venice_client 1.0.20 → 1.0.22

data/swagger.yaml

@@ -5,7 +5,7 @@ info:
   description: The Venice.ai API.
   termsOfService: https://venice.ai/legal/tos
   title: Venice.ai API
-  version: "20250918.173746"
+  version: "20251209.153516"
 openapi: 3.0.0
 security:
   - BearerAuth: []
@@ -19,6 +19,8 @@ tags:
     name: Models
   - description: Generate and manipulate images using AI models.
     name: Image
+  - description: Generate videos using AI models.
+    name: Video
   - description: List and retrieve character information for use in completions.
     name: Characters
 components:
@@ -106,6 +108,26 @@ components:
                           oneOf:
                             - type: object
                               properties:
+                                cache_control:
+                                  type: object
+                                  properties:
+                                    ttl:
+                                      type: string
+                                      description: Optional TTL for extended cache duration. Beta feature requiring
+                                        special header.
+                                      example: 1h
+                                    type:
+                                      type: string
+                                      enum:
+                                        - ephemeral
+                                      description: The type of cache control. Currently only "ephemeral" is supported.
+                                      example: ephemeral
+                                  required:
+                                    - type
+                                  description: Optional cache control for prompt caching on supported providers.
+                                  example:
+                                    type: ephemeral
+                                  title: Cache Control
                                 text:
                                   type: string
                                   minLength: 1
@@ -122,13 +144,34 @@ components:
                                 - text
                                 - type
                               additionalProperties: false
-                              description: Text message type.
+                              description: Text message type. Supports optional cache_control for prompt
+                                caching on supported providers.
                               example:
                                 text: Why is the sky blue?
                                 type: text
                               title: text
                             - type: object
                               properties:
+                                cache_control:
+                                  type: object
+                                  properties:
+                                    ttl:
+                                      type: string
+                                      description: Optional TTL for extended cache duration. Beta feature requiring
+                                        special header.
+                                      example: 1h
+                                    type:
+                                      type: string
+                                      enum:
+                                        - ephemeral
+                                      description: The type of cache control. Currently only "ephemeral" is supported.
+                                      example: ephemeral
+                                  required:
+                                    - type
+                                  description: Optional cache control for prompt caching on supported providers.
+                                  example:
+                                    type: ephemeral
+                                  title: Cache Control
                                 image_url:
                                   type: object
                                   properties:
@@ -151,7 +194,8 @@ components:
                                 - image_url
                                 - type
                               additionalProperties: false
-                              description: image_url message type.
+                              description: Image URL message type. Supports optional cache_control for prompt
+                                caching on supported providers.
                               title: image_url
                         title: Objects
                   role:
@@ -174,6 +218,26 @@ components:
                         items:
                           type: object
                           properties:
+                            cache_control:
+                              type: object
+                              properties:
+                                ttl:
+                                  type: string
+                                  description: Optional TTL for extended cache duration. Beta feature requiring
+                                    special header.
+                                  example: 1h
+                                type:
+                                  type: string
+                                  enum:
+                                    - ephemeral
+                                  description: The type of cache control. Currently only "ephemeral" is supported.
+                                  example: ephemeral
+                              required:
+                                - type
+                              description: Optional cache control for prompt caching on supported providers.
+                              example:
+                                type: ephemeral
+                              title: Cache Control
                             text:
                               type: string
                               minLength: 1
@@ -190,7 +254,8 @@ components:
                             - text
                             - type
                           additionalProperties: false
-                          description: Text message type.
+                          description: Text message type. Supports optional cache_control for prompt
+                            caching on supported providers.
                           example:
                             text: Why is the sky blue?
                             type: text
@@ -255,6 +320,26 @@ components:
                         items:
                           type: object
                           properties:
+                            cache_control:
+                              type: object
+                              properties:
+                                ttl:
+                                  type: string
+                                  description: Optional TTL for extended cache duration. Beta feature requiring
+                                    special header.
+                                  example: 1h
+                                type:
+                                  type: string
+                                  enum:
+                                    - ephemeral
+                                  description: The type of cache control. Currently only "ephemeral" is supported.
+                                  example: ephemeral
+                              required:
+                                - type
+                              description: Optional cache control for prompt caching on supported providers.
+                              example:
+                                type: ephemeral
+                              title: Cache Control
                             text:
                               type: string
                               minLength: 1
@@ -271,7 +356,8 @@ components:
                             - text
                             - type
                           additionalProperties: false
-                          description: Text message type.
+                          description: Text message type. Supports optional cache_control for prompt
+                            caching on supported providers.
                           example:
                             text: Why is the sky blue?
                             type: text
@@ -317,7 +403,7 @@ components:
             of models available to you. You can use feature suffixes to enable
             features from the venice_parameters object. Please see "Model
             Feature Suffix" documentation for more details.
-          example: venice-uncensored
+          example: zai-org-glm-4.6
         n:
           type: integer
           default: 1
@@ -333,12 +419,41 @@ components:
           description: Number between -2.0 and 2.0. Positive values penalize new tokens
             based on whether they appear in the text so far, increasing the
             model's likelihood to talk about new topics.
+        prompt_cache_key:
+          type: string
+          description: When supplied, this field may be used to optimize conversation
+            routing to improve cache performance and thus reduce latency.
+          example: random-string
         repetition_penalty:
           type: number
           minimum: 0
           description: The parameter for repetition penalty. 1.0 means no penalty. Values
             > 1.0 discourage repetition.
           example: 1.2
+        reasoning:
+          type: object
+          properties:
+            effort:
+              type: string
+              enum:
+                - low
+                - medium
+                - high
+              description: Controls the reasoning effort level for supported models. Higher
+                effort means more thorough reasoning but increased token usage.
+                Defaults to the model configuration if not specified.
+              example: medium
+          description: Configuration for reasoning behavior on supported models.
+        reasoning_effort:
+          type: string
+          enum:
+            - low
+            - medium
+            - high
+          description: OpenAI-compatible parameter to control reasoning effort level for
+            supported models. Takes precedence over reasoning.effort if both are
+            provided.
+          example: medium
         seed:
           type: integer
           minimum: 0
@@ -441,11 +556,18 @@ components:
                 first chunk of a streaming result, or in the non streaming
                 response.
               example: off
+            enable_web_scraping:
+              type: boolean
+              default: false
+              description: Enable Venice web scraping of URLs in the latest user message using
+                Firecrawl. Off by default.
+              example: false
             enable_web_citations:
               type: boolean
               default: false
               description: When web search is enabled, this will request that the LLM cite its
-                sources using a [REF]0[/REF] format. Defaults to false.
+                sources using a ^index^ or ^i,j^ superscript format (e.g., ^1^).
+                Defaults to false.
             include_search_results_in_stream:
               type: boolean
               default: false
@@ -632,10 +754,10 @@ components:
         model:
           type: string
           description: The model to use for image generation.
-          example: hidream
+          example: z-image-turbo
         negative_prompt:
           type: string
-          maxLength: 1500
+          maxLength: 7500
           description: A description of what should not be in the image. Character limit
             is model specific and is listed in the promptCharacterLimit
             constraint in the model list endpoint.
@@ -643,7 +765,7 @@ components:
         prompt:
           type: string
           minLength: 1
-          maxLength: 1500
+          maxLength: 7500
           description: The description for the image. Character limit is model specific
             and is listed in the promptCharacterLimit setting in the model list
             endpoint.
@@ -676,25 +798,33 @@ components:
           example: 123456789
         steps:
           type: integer
-          minimum: 0
-          exclusiveMinimum: true
-          maximum: 50
-          default: 20
-          description: "Number of inference steps. The following models have reduced max
-            steps from the global max: venice-sd35: 30 max steps, hidream: 50
-            max steps, flux.1-krea: 30 max steps, flux-dev: 30 max steps,
-            flux-dev-uncensored: 30 max steps, lustify-sdxl: 50 max steps,
-            lustify-v7: 25 max steps, pony-realism: 50 max steps, qwen-image: 8
-            max steps, stable-diffusion-3.5: 30 max steps, wai-Illustrious: 30
-            max steps. These constraints are exposed in the model list endpoint
-            for each model."
-          example: 20
+          default: 0
+          description: Number of inference steps. This model does not support steps - this
+            field is ignored.
+          example: 0
         style_preset:
           type: string
           description: An image style to apply to the image. Visit
             https://docs.venice.ai/api-reference/endpoint/image/styles for more
             details.
           example: 3D Model
+        aspect_ratio:
+          type: string
+          description: 'Aspect ratio (utilized by certain image models including Nano
+            Banana). Examples: "1:1", "16:9".'
+          example: 1:1
+        resolution:
+          type: string
+          description: 'Resolution (utilized by certain image models including Nano
+            Banana). Examples: "1024x1024", "512x512".'
+          example: 1024x1024
+        enable_web_search:
+          type: boolean
+          description: Enable web search for the image generation task. This will allow
+            the model to use the latest information from the web to generate the
+            image. Only supported by certain models. If web search is used,
+            additional credits are getting charged.
+          example: false
         width:
           type: integer
           minimum: 0
@@ -729,7 +859,7 @@ components:
           description: The model to use for image generation. Defaults to Venice's default
             image model. If a non-existent model is specified (ie an OpenAI
             model name), it will default to Venice's default image model.
-          example: hidream
+          example: z-image-turbo
         moderation:
           type: string
           nullable: true
@@ -1135,6 +1265,99 @@ components:
         speed: 1
         streaming: false
         voice: af_sky
+    QueueVideoRequest:
+      type: object
+      properties:
+        model:
+          type: string
+          description: The model to use for image generation.
+          example: wan-2.5-preview-image-to-video
+        prompt:
+          type: string
+          minLength: 1
+          maxLength: 2500
+          description: The prompt to use for video generation. The maximum length is 2500
+            characters.
+          example: Commerce being conducted in the city of Venice, Italy.
+        negative_prompt:
+          type: string
+          maxLength: 2500
+          default: low resolution, error, worst quality, low quality, defects
+          description: The negative prompt to use for video generation. The maximum length
+            is 2500 characters.
+          example: low resolution, error, worst quality, low quality, defects
+        duration:
+          type: string
+          enum:
+            - 5s
+            - 10s
+          description: The duration of the video to generate.
+          example: 5s
+        aspect_ratio:
+          description: The aspect ratio of the video to generate.
+          example: 16:9
+        resolution:
+          type: string
+          enum:
+            - 1080p
+            - 720p
+            - 480p
+          default: 720p
+          description: The resolution of the video to generate.
+          example: 720p
+        audio:
+          description: For models which support audio generation and configuration,
+            indicates if audio should be generated. Defaults to true.
+          example: true
+        image_url:
+          type: string
+          description: For image to video models, the reference image to use for video
+            generation. Must be either a URL (starting with "http://" or
+            "https://") or a data URL (starting with "data:").
+          example: data:image/png;base64,iVBORw0K...
+      required:
+        - model
+        - prompt
+        - duration
+        - image_url
+      additionalProperties: false
+    CompleteVideoRequest:
+      type: object
+      properties:
+        model:
+          type: string
+          description: The ID of the model used for video generation.
+          example: video-model-123
+        queue_id:
+          type: string
+          description: The ID of the video generation request.
+          example: 123e4567-e89b-12d3-a456-426614174000
+      required:
+        - model
+        - queue_id
+      additionalProperties: false
+    RetrieveVideoRequest:
+      type: object
+      properties:
+        model:
+          type: string
+          description: The ID of the model used for video generation.
+          example: video-model-123
+        queue_id:
+          type: string
+          description: The ID of the video generation request.
+          example: 123e4567-e89b-12d3-a456-426614174000
+        delete_media_on_completion:
+          type: boolean
+          default: false
+          description: If true, the video media will be deleted from storage after the
+            request is completed. If false, you can use the complete endpoint to
+            remove the media once you have successfully downloaded the video.
+          example: false
+      required:
+        - model
+        - queue_id
+      additionalProperties: false
     BillingUsageRequest:
       type: object
       properties:
@@ -1326,6 +1549,15 @@ components:
               type: boolean
               description: Is this model in beta?
               example: false
+            privacy:
+              type: string
+              enum:
+                - private
+                - anonymized
+              description: The privacy mode of the model. Private models have zero data
+                retention. Anonymized models Venice can not guarantee privacy
+                on, but requests are not affiliated with a user
+              example: private
             capabilities:
               type: object
               properties:
@@ -1336,9 +1568,12 @@ components:
                 quantization:
                   type: string
                   enum:
+                    - fp4
                     - fp8
                     - fp16
                     - bf16
+                    - int8
+                    - int4
                     - not-available
                   description: The quantization type of the running model.
                   example: fp8
@@ -1436,6 +1671,64 @@ components:
                     - top_p
                   description: Constraints that apply to text models.
                   title: Text Model Constraints
+                - type: object
+                  properties:
+                    aspect_ratios:
+                      type: array
+                      items:
+                        type: string
+                      description: The aspect ratios supported by the model. Empty array means the
+                        model does not support a defined aspect ratio.
+                      example:
+                        - 16:9
+                        - 9:16
+                    resolutions:
+                      type: array
+                      items:
+                        type: string
+                      description: The resolutions supported by the model. Empty array means the model
+                        does not support a defined resolution.
+                      example:
+                        - 1080p
+                        - 720p
+                        - 480p
+                    durations:
+                      type: array
+                      items:
+                        type: string
+                      description: The durations supported by the model. Empty array means the model
+                        does not support a defined duration.
+                      example:
+                        - 5s
+                        - 10s
+                        - 15s
+                        - 20s
+                        - 30s
+                    model_type:
+                      type: string
+                      enum:
+                        - image-to-video
+                        - text-to-video
+                        - video
+                      description: The type of video model.
+                      example: image-to-video
+                    audio:
+                      type: boolean
+                      description: Does the model support audio generation?
+                      example: true
+                    audio_configurable:
+                      type: boolean
+                      description: Can audio be enabled or disabled for the video generation?
+                      example: true
+                  required:
+                    - aspect_ratios
+                    - resolutions
+                    - durations
+                    - model_type
+                    - audio
+                    - audio_configurable
+                  description: Constraints that apply to video models.
+                  title: Video Model Constraints
               description: Constraints that apply to this model.
             name:
               type: string
@@ -1461,18 +1754,12 @@ components:
                           type: number
                           description: USD cost per million input tokens
                           example: 0.7
-                        vcu:
-                          type: number
-                          description: VCU cost per million input tokens (deprecated - use Diem instead)
-                          deprecated: true
-                          example: 7
                         diem:
                           type: number
                           description: Diem cost per million input tokens
                           example: 7
                       required:
                         - usd
-                        - vcu
                         - diem
                     output:
                       type: object
@@ -1481,18 +1768,12 @@ components:
                           type: number
                           description: USD cost per million output tokens
                           example: 2.8
-                        vcu:
-                          type: number
-                          description: VCU cost per million output tokens (deprecated - use Diem instead)
-                          deprecated: true
-                          example: 28
                         diem:
                           type: number
                           description: Diem cost per million output tokens
                           example: 28
                       required:
                         - usd
-                        - vcu
                         - diem
                   required:
                     - input
@@ -1508,18 +1789,12 @@ components:
                           type: number
                           description: USD cost per image generation
                           example: 0.01
-                        vcu:
-                          type: number
-                          description: VCU cost per image generation (deprecated - use Diem instead)
-                          deprecated: true
-                          example: 0.1
                         diem:
                           type: number
                           description: Diem cost per image generation
                           example: 0.1
                       required:
                         - usd
-                        - vcu
                         - diem
                     upscale:
                       type: object
@@ -1531,18 +1806,12 @@ components:
                               type: number
                               description: USD cost for 2x upscale
                               example: 0.02
-                            vcu:
-                              type: number
-                              description: VCU cost for 2x upscale (deprecated - use Diem instead)
-                              deprecated: true
-                              example: 0.2
                             diem:
                               type: number
                               description: Diem cost for 2x upscale
                               example: 0.2
                           required:
                             - usd
-                            - vcu
                             - diem
                         4x:
                           type: object
@@ -1551,18 +1820,12 @@ components:
                               type: number
                               description: USD cost for 4x upscale
                               example: 0.08
-                            vcu:
-                              type: number
-                              description: VCU cost for 4x upscale (deprecated - use Diem instead)
-                              deprecated: true
-                              example: 0.8
                             diem:
                               type: number
                               description: Diem cost for 4x upscale
                               example: 0.8
                           required:
                             - usd
-                            - vcu
                             - diem
                       required:
                         - 2x
@@ -1581,19 +1844,12 @@ components:
                           type: number
                           description: USD cost per million input characters
                           example: 3.5
-                        vcu:
-                          type: number
-                          description: VCU cost per million input characters (deprecated - use Diem
-                            instead)
-                          deprecated: true
-                          example: 35
                         diem:
                           type: number
                           description: Diem cost per million input characters
                           example: 35
                       required:
                         - usd
-                        - vcu
                         - diem
                   required:
                     - input
@@ -1636,12 +1892,14 @@ components:
         type:
           type: string
           enum:
+            - asr
             - embedding
             - image
             - text
             - tts
             - upscale
             - inpaint
+            - video
           description: Model type
           example: text
       required:
@@ -1676,11 +1934,9 @@ components:
           pricing:
             input:
               usd: 0.15
-              vcu: 1.5
               diem: 0.15
             output:
               usd: 0.6
-              vcu: 6
               diem: 0.6
           traits:
             - fastest
@@ -1814,6 +2070,26 @@ paths:
                                       items:
                                         type: object
                                         properties:
+                                          cache_control:
+                                            type: object
+                                            properties:
+                                              ttl:
+                                                type: string
+                                                description: Optional TTL for extended cache duration. Beta feature requiring
+                                                  special header.
+                                                example: 1h
+                                              type:
+                                                type: string
+                                                enum:
+                                                  - ephemeral
+                                                description: The type of cache control. Currently only "ephemeral" is supported.
+                                                example: ephemeral
+                                            required:
+                                              - type
+                                            description: Optional cache control for prompt caching on supported providers.
+                                            example:
+                                              type: ephemeral
+                                            title: Cache Control
                                           text:
                                             type: string
                                             minLength: 1
@@ -1830,7 +2106,8 @@ paths:
                                           - text
                                           - type
                                         additionalProperties: false
-                                        description: Text message type.
+                                        description: Text message type. Supports optional cache_control for prompt
+                                          caching on supported providers.
                                         example:
                                           text: Why is the sky blue?
                                           type: text
@@ -1935,7 +2212,7 @@ paths:
                   model:
                     type: string
                     description: The model id used for the request.
-                    example: venice-uncensored
+                    example: zai-org-glm-4.6
                   object:
                     type: string
                     enum:
@@ -1992,6 +2269,10 @@ paths:
                         type: boolean
                         description: Did the request enable web citations?
                         example: true
+                      enable_web_scraping:
+                        type: boolean
+                        description: Did the request enable web scraping of URLs via Firecrawl?
+                        example: false
                       include_venice_system_prompt:
                         type: boolean
                         description: Did the request include the Venice system prompt?
@@ -2098,6 +2379,7 @@ paths:
                     required:
                       - enable_web_search
                       - enable_web_citations
+                      - enable_web_scraping
                       - include_venice_system_prompt
                       - include_search_results_in_stream
                       - return_search_results_as_documents
@@ -2151,6 +2433,7 @@ paths:
                     return_search_results_as_documents: false
                     web_search_citations: []
                     enable_web_search: auto
+                    enable_web_scraping: false
                     enable_web_citations: true
                     strip_thinking_response: true
                     disable_thinking: true
@@ -2700,12 +2983,14 @@ paths:
             anyOf:
               - type: string
                 enum:
+                  - asr
                   - embedding
                   - image
                   - text
                   - tts
                   - upscale
                   - inpaint
+                  - video
               - type: string
                 enum:
                   - all
@@ -2736,12 +3021,14 @@ paths:
                     anyOf:
                       - type: string
                         enum:
+                          - asr
                           - embedding
                           - image
                           - text
                           - tts
                           - upscale
                           - inpaint
+                          - video
                       - type: string
                         enum:
                           - all
@@ -2772,12 +3059,14 @@ paths:
         - schema:
             type: string
             enum:
+              - asr
               - embedding
               - image
               - text
               - tts
               - upscale
               - inpaint
+              - video
             default: text
             description: Filter models by type.
             example: text
@@ -2802,12 +3091,14 @@ paths:
                     anyOf:
                       - type: string
                         enum:
+                          - asr
                           - embedding
                           - image
                           - text
                           - tts
                           - upscale
                           - inpaint
+                          - video
                       - type: string
                         enum:
                           - all
@@ -2844,12 +3135,14 @@ paths:
         - schema:
             type: string
             enum:
+              - asr
               - embedding
               - image
               - text
               - tts
               - upscale
               - inpaint
+              - video
             default: text
             description: Filter models by type.
             example: text
@@ -2874,12 +3167,14 @@ paths:
                     anyOf:
                       - type: string
                         enum:
+                          - asr
                           - embedding
                           - image
                           - text
                           - tts
                           - upscale
                           - inpaint
+                          - video
                       - type: string
                         enum:
                           - all
@@ -3470,10 +3765,6 @@ paths:
               schema:
                 type: object
                 properties:
-                  warningMessage:
-                    type: string
-                    description: A warning message to disambiguate staked DIEM balance from legacy
-                      DIEM (formerly VCU) balance
                   data:
                     type: object
                     properties:
@@ -3502,11 +3793,6 @@ paths:
                             type: number
                             description: The USD balance of the key.
                             example: 50.23
-                          VCU:
-                            type: number
-                            description: The VCU balance of the key. VCU is being deprecated in favor of
-                              Diem.
-                            example: 100.023
                           DIEM:
                             type: number
                             description: The Diem balance of the key.
@@ -3529,7 +3815,7 @@ paths:
                             apiModelId:
                               type: string
                               description: The ID of the API model.
-                              example: venice-uncensored
+                              example: zai-org-glm-4.6
                             rateLimits:
                               type: array
                               items:
@@ -3596,7 +3882,7 @@ paths:
                           description: The ID of the API key that exceeded the limit.
                         modelId:
                           type: string
-                          default: venice-uncensored
+                          default: zai-org-glm-4.6
                           description: The ID of the model that was used when the rate limit was exceeded.
                         rateLimitTier:
                           type: string
@@ -4337,6 +4623,231 @@ paths:
             application/json:
               schema:
                 $ref: "#/components/schemas/StandardError"
+  /video/complete:
+    post:
+      description: Delete a video generation request from storage after it has been
+        successfully downloaded. Videos can be automatically deleted after
+        retrieval by setting the `delete_media_on_completion` flag to true when
+        calling the retrieve API.
+      operationId: completeVideo
+      summary: /api/v1/video/complete
+      tags:
+        - Video
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/CompleteVideoRequest"
+      responses:
+        "200":
+          description: Video generation request completed successfully
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  success:
+                    type: boolean
+                    description: Indicates whether the video cleanup was successful.
+                    example: true
+                required:
+                  - success
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/DetailedError"
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+  /video/queue:
+    post:
+      description: Queue a new video generation request.
+      operationId: queueVideo
+      summary: /api/v1/video/queue
+      tags:
+        - Video
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/QueueVideoRequest"
+      responses:
+        "200":
+          description: Video generation request queued successfully
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  model:
+                    type: string
+                    description: The ID of the model used for video generation.
+                    example: video-model-123
+                  queue_id:
+                    type: string
+                    description: The ID of the video generation request.
+                    example: 123e4567-e89b-12d3-a456-426614174000
+                required:
+                  - model
+                  - queue_id
+                additionalProperties: false
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/DetailedError"
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "413":
+          description: The request payload is too large. Please reduce the size of your
+            request.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "422":
+          description: Your prompt violates the content policy of Venice.ai or the model
+            provider
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+  /video/quote:
+    post:
+      description: Quote a video generation request. Utilizes the same parameters as
+        the queue API and will return the price in USD for the request.
+      operationId: quoteVideo
+      summary: /api/v1/video/quote
+      tags:
+        - Video
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/QueueVideoRequest"
+      responses:
+        "200":
+          description: Video generation price quote
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  quote:
+                    type: number
+                required:
+                  - quote
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/DetailedError"
+  /video/retrieve:
+    post:
+      description: Retrieve a video generation result. Returns the video file if
+        completed, or a status if the request is still processing.
+      operationId: retrieveVideo
+      summary: /api/v1/video/retrieve
+      tags:
+        - Video
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/RetrieveVideoRequest"
+      responses:
+        "200":
+          description: Video file if completed, or processing status if still in progress
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  status:
+                    type: string
+                    enum:
+                      - PROCESSING
+                    description: The status of the video generation request.
+                    example: PROCESSING
+                  average_execution_time:
+                    type: number
+                    description: The average execution time of the video generation request in
+                      milliseconds.
+                    example: 145000
+                  execution_duration:
+                    type: number
+                    description: The current duration of the video generation request in
+                      milliseconds.
+                    example: 53200
+                required:
+                  - status
+                  - average_execution_time
+                  - execution_duration
+            video/mp4:
+              schema:
+                format: binary
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/DetailedError"
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "404":
+          description: Media could not be found. Request may may be invalid, expired, or
+            deleted.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "422":
+          description: Your prompt violates the content policy of Venice.ai or the model
+            provider
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StandardError"
   /billing/usage:
     get:
       description: "Get paginated billing usage data for the authenticated user. NOTE: