditRequest'
+    responses:
+      '200':
+        description: |
+          Successful response. Returns JSON for non-streaming requests, or Server-Sent Events (SSE) stream when `stream=true`.
+          When streaming, events are sent with the following event types:
+          - `image_edit.partial_image`: Intermediate image chunks with base64-encoded image data
+          - `image_edit.completed`: Final event for each image with usage information
+          - `error`: Error events with error details
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/images.yaml#/ImageGenerationResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/images.yaml#/ImageEditStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+image-variation:
+  post:
+    operationId: imageVariation
+    summary: Create Variation
+    description: |
+      Creates variations of an image. Request must be sent as multipart/form-data with `model` and `image` (or `image[]`).
+      Does not support streaming.
+    tags:
+    - Images
+    requestBody:
+      required: true
+      content:
+        multipart/form-data:
+          schema:
+            $ref: '../../schemas/inference/images.yaml#/ImageVariationRequest'
+    responses:
+      '200':
+        description: Successful response. Returns JSON with generated image variation(s).
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/images.yaml#/ImageGenerationResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/models.yaml

@@ -0,0 +1,41 @@
+models:
+  get:
+    operationId: listModels
+    summary: List available models
+    description: |
+      Lists available models. If provider is not specified, lists all models from all configured providers.
+    tags:
+    - Models
+    parameters:
+    - name: provider
+      in: query
+      description: Filter by provider (e.g., openai, anthropic, bedrock)
+      schema:
+        $ref: '../../schemas/inference/common.yaml#/ModelProvider'
+    - name: page_size
+      in: query
+      description: Maximum number of models to return
+      schema:
+        type: integer
+        minimum: 0
+    - name: page_token
+      in: query
+      description: Token for pagination
+      schema:
+        type: string
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/models.yaml#/ListModelsResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/rerank.yaml

@@ -0,0 +1,30 @@
+rerank:
+  post:
+    operationId: rerankDocuments
+    summary: Rerank documents
+    description: |
+      Reorders input documents by relevance to a query.
+    tags:
+    - Rerank
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/rerank.yaml#/RerankRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/rerank.yaml#/RerankResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/responses.yaml

@@ -0,0 +1,33 @@
+responses:
+  post:
+    operationId: createResponse
+    summary: Create a response
+    description: |
+      Creates a response using the OpenAI Responses API format. Supports streaming via SSE.
+    tags:
+    - Responses
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/responses.yaml#/ResponsesRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/responses.yaml#/ResponsesResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/responses.yaml#/ResponsesStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/text-completions.yaml

@@ -0,0 +1,33 @@
+text-completions:
+  post:
+    operationId: createTextCompletion
+    summary: Create a text completion
+    description: |
+      Creates a completion for the provided prompt. Supports streaming via SSE.
+    tags:
+    - Text Completions
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/text.yaml#/TextCompletionRequest'
+    responses:
+      '200':
+        description: Successful response
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/text.yaml#/TextCompletionResponse'
+          text/event-stream:
+            schema:
+              $ref: '../../schemas/inference/text.yaml#/TextCompletionStreamResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []

docs/openapi/paths/inference/videos.yaml

@@ -0,0 +1,311 @@
+# Video Generation Endpoints
+
+video-generation:
+  post:
+    operationId: videoGeneration
+    summary: Generate a video
+    description: |
+      Creates a video generation job from a text prompt. This is an asynchronous operation
+      that returns immediately with a job ID. Use the retrieve endpoint to check the status
+      and get the video URL when generation is complete.
+    tags:
+    - Videos
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/videos.yaml#/VideoGenerationRequest'
+    responses:
+      '200':
+        description: |
+          Successful response. Returns a video generation job object with status information.
+          Poll the retrieve endpoint to check completion status.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoGenerationResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  get:
+    operationId: videoList
+    summary: List video generation jobs
+    description: |
+      Lists video generation jobs for a specific provider. Results are paginated
+      and can be filtered using query parameters.
+    tags:
+    - Videos
+    parameters:
+    - name: provider
+      in: query
+      required: true
+      schema:
+        type: string
+      description: Provider name (e.g., "openai", "gemini")
+    - name: after
+      in: query
+      required: false
+      schema:
+        type: string
+      description: Cursor for pagination - ID of the last item from the previous page
+    - name: limit
+      in: query
+      required: false
+      schema:
+        type: integer
+        minimum: 1
+        maximum: 100
+        default: 20
+      description: Maximum number of results to return
+    - name: order
+      in: query
+      required: false
+      schema:
+        type: string
+        enum:
+        - "asc"
+        - "desc"
+        default: "desc"
+      description: Sort order by creation time
+    responses:
+      '200':
+        description: Successful response. Returns a paginated list of video generation jobs.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoListResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+video-by-id:
+  get:
+    operationId: videoRetrieve
+    summary: Retrieve a video generation job
+    description: |
+      Retrieves the status and metadata for a video generation job.
+      Use this endpoint to poll for completion status after creating a video generation job.
+      When the status is "completed", the response will include a URL to download the video.
+    tags:
+    - Videos
+    parameters:
+    - name: video_id
+      in: path
+      required: true
+      schema:
+        type: string
+      description: Video ID in format `id:provider` (e.g., `video_abc123:openai`)
+    responses:
+      '200':
+        description: Successful response. Returns the video generation job details.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoGenerationResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '404':
+        description: Video not found
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+  delete:
+    operationId: videoDelete
+    summary: Delete a video generation job
+    description: |
+      Deletes a video generation job and its associated assets.
+      This operation cannot be undone.
+    tags:
+    - Videos
+    parameters:
+    - name: video_id
+      in: path
+      required: true
+      schema:
+        type: string
+      description: Video ID in format `id:provider` (e.g., `video_abc123:openai`)
+    responses:
+      '200':
+        description: Successful response. Returns deletion confirmation.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoDeleteResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '404':
+        description: Video not found
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+video-download:
+  get:
+    operationId: videoDownload
+    summary: Download video content
+    description: |
+      Downloads the binary content of a generated video.
+      The video must have a status of "completed" to be downloadable.
+      Returns the raw video file (typically MP4 format).
+    tags:
+    - Videos
+    parameters:
+    - name: video_id
+      in: path
+      required: true
+      schema:
+        type: string
+      description: Video ID in format `id:provider` (e.g., `video_abc123:openai`)
+    - name: variant
+      in: query
+      required: false
+      schema:
+        type: string
+        enum:
+        - "video"
+        - "thumbnail"
+        - "spritesheet"
+      description: Variant of the video content to download (provider-specific)
+    responses:
+      '200':
+        description: Successful response. Returns the video file as binary content.
+        content:
+          video/mp4:
+            schema:
+              type: string
+              format: binary
+          application/octet-stream:
+            schema:
+              type: string
+              format: binary
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '404':
+        description: Video not found or not yet available
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+video-delete:
+  delete:
+    operationId: videoDelete
+    summary: Delete a video generation job
+    description: |
+      Deletes a video generation job and its associated assets.
+      This operation cannot be undone.
+    tags:
+    - Videos
+    parameters:
+    - name: video_id
+      in: path
+      required: true
+      schema:
+        type: string
+      description: Video ID in format `id:provider` (e.g., `video_abc123:openai`)
+    responses:
+      '200':
+        description: Successful response. Returns deletion confirmation.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoDeleteResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '404':
+        description: Video not found
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []
+video-remix:
+  post:
+    operationId: videoRemix
+    summary: Remix a video
+    description: |
+      Creates a new video generation job by remixing an existing video with a new prompt.
+      The source video must have a status of "completed" to be remixed.
+      Returns a new video generation job that can be polled for completion.
+    tags:
+    - Videos
+    parameters:
+    - name: video_id
+      in: path
+      required: true
+      schema:
+        type: string
+      description: Video ID in format `id:provider` (e.g., `video_abc123:openai`)
+    requestBody:
+      required: true
+      content:
+        application/json:
+          schema:
+            $ref: '../../schemas/inference/videos.yaml#/VideoRemixRequest'
+    responses:
+      '200':
+        description: |
+          Successful response. Returns a new video generation job object.
+          Poll the retrieve endpoint to check completion status.
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/videos.yaml#/VideoGenerationResponse'
+      '400':
+        $ref: '../../openapi.yaml#/components/responses/BadRequest'
+      '404':
+        description: Source video not found
+        content:
+          application/json:
+            schema:
+              $ref: '../../schemas/inference/common.yaml#/BifrostError'
+      '500':
+        $ref: '../../openapi.yaml#/components/responses/InternalError'
+    security:
+    - BearerAuth: []
+    - BasicAuth: []
+    - VirtualKeyAuth: []
+    - ApiKeyAuth: []