venice_client 1.0.1 → 1.0.3

data/swagger.yaml

@@ -0,0 +1,4791 @@
+externalDocs:
+  description: Venice.ai API documentation
+  url: https://docs.venice.ai
+info:
+  description: The Venice.ai API.
+  termsOfService: https://venice.ai/legal/tos
+  title: Venice.ai API
+  version: "20250709.013306"
+openapi: 3.0.0
+security:
+  - BearerAuth: []
+servers:
+  - url: https://api.venice.ai/api/v1
+tags:
+  - description: Given a list of messages comprising a conversation, the model will
+      return a response.
+    name: Chat
+  - description: List and describe the various models available in the API.
+    name: Models
+  - description: Generate and manipulate images using AI models.
+    name: Image
+components:
+  securitySchemes:
+    BearerAuth:
+      bearerFormat: JWT
+      scheme: bearer
+      type: http
+  schemas:
+    ChatCompletionRequest:
+      type: object
+      properties:
+        frequency_penalty:
+          type: number
+          maximum: 2
+          minimum: -2
+          default: 0
+          description: Number between -2.0 and 2.0. Positive values penalize new tokens
+            based on their existing frequency in the text so far, decreasing the
+            model's likelihood to repeat the same line verbatim.
+        logprobs:
+          type: boolean
+          description: Whether to include log probabilities in the response. This is not
+            supported by all models.
+          example: true
+        top_logprobs:
+          type: integer
+          minimum: 0
+          description: The number of highest probability tokens to return for each token
+            position.
+          example: 1
+        max_completion_tokens:
+          type: integer
+          description: An upper bound for the number of tokens that can be generated for a
+            completion, including visible output tokens and reasoning tokens.
+        max_temp:
+          type: number
+          minimum: 0
+          maximum: 2
+          description: Maximum temperature value for dynamic temperature scaling.
+          example: 1.5
+        max_tokens:
+          type: integer
+          description: The maximum number of tokens that can be generated in the chat
+            completion. This value can be used to control costs for text
+            generated via API. This value is now deprecated in favor of
+            max_completion_tokens.
+        messages:
+          type: array
+          items:
+            anyOf:
+              - type: object
+                properties:
+                  content:
+                    anyOf:
+                      - type: string
+                        title: String
+                      - type: array
+                        items:
+                          oneOf:
+                            - type: object
+                              properties:
+                                text:
+                                  type: string
+                                  minLength: 1
+                                  description: The prompt text of the message. Must be at-least one character in
+                                    length
+                                  example: Why is the sky blue?
+                                  title: Text Content Object
+                                type:
+                                  type: string
+                                  enum:
+                                    - text
+                                  title: Text Content String
+                              required:
+                                - text
+                                - type
+                              additionalProperties: false
+                              description: Text message type.
+                              example:
+                                text: Why is the sky blue?
+                                type: text
+                              title: text
+                            - type: object
+                              properties:
+                                image_url:
+                                  type: object
+                                  properties:
+                                    url:
+                                      type: string
+                                      description: The URL of the image. Can be a data URL with a base64 encoded image
+                                        or a public URL. URL must be publicly
+                                        accessible. Image must pass validation
+                                        checks and be >= 64 pixels square.
+                                      format: uri
+                                  required:
+                                    - url
+                                  description: Object containing the image URL information
+                                  title: Image URL Object
+                                type:
+                                  type: string
+                                  enum:
+                                    - image_url
+                              required:
+                                - image_url
+                                - type
+                              additionalProperties: false
+                              description: image_url message type.
+                              title: image_url
+                        title: Objects
+                  role:
+                    type: string
+                    enum:
+                      - user
+                required:
+                  - content
+                  - role
+                description: The user message is the input from the user. It is part of the
+                  conversation and is visible to the assistant.
+                title: User Message
+              - type: object
+                properties:
+                  content:
+                    anyOf:
+                      - type: string
+                        title: String
+                      - type: array
+                        items:
+                          type: object
+                          properties:
+                            text:
+                              type: string
+                              minLength: 1
+                              description: The prompt text of the message. Must be at-least one character in
+                                length
+                              example: Why is the sky blue?
+                              title: Text Content Object
+                            type:
+                              type: string
+                              enum:
+                                - text
+                              title: Text Content String
+                          required:
+                            - text
+                            - type
+                          additionalProperties: false
+                          description: Text message type.
+                          example:
+                            text: Why is the sky blue?
+                            type: text
+                          title: text
+                        title: Objects
+                      - nullable: true
+                        title: "null"
+                  name:
+                    type: string
+                  reasoning_content:
+                    type: string
+                    nullable: true
+                  role:
+                    type: string
+                    enum:
+                      - assistant
+                  tool_calls:
+                    type: array
+                    items:
+                      nullable: true
+                required:
+                  - content
+                  - role
+                description: The assistant message contains the response from the LLM.
+                title: Assistant Message
+              - type: object
+                properties:
+                  content:
+                    type: string
+                  name:
+                    type: string
+                  reasoning_content:
+                    type: string
+                    nullable: true
+                  role:
+                    type: string
+                    enum:
+                      - tool
+                  tool_call_id:
+                    type: string
+                  tool_calls:
+                    type: array
+                    items:
+                      nullable: true
+                required:
+                  - content
+                  - role
+                  - tool_call_id
+                description: The tool message is a special message that is used to call a tool.
+                  It is not part of the conversation and is not visible to the
+                  user.
+                title: Tool Message
+              - type: object
+                properties:
+                  content:
+                    anyOf:
+                      - type: string
+                        title: String
+                      - type: array
+                        items:
+                          type: object
+                          properties:
+                            text:
+                              type: string
+                              minLength: 1
+                              description: The prompt text of the message. Must be at-least one character in
+                                length
+                              example: Why is the sky blue?
+                              title: Text Content Object
+                            type:
+                              type: string
+                              enum:
+                                - text
+                              title: Text Content String
+                          required:
+                            - text
+                            - type
+                          additionalProperties: false
+                          description: Text message type.
+                          example:
+                            text: Why is the sky blue?
+                            type: text
+                          title: text
+                        title: Objects
+                  name:
+                    type: string
+                  role:
+                    type: string
+                    enum:
+                      - system
+                required:
+                  - content
+                  - role
+                description: The system message is a special message that provides context to
+                  the model. It is not part of the conversation and is not
+                  visible to the user.
+                title: System Message
+          minItems: 1
+          description: A list of messages comprising the conversation so far. Depending on
+            the model you use, different message types (modalities) are
+            supported, like text and images. For compatibility purposes, the
+            schema supports submitting multiple image_url messages, however,
+            only the last image_url message will be passed to and processed by
+            the model.
+        min_p:
+          type: number
+          minimum: 0
+          maximum: 1
+          description: Sets a minimum probability threshold for token selection. Tokens
+            with probabilities below this value are filtered out.
+          example: 0.05
+        min_temp:
+          type: number
+          minimum: 0
+          maximum: 2
+          description: Minimum temperature value for dynamic temperature scaling.
+          example: 0.1
+        model:
+          type: string
+          description: The ID of the model you wish to prompt. May also be a model trait,
+            or a model compatibility mapping. See the models endpoint for a list
+            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
+        n:
+          type: integer
+          default: 1
+          description: How many chat completion choices to generate for each input
+            message. Note that you will be charged based on the number of
+            generated tokens across all of the choices. Keep n as 1 to minimize
+            costs.
+        presence_penalty:
+          type: number
+          maximum: 2
+          minimum: -2
+          default: 0
+          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.
+        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
+        seed:
+          type: integer
+          minimum: 0
+          exclusiveMinimum: true
+          description: The random seed used to generate the response. This is useful for
+            reproducibility.
+          example: 42
+        stop:
+          anyOf:
+            - type: string
+              title: String
+            - type: array
+              items:
+                type: string
+              minItems: 1
+              maxItems: 4
+              title: Array of Strings
+            - nullable: true
+              title: "null"
+          description: Up to 4 sequences where the API will stop generating further
+            tokens. Defaults to null.
+        stop_token_ids:
+          type: array
+          items:
+            type: number
+          description: Array of token IDs where the API will stop generating further tokens.
+          example:
+            - 151643
+            - 151645
+        stream:
+          type: boolean
+          description: Whether to stream back partial progress. Defaults to false.
+          example: true
+        stream_options:
+          type: object
+          properties:
+            include_usage:
+              type: boolean
+              description: Whether to include usage information in the stream.
+        temperature:
+          type: number
+          minimum: 0
+          maximum: 2
+          default: 0.7
+          description: What sampling temperature to use, between 0 and 2. Higher values
+            like 0.8 will make the output more random, while lower values like
+            0.2 will make it more focused and deterministic. We generally
+            recommend altering this or top_p but not both.
+          example: 0.7
+        top_k:
+          type: integer
+          minimum: 0
+          description: The number of highest probability vocabulary tokens to keep for
+            top-k-filtering.
+          example: 40
+        top_p:
+          type: number
+          minimum: 0
+          maximum: 1
+          default: 0.9
+          description: An alternative to sampling with temperature, called nucleus
+            sampling, where the model considers the results of the tokens with
+            top_p probability mass. So 0.1 means only the tokens comprising the
+            top 10% probability mass are considered.
+          example: 0.9
+        user:
+          type: string
+          description: This field is discarded on the request but is supported in the
+            Venice API for compatibility with OpenAI clients.
+        venice_parameters:
+          type: object
+          properties:
+            character_slug:
+              type: string
+              description: The character slug of a public Venice character.
+              example: venice
+            strip_thinking_response:
+              type: boolean
+              default: false
+              description: Strip <think></think> blocks from the response. Applicable only to
+                reasoning / thinking models. Also available to use as a model
+                feature suffix. Defaults to false.
+              example: false
+            disable_thinking:
+              type: boolean
+              default: false
+              description: On supported reasoning models, will disable thinking and strip the
+                <think></think> blocks from the response. Defaults to false.
+              example: false
+            enable_web_search:
+              type: string
+              enum:
+                - auto
+                - off
+                - on
+              default: off
+              description: Enable web search for this request. Defaults to off. On will force
+                web search on the request. Auto will enable it based on the
+                model's discretion. Citations will be returned either in the
+                first chunk of a streaming result, or in the non streaming
+                response.
+              example: auto
+            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.
+              example: true
+            include_search_results_in_stream:
+              type: boolean
+              default: false
+              description: Experimental feature - When set to true, the LLM will include
+                search results in the stream as the first emitted chunk.
+                Defaults to false.
+              example: true
+            include_venice_system_prompt:
+              type: boolean
+              default: true
+              description: Whether to include the Venice supplied system prompts along side
+                specified system prompts. Defaults to true.
+          description: Unique parameters to Venice's API implementation.
+        parallel_tool_calls:
+          type: boolean
+          default: true
+          description: Whether to enable parallel function calling during tool use.
+          example: false
+        response_format:
+          oneOf:
+            - type: object
+              properties:
+                json_schema:
+                  type: object
+                  additionalProperties:
+                    nullable: true
+                type:
+                  type: string
+                  enum:
+                    - json_schema
+              required:
+                - json_schema
+                - type
+              additionalProperties: false
+              description: The JSON Schema that should be used to validate and format the
+                response.
+              example:
+                json_schema:
+                  properties:
+                    age:
+                      type: number
+                    name:
+                      type: string
+                  required:
+                    - name
+                    - age
+                  type: object
+                type: json_schema
+              title: json_schema
+            - type: object
+              properties:
+                type:
+                  type: string
+                  enum:
+                    - json_object
+              required:
+                - type
+              additionalProperties: false
+              description: The response should be formatted as a JSON object. This is a
+                deprecated implementation and the preferred use is json_schema.
+              title: json_object
+          description: Format in which the response should be returned.
+        tool_choice:
+          anyOf:
+            - type: object
+              properties:
+                function:
+                  type: object
+                  properties:
+                    name:
+                      type: string
+                  required:
+                    - name
+                  additionalProperties: false
+                type:
+                  type: string
+              required:
+                - function
+                - type
+              additionalProperties: false
+            - type: string
+        tools:
+          type: array
+          nullable: true
+          items:
+            type: object
+            properties:
+              function:
+                type: object
+                properties:
+                  description:
+                    type: string
+                  name:
+                    type: string
+                  parameters:
+                    type: object
+                    additionalProperties:
+                      nullable: true
+                required:
+                  - name
+                additionalProperties: false
+              id:
+                type: string
+              type:
+                type: string
+            required:
+              - function
+            description: A tool that can be called by the model. Currently, only functions
+              are supported as tools.
+            title: Tool Call
+          description: A list of tools the model may call. Currently, only functions are
+            supported as a tool. Use this to provide a list of functions the
+            model may generate JSON inputs for.
+      required:
+        - messages
+        - model
+      additionalProperties: false
+    GenerateImageRequest:
+      type: object
+      properties:
+        cfg_scale:
+          type: number
+          minimum: 0
+          exclusiveMinimum: true
+          maximum: 20
+          description: CFG scale parameter. Higher values lead to more adherence to the
+            prompt.
+          example: 7.5
+        embed_exif_metadata:
+          type: boolean
+          default: false
+          description: Embed prompt generation information into the image's EXIF metadata.
+          example: false
+        format:
+          type: string
+          enum:
+            - jpeg
+            - png
+            - webp
+          default: webp
+          description: "The image format to return. WebP are smaller and optimized for web
+            use. PNG are higher quality but larger in file size. "
+          example: webp
+        height:
+          type: integer
+          minimum: 0
+          exclusiveMinimum: true
+          maximum: 1280
+          default: 1024
+          description: Height of the generated image. Each model has a specific height and
+            width divisor listed in the widthHeightDivisor constraint in the
+            model list endpoint.
+          example: 1024
+        hide_watermark:
+          type: boolean
+          default: false
+          description: Whether to hide the Venice watermark. Venice may ignore this
+            parameter for certain generated content.
+          example: false
+        inpaint:
+          nullable: true
+          description: This feature is deprecated and was disabled on May 19th, 2025. A
+            revised in-painting API will be launched in the near future.
+          deprecated: true
+        lora_strength:
+          type: integer
+          minimum: 0
+          maximum: 100
+          description: Lora strength for the model. Only applies if the model uses
+            additional Loras.
+          example: 50
+        model:
+          type: string
+          description: The model to use for image generation.
+          example: hidream
+        negative_prompt:
+          type: string
+          maxLength: 1500
+          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.
+          example: Clouds, Rain, Snow
+        prompt:
+          type: string
+          minLength: 1
+          maxLength: 1500
+          description: The description for the image. Character limit is model specific
+            and is listed in the promptCharacterLimit setting in the model list
+            endpoint.
+          example: A beautiful sunset over a mountain range
+        return_binary:
+          type: boolean
+          default: false
+          description: Whether to return binary image data instead of base64.
+          example: false
+        safe_mode:
+          type: boolean
+          default: true
+          description: Whether to use safe mode. If enabled, this will blur images that
+            are classified as having adult content.
+          example: false
+        seed:
+          type: integer
+          minimum: -999999999
+          maximum: 999999999
+          default: 0
+          description: Random seed for generation. If not provided, a random seed will be
+            used.
+          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, fluently-xl: 50 max steps, flux-dev: 30 max steps,
+            flux-dev-uncensored-11: 30 max steps, flux-dev-uncensored: 30 max
+            steps, lustify-sdxl: 50 max steps, pony-realism: 50 max steps,
+            stable-diffusion-3.5: 30 max steps. These constraints are exposed in
+            the model list endpoint for each model."
+          example: 20
+        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
+        width:
+          type: integer
+          minimum: 0
+          exclusiveMinimum: true
+          maximum: 1280
+          default: 1024
+          description: Width of the generated image. Each model has a specific height and
+            width divisor listed in the widthHeightDivisor constraint in the
+            model list endpoint.
+          example: 1024
+      required:
+        - model
+        - prompt
+      additionalProperties: false
+    SimpleGenerateImageRequest:
+      type: object
+      properties:
+        background:
+          type: string
+          nullable: true
+          enum:
+            - transparent
+            - opaque
+            - auto
+          default: auto
+          description: This parameter is not used in Venice image generation but is
+            supported for compatibility with OpenAI API
+          example: auto
+        model:
+          type: string
+          default: default
+          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
+        moderation:
+          type: string
+          nullable: true
+          enum:
+            - low
+            - auto
+          default: auto
+          description: auto enables safe venice mode which will blur out adult content.
+            low disables safe venice mode.
+          example: auto
+        n:
+          type: integer
+          nullable: true
+          minimum: 1
+          maximum: 1
+          default: 1
+          description: Number of images to generate. Venice presently only supports 1
+            image per request.
+          example: 1
+        output_compression:
+          type: integer
+          nullable: true
+          minimum: 0
+          maximum: 100
+          default: 100
+          description: This parameter is not used in Venice image generation but is
+            supported for compatibility with OpenAI API
+        output_format:
+          type: string
+          enum:
+            - jpeg
+            - png
+            - webp
+          default: png
+          description: Output format for generated images
+          example: png
+        prompt:
+          type: string
+          minLength: 1
+          maxLength: 1500
+          description: A text description of the desired image.
+          example: A beautiful sunset over mountain ranges
+        quality:
+          type: string
+          nullable: true
+          enum:
+            - auto
+            - high
+            - medium
+            - low
+            - hd
+            - standard
+          default: auto
+          description: This parameter is not used in Venice image generation but is
+            supported for compatibility with OpenAI API
+          example: auto
+        response_format:
+          type: string
+          nullable: true
+          enum:
+            - b64_json
+            - url
+          default: b64_json
+          description: Response format. URL will be a data URL.
+          example: b64_json
+        size:
+          type: string
+          nullable: true
+          enum:
+            - auto
+            - 256x256
+            - 512x512
+            - 1024x1024
+            - 1536x1024
+            - 1024x1536
+            - 1792x1024
+            - 1024x1792
+          default: auto
+          description: Size of generated images. Default is 1024x1024
+          example: 1024x1024
+        style:
+          type: string
+          nullable: true
+          enum:
+            - vivid
+            - natural
+          default: natural
+          description: This parameter is not used in Venice image generation but is
+            supported for compatibility with OpenAI API
+          example: natural
+        user:
+          type: string
+          description: This parameter is not used in Venice image generation but is
+            supported for compatibility with OpenAI API
+          example: user123
+      required:
+        - prompt
+      additionalProperties: false
+    UpscaleImageRequest:
+      type: object
+      properties:
+        enhance:
+          anyOf:
+            - type: boolean
+            - type: string
+              enum:
+                - "true"
+                - "false"
+          default: "false"
+          description: Whether to enhance the image using Venice's image engine during
+            upscaling. Must be true if scale is 1.
+          example: true
+        enhanceCreativity:
+          type: number
+          nullable: true
+          minimum: 0
+          maximum: 1
+          default: 0.5
+          description: Higher values let the enhancement AI change the image more. Setting
+            this to 1 effectively creates an entirely new image.
+          example: 0.5
+        enhancePrompt:
+          type: string
+          maxLength: 1500
+          description: The text to image style to apply during prompt enhancement. Does
+            best with short descriptive prompts, like gold, marble or angry,
+            menacing.
+          example: gold
+        image:
+          anyOf:
+            - {}
+            - type: string
+          description: The image to upscale. Can be either a file upload or a
+            base64-encoded string. Image dimensions must be at least 65536
+            pixels and final dimensions after scaling must not exceed 16777216
+            pixels.
+        replication:
+          type: number
+          nullable: true
+          minimum: 0
+          maximum: 1
+          default: 0.35
+          description: How strongly lines and noise in the base image are preserved.
+            Higher values are noisier but less plastic/AI
+            "generated"/hallucinated. Must be between 0 and 1.
+          example: 0.35
+        scale:
+          type: number
+          minimum: 1
+          maximum: 4
+          default: 2
+          description: The scale factor for upscaling the image. Must be a number between
+            1 and 4. Scale of 1 requires enhance to be set true and will only
+            run the enhancer. Scale must be > 1 if enhance is false. A scale of
+            4 with large images will result in the scale being dynamically set
+            to ensure the final image stays within the maximum size limits.
+          example: 2
+      required:
+        - image
+      additionalProperties: false
+      description: Upscale or enhance an image based on the supplied parameters. Using
+        a scale of 1 with enhance enabled will only run the enhancer.
+      example:
+        enhance: true
+        enhanceCreativity: 0.5
+        enhancePrompt: gold
+        image: iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...
+        scale: 2
+    EditImageRequest:
+      type: object
+      properties:
+        prompt:
+          type: string
+          maxLength: 1500
+          description: 'The text directions to edit or modify the image. Does best with
+            short but descriptive prompts. IE: "Change the color of", "remove
+            the object", "change the sky to a sunrise", etc.'
+          example: Change the color of the sky to a sunrise
+        image:
+          anyOf:
+            - {}
+            - type: string
+          description: The image to edit. Can be either a file upload or a base64-encoded
+            string. Image dimensions must be at least 65536 pixels and must not
+            exceed 33177600 pixels.
+      required:
+        - prompt
+        - image
+      additionalProperties: false
+      description: Edit an image based on the supplied prompt.
+      example:
+        prompt: Colorize
+        image: iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAAIGNIUk0A...
+    CreateEmbeddingRequestSchema:
+      type: object
+      properties:
+        dimensions:
+          type: integer
+          minimum: 1
+          description: The number of dimensions the resulting output embeddings should have.
+        encoding_format:
+          type: string
+          enum:
+            - float
+            - base64
+          default: float
+          description: The format to return the embeddings in. Can be either `float` or
+            `base64`.
+          example: float
+        input:
+          anyOf:
+            - type: string
+              minLength: 1
+              description: The string that will be turned into an embedding. Cannot be an
+                empty string.
+              example: This is a test.
+              title: string
+            - type: array
+              items:
+                type: string
+              minItems: 1
+              maxItems: 2048
+              description: The array of strings that will be turned into an embedding. Array
+                must be 2048 dimensions or less.
+              example:
+                - This is a test.
+              title: array
+            - type: array
+              items:
+                type: integer
+                minimum: 1
+              minItems: 1
+              maxItems: 2048
+              description: The array of integers that will be turned into an embedding. Array
+                must be 2048 dimensions or less.
+              example:
+                - 1212
+                - 318
+                - 257
+                - 1332
+                - 13
+              title: array
+            - type: array
+              items:
+                type: array
+                items:
+                  type: integer
+                minItems: 1
+              minItems: 1
+              maxItems: 2048
+              description: The array of arrays containing integers that will be turned into an
+                embedding. Array must be 2048 dimensions or less.
+              example:
+                - - 1212
+                  - 318
+                  - 257
+                  - 1332
+                  - 13
+              title: array
+          description: Input text to embed, encoded as a string or array of tokens. To
+            embed multiple inputs in a single request, pass an array of strings
+            or array of token arrays. The input must not exceed the max input
+            tokens for the model (8192 tokens), cannot be an empty string, and
+            any array must be 2048 dimensions or less.
+          example: The quick brown fox jumped over the lazy dog
+        model:
+          anyOf:
+            - type: string
+            - type: string
+              enum:
+                - text-embedding-bge-m3
+          description: ID of the model to use. You can use the List models API to see all
+            of your available models, or see our Model overview for descriptions
+            of them.
+          example: text-embedding-bge-m3
+        user:
+          type: string
+          description: This is an unused parameter and is discarded by Venice. It is
+            supported solely for API compatibility with OpenAI.
+      required:
+        - input
+        - model
+      additionalProperties: false
+      description: Create embeddings for the supplied input.
+      example:
+        encoding_format: float
+        input: The quick brown fox jumped over the lazy dog
+        model: text-embedding-bge-m3
+    CreateSpeechRequestSchema:
+      type: object
+      properties:
+        input:
+          type: string
+          minLength: 1
+          maxLength: 4096
+          description: The text to generate audio for. The maximum length is 4096
+            characters.
+          example: Hello, this is a test of the text to speech system.
+        model:
+          type: string
+          enum:
+            - tts-kokoro
+          default: tts-kokoro
+          description: The model ID of a Venice TTS model.
+          example: tts-kokoro
+        response_format:
+          type: string
+          enum:
+            - mp3
+            - opus
+            - aac
+            - flac
+            - wav
+            - pcm
+          default: mp3
+          description: The format to audio in.
+          example: mp3
+        speed:
+          type: number
+          minimum: 0.25
+          maximum: 4
+          default: 1
+          description: The speed of the generated audio. Select a value from 0.25 to 4.0.
+            1.0 is the default.
+          example: 1
+        streaming:
+          type: boolean
+          default: false
+          description: Should the content stream back sentence by sentence or be processed
+            and returned as a complete audio file.
+          example: true
+        voice:
+          type: string
+          enum:
+            - af_alloy
+            - af_aoede
+            - af_bella
+            - af_heart
+            - af_jadzia
+            - af_jessica
+            - af_kore
+            - af_nicole
+            - af_nova
+            - af_river
+            - af_sarah
+            - af_sky
+            - am_adam
+            - am_echo
+            - am_eric
+            - am_fenrir
+            - am_liam
+            - am_michael
+            - am_onyx
+            - am_puck
+            - am_santa
+            - bf_alice
+            - bf_emma
+            - bf_lily
+            - bm_daniel
+            - bm_fable
+            - bm_george
+            - bm_lewis
+            - zf_xiaobei
+            - zf_xiaoni
+            - zf_xiaoxiao
+            - zf_xiaoyi
+            - zm_yunjian
+            - zm_yunxi
+            - zm_yunxia
+            - zm_yunyang
+            - ff_siwis
+            - hf_alpha
+            - hf_beta
+            - hm_omega
+            - hm_psi
+            - if_sara
+            - im_nicola
+            - jf_alpha
+            - jf_gongitsune
+            - jf_nezumi
+            - jf_tebukuro
+            - jm_kumo
+            - pf_dora
+            - pm_alex
+            - pm_santa
+            - ef_dora
+            - em_alex
+            - em_santa
+          default: af_sky
+          description: The voice to use when generating the audio.
+          example: af_sky
+      required:
+        - input
+      additionalProperties: false
+      description: Request to generate audio from text.
+      example:
+        input: Hello, welcome to Venice Voice.
+        model: tts-kokoro
+        response_format: mp3
+        speed: 1
+        streaming: false
+        voice: af_sky
+    BillingUsageRequest:
+      type: object
+      properties:
+        currency:
+          type: string
+          description: Filter by currency
+          enum:
+            - USD
+            - VCU
+            - DIEM
+          example: USD
+        endDate:
+          type: string
+          format: date-time
+          description: End date for filtering records (ISO 8601)
+          example: 2024-12-31T23:59:59Z
+        limit:
+          type: integer
+          minimum: 0
+          exclusiveMinimum: true
+          maximum: 500
+          default: 200
+          description: Number of items per page
+          example: 200
+        page:
+          type: integer
+          minimum: 0
+          exclusiveMinimum: true
+          default: 1
+          description: Page number for pagination
+          example: 1
+        sortOrder:
+          type: string
+          enum:
+            - asc
+            - desc
+          default: desc
+          description: Sort order for createdAt field
+          example: desc
+        startDate:
+          type: string
+          format: date-time
+          description: Start date for filtering records (ISO 8601)
+          example: 2024-01-01T00:00:00Z
+    BillingUsageResponse:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            type: object
+            properties:
+              amount:
+                type: number
+                description: The total amount charged for the billing usage entry
+              currency:
+                type: string
+                enum:
+                  - USD
+                  - VCU
+                  - DIEM
+                description: The currency charged for the billing usage entry
+                example: USD
+              inferenceDetails:
+                type: object
+                nullable: true
+                properties:
+                  completionTokens:
+                    type: number
+                    nullable: true
+                    description: Number of tokens used in the completion. Only present for LLM
+                      usage.
+                  inferenceExecutionTime:
+                    type: number
+                    nullable: true
+                    description: Time taken for inference execution in milliseconds
+                  promptTokens:
+                    type: number
+                    nullable: true
+                    description: Number of tokens requested in the prompt. Only present for LLM
+                      usage.
+                  requestId:
+                    type: string
+                    nullable: true
+                    description: Unique identifier for the inference request
+                required:
+                  - completionTokens
+                  - inferenceExecutionTime
+                  - promptTokens
+                  - requestId
+                description: Details about the related inference request, if applicable
+              notes:
+                type: string
+                description: Notes about the billing usage entry
+              pricePerUnitUsd:
+                type: number
+                description: The price per unit in USD
+              sku:
+                type: string
+                description: The product associated with the billing usage entry
+              timestamp:
+                type: string
+                description: The timestamp the billing usage entry was created
+                example: 2025-01-01T00:00:00Z
+              units:
+                type: number
+                description: The number of units consumed
+            required:
+              - amount
+              - currency
+              - inferenceDetails
+              - notes
+              - pricePerUnitUsd
+              - sku
+              - timestamp
+              - units
+        pagination:
+          type: object
+          properties:
+            limit:
+              type: number
+            page:
+              type: number
+            total:
+              type: number
+            totalPages:
+              type: number
+          required:
+            - limit
+            - page
+            - total
+            - totalPages
+      required:
+        - data
+        - pagination
+      additionalProperties: false
+      description: The response schema for the billing usage endpoint
+      example:
+        data:
+          - amount: -0.1
+            currency: DIEM
+            inferenceDetails: null
+            notes: API Inference
+            pricePerUnitUsd: 0.1
+            sku: venice-sd35-image-unit
+            timestamp: {}
+            units: 1
+          - amount: -0.06356
+            currency: DIEM
+            inferenceDetails:
+              completionTokens: 227
+              inferenceExecutionTime: 2964
+              promptTokens: 339
+              requestId: chatcmpl-4007fd29f42b7d3c4107f4345e8d174a
+            notes: API Inference
+            pricePerUnitUsd: 2.8
+            sku: llama-3.3-70b-llm-output-mtoken
+            timestamp: {}
+            units: 0.000227
+        pagination:
+          limit: 1
+          page: 200
+          total: 56090
+          totalPages: 56090
+    ModelResponse:
+      type: object
+      properties:
+        created:
+          type: number
+          description: Release date on Venice API
+          example: 1699000000
+        id:
+          type: string
+          description: Model ID
+          example: venice-uncensored
+        model_spec:
+          type: object
+          properties:
+            availableContextTokens:
+              type: number
+              description: The context length supported by the model. Only applicable for text
+                models.
+              example: 32768
+            beta:
+              type: boolean
+              description: Is this model in beta?
+              example: false
+            capabilities:
+              type: object
+              properties:
+                optimizedForCode:
+                  type: boolean
+                  description: Is the LLM optimized for coding?
+                  example: true
+                quantization:
+                  type: string
+                  enum:
+                    - fp8
+                    - fp16
+                    - not-available
+                  description: The quantization type of the running model.
+                  example: fp8
+                supportsFunctionCalling:
+                  type: boolean
+                  description: Does the LLM model support function calling?
+                  example: true
+                supportsReasoning:
+                  type: boolean
+                  description: Does the model support reasoning with <thinking> blocks of output.
+                  example: true
+                supportsResponseSchema:
+                  type: boolean
+                  description: Does the LLM model support response schema? Only models that
+                    support function calling can support response_schema.
+                  example: true
+                supportsVision:
+                  type: boolean
+                  description: Does the LLM support vision?
+                  example: true
+                supportsWebSearch:
+                  type: boolean
+                  description: Does the LLM model support web search?
+                  example: true
+                supportsLogProbs:
+                  type: boolean
+                  description: Does the LLM model support logprobs parameter?
+                  example: true
+              required:
+                - optimizedForCode
+                - quantization
+                - supportsFunctionCalling
+                - supportsReasoning
+                - supportsResponseSchema
+                - supportsVision
+                - supportsWebSearch
+                - supportsLogProbs
+              additionalProperties: false
+              description: Text model specific capabilities.
+            constraints:
+              anyOf:
+                - type: object
+                  properties:
+                    promptCharacterLimit:
+                      type: number
+                      description: The maximum supported prompt length.
+                      example: 2048
+                    steps:
+                      type: object
+                      properties:
+                        default:
+                          type: number
+                          description: The default steps value for the model
+                          example: 25
+                        max:
+                          type: number
+                          description: The maximum supported steps value for the model
+                          example: 50
+                      required:
+                        - default
+                        - max
+                    widthHeightDivisor:
+                      type: number
+                      description: The requested width and height of the image generation must be
+                        divisible by this value.
+                      example: 8
+                  required:
+                    - promptCharacterLimit
+                    - steps
+                    - widthHeightDivisor
+                  description: Constraints that apply to image models.
+                  title: Image Model Constraints
+                - type: object
+                  properties:
+                    temperature:
+                      type: object
+                      properties:
+                        default:
+                          type: number
+                          description: The default temperature value for the model
+                          example: 0.7
+                      required:
+                        - default
+                    top_p:
+                      type: object
+                      properties:
+                        default:
+                          type: number
+                          description: The default top_p value for the model
+                          example: 0.9
+                      required:
+                        - default
+                  required:
+                    - temperature
+                    - top_p
+                  description: Constraints that apply to text models.
+                  title: Text Model Constraints
+              description: Constraints that apply to this model.
+            name:
+              type: string
+              description: The name of the model.
+              example: Venice Uncensored 1.1
+            modelSource:
+              type: string
+              description: The source of the model, such as a URL to the model repository.
+              example: https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
+            offline:
+              type: boolean
+              default: false
+              description: Is this model presently offline?
+              example: false
+            pricing:
+              anyOf:
+                - type: object
+                  properties:
+                    input:
+                      type: object
+                      properties:
+                        usd:
+                          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
+                      properties:
+                        usd:
+                          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
+                    - output
+                  description: Token-based pricing for chat models
+                  title: LLM Model Pricing
+                - type: object
+                  properties:
+                    generation:
+                      type: object
+                      properties:
+                        usd:
+                          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
+                      properties:
+                        2x:
+                          type: object
+                          properties:
+                            usd:
+                              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
+                          properties:
+                            usd:
+                              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
+                        - 4x
+                  required:
+                    - generation
+                    - upscale
+                  description: Pricing for image generation and upscaling
+                  title: Image Model Pricing
+                - type: object
+                  properties:
+                    input:
+                      type: object
+                      properties:
+                        usd:
+                          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
+                  description: Pricing for audio models (TTS)
+                  title: Audio Model Pricing
+              description: Pricing details for the model
+            traits:
+              type: array
+              items:
+                type: string
+              description: Traits that apply to this model. You can specify a trait to
+                auto-select a model vs. specifying the model ID in your request
+                to avoid breakage as Venice updates and iterates on its models.
+              example:
+                - default_code
+            voices:
+              type: array
+              items:
+                type: string
+              description: The voices available for this TTS model. Only applicable for TTS
+                models.
+              example:
+                - af_alloy
+                - af_aoede
+                - af_bella
+                - af_heart
+                - af_jadzia
+        object:
+          type: string
+          enum:
+            - model
+          description: Object type
+          example: model
+        owned_by:
+          type: string
+          enum:
+            - venice.ai
+          description: Who runs the model
+          example: venice.ai
+        type:
+          type: string
+          enum:
+            - embedding
+            - image
+            - text
+            - tts
+            - upscale
+            - inpaint
+          description: Model type
+          example: text
+      required:
+        - id
+        - model_spec
+        - object
+        - owned_by
+        - type
+      description: Response schema for model information
+      example:
+        created: 1727966436
+        id: llama-3.2-3b
+        model_spec:
+          availableContextTokens: 131072
+          capabilities:
+            optimizedForCode: false
+            quantization: fp16
+            supportsFunctionCalling: true
+            supportsReasoning: false
+            supportsResponseSchema: true
+            supportsVision: false
+            supportsWebSearch: true
+            supportsLogProbs: true
+          constraints:
+            temperature:
+              default: 0.8
+            top_p:
+              default: 0.9
+          name: Llama 3.2 3B
+          modelSource: https://huggingface.co/meta-llama/Llama-3.2-3B
+          offline: false
+          pricing:
+            input:
+              usd: 0.15
+              vcu: 1.5
+              diem: 0.15
+            output:
+              usd: 0.6
+              vcu: 6
+              diem: 0.6
+          traits:
+            - fastest
+        object: model
+        owned_by: venice.ai
+        type: text
+    ModelTraitSchema:
+      type: object
+      additionalProperties:
+        type: string
+      description: List of available models
+      example:
+        default: llama-3.3-70b
+        fastest: llama-3.2-3b-akash
+    ModelCompatibilitySchema:
+      type: object
+      additionalProperties:
+        type: string
+      description: List of available models
+      example:
+        gpt-4o: llama-3.3-70b
+  parameters: {}
+paths:
+  /chat/completions:
+    post:
+      description: Run text inference based on the supplied parameters. Long running
+        requests should use the streaming API by setting stream=true in your
+        request.
+      operationId: createChatCompletion
+      parameters:
+        - description: Supported compression encodings (gzip, br). Only applied when
+            stream is false.
+          in: header
+          name: Accept-Encoding
+          required: false
+          schema:
+            example: gzip, br
+            type: string
+      summary: /api/v1/chat/completions
+      tags:
+        - Chat
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/ChatCompletionRequest"
+      responses:
+        "200":
+          description: OK
+          headers:
+            Content-Encoding:
+              description: The encoding used to compress the response
+              schema:
+                enum:
+                  - gzip
+                  - br
+                type: string
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  choices:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        finish_reason:
+                          type: string
+                          enum:
+                            - stop
+                            - length
+                          description: The reason the completion finished.
+                          example: stop
+                        index:
+                          type: integer
+                          description: The index of the choice in the list.
+                          example: 0
+                        logprobs:
+                          type: object
+                          nullable: true
+                          properties:
+                            bytes:
+                              type: array
+                              items:
+                                type: number
+                              description: Raw bytes of the token
+                              example:
+                                - 104
+                                - 101
+                                - 108
+                                - 108
+                                - 111
+                            logprob:
+                              type: number
+                              description: The log probability of this token
+                              example: -0.34
+                            token:
+                              type: string
+                              description: The token string
+                              example: hello
+                            top_logprobs:
+                              type: array
+                              items:
+                                type: object
+                                properties:
+                                  bytes:
+                                    type: array
+                                    items:
+                                      type: number
+                                  logprob:
+                                    type: number
+                                  token:
+                                    type: string
+                                required:
+                                  - logprob
+                                  - token
+                              description: Top tokens considered with their log probabilities
+                          required:
+                            - logprob
+                            - token
+                        message:
+                          anyOf:
+                            - type: object
+                              properties:
+                                content:
+                                  anyOf:
+                                    - type: string
+                                      title: String
+                                    - type: array
+                                      items:
+                                        type: object
+                                        properties:
+                                          text:
+                                            type: string
+                                            minLength: 1
+                                            description: The prompt text of the message. Must be at-least one character in
+                                              length
+                                            example: Why is the sky blue?
+                                            title: Text Content Object
+                                          type:
+                                            type: string
+                                            enum:
+                                              - text
+                                            title: Text Content String
+                                        required:
+                                          - text
+                                          - type
+                                        additionalProperties: false
+                                        description: Text message type.
+                                        example:
+                                          text: Why is the sky blue?
+                                          type: text
+                                        title: text
+                                      title: Objects
+                                    - nullable: true
+                                      title: "null"
+                                name:
+                                  type: string
+                                reasoning_content:
+                                  type: string
+                                  nullable: true
+                                role:
+                                  type: string
+                                  enum:
+                                    - assistant
+                                tool_calls:
+                                  type: array
+                                  items:
+                                    nullable: true
+                              required:
+                                - content
+                                - role
+                              description: The assistant message contains the response from the LLM.
+                              title: Assistant Message
+                            - type: object
+                              properties:
+                                content:
+                                  type: string
+                                name:
+                                  type: string
+                                reasoning_content:
+                                  type: string
+                                  nullable: true
+                                role:
+                                  type: string
+                                  enum:
+                                    - tool
+                                tool_call_id:
+                                  type: string
+                                tool_calls:
+                                  type: array
+                                  items:
+                                    nullable: true
+                              required:
+                                - content
+                                - role
+                                - tool_call_id
+                              description: The tool message is a special message that is used to call a tool.
+                                It is not part of the conversation and is not
+                                visible to the user.
+                              title: Tool Message
+                        stop_reason:
+                          type: string
+                          nullable: true
+                          enum:
+                            - stop
+                            - length
+                          description: The reason the completion stopped.
+                          example: stop
+                      required:
+                        - finish_reason
+                        - index
+                        - logprobs
+                        - message
+                    description: A list of chat completion choices. Can be more than one if n is
+                      greater than 1.
+                    example:
+                      - finish_reason: stop
+                        index: 0
+                        logprobs: null
+                        message:
+                          content: The sky appears blue because of the way Earth's atmosphere scatters
+                            sunlight. When sunlight reaches Earth's atmosphere,
+                            it is made up of various colors of the spectrum, but
+                            blue light waves are shorter and scatter more easily
+                            when they hit the gases and particles in the
+                            atmosphere. This scattering occurs in all
+                            directions, but from our perspective on the ground,
+                            it appears as a blue hue that dominates the sky's
+                            color. This phenomenon is known as Rayleigh
+                            scattering. During sunrise and sunset, the sunlight
+                            has to travel further through the atmosphere, which
+                            allows more time for the blue light to scatter away
+                            from our direct line of sight, leaving the longer
+                            wavelengths, such as red, yellow, and orange, to
+                            dominate the sky's color.
+                          reasoning_content: null
+                          role: assistant
+                          tool_calls: []
+                        stop_reason: null
+                  created:
+                    type: integer
+                    description: The time at which the request was created.
+                    example: 1677858240
+                  id:
+                    type: string
+                    description: The ID of the request.
+                    example: chatcmpl-abc123
+                  model:
+                    type: string
+                    description: The model id used for the request.
+                    example: venice-uncensored
+                  object:
+                    type: string
+                    enum:
+                      - chat.completion
+                    description: The type of the object returned.
+                    example: chat.completion
+                  prompt_logprobs:
+                    anyOf:
+                      - nullable: true
+                        title: "null"
+                      - type: object
+                        additionalProperties:
+                          nullable: true
+                      - nullable: true
+                        title: "null"
+                    description: Log probability information for the prompt.
+                  usage:
+                    type: object
+                    properties:
+                      completion_tokens:
+                        type: integer
+                        description: The number of tokens in the completion.
+                        example: 20
+                      prompt_tokens:
+                        type: integer
+                        description: The number of tokens in the prompt.
+                        example: 10
+                      prompt_tokens_details:
+                        type: object
+                        nullable: true
+                        properties: {}
+                        description: Breakdown of tokens used in the prompt. Not presently used by
+                          Venice.
+                      total_tokens:
+                        type: integer
+                        description: The total number of tokens used in the request.
+                        example: 30
+                    required:
+                      - completion_tokens
+                      - prompt_tokens
+                      - total_tokens
+                  venice_parameters:
+                    type: object
+                    properties:
+                      enable_web_search:
+                        type: string
+                        enum:
+                          - auto
+                          - off
+                          - on
+                        description: Did the request enable web search?
+                        example: auto
+                      enable_web_citations:
+                        type: boolean
+                        description: Did the request enable web citations?
+                        example: true
+                      include_venice_system_prompt:
+                        type: boolean
+                        description: Did the request include the Venice system prompt?
+                        example: true
+                      include_search_results_in_stream:
+                        type: boolean
+                        description: Did the request include search results in the stream?
+                        example: false
+                      character_slug:
+                        type: string
+                        description: The character slug of a public Venice character.
+                        example: venice
+                      strip_thinking_response:
+                        type: boolean
+                        description: Did the request strip thinking response?
+                        example: true
+                      disable_thinking:
+                        type: boolean
+                        description: Did the request disable thinking?
+                        example: true
+                      web_search_citations:
+                        type: array
+                        items:
+                          type: object
+                          properties:
+                            content:
+                              type: string
+                            date:
+                              type: string
+                            title:
+                              type: string
+                            url:
+                              type: string
+                          required:
+                            - title
+                            - url
+                        description: Citations from web search results.
+                        example:
+                          - content: >-
+                              What&#x27;s the scientific reason behind
+                              Earth&#x27;s sky appearing blue to the human eye?
+                              And what&#x27;s the real colour of the sky?
+
+
+                              Save 30% on the shop price when you subscribe to
+                              BBC Sky at Night Magazine today!
+
+
+                              In this article we'll look at the science behind
+                              why the sky is blue, or at least why it appears
+                              blue to our eyes.
+
+
+                              A beautiful blue sky is the sign of a pleasant day
+                              ahead. But what makes the sky appear blue?
+
+
+                              So, the sky appears blue because the molecules of
+                              nitrogen and oxygen in the atmosphere scatter
+                              light in short wavelengths towards the blue end of
+                              the visible spectrum.
+                            date: 2024-08-13T13:45:16
+                            title: Why is the sky blue? | BBC Sky at Night Magazine
+                            url: https://www.skyatnightmagazine.com/space-science/why-is-the-sky-blue
+                          - content: >-
+                              It was around 1870 when the British physicist John
+                              William Strutt, better known as Lord Rayleigh,
+                              first found an explanation for why the sky is
+                              blue: Blue light from the Sun is scattered the
+                              most when it passes through the atmosphere.
+
+
+                              Published: January 20, 2025 8:34am EST · Daniel
+                              Freedman, University of Wisconsin-Stout · Daniel
+                              Freedman · Dean of the College of Science,
+                              Technology, Engineering, Mathematics & Management,
+                              University of Wisconsin-Stout ·
+
+
+                              The answer has to do with molecules.
+
+
+                              It was around 1870 when the British physicist John
+                              William Strutt, better known as Lord Rayleigh,
+                              first found an explanation for why the sky is
+                              blue: Blue light from the Sun is scattered the
+                              most when it passes through the atmosphere.
+
+
+                              When the Sun is near the horizon, its light passes
+                              through a lot more of the atmosphere to reach the
+                              Earth’s surface than when it is directly overhead.
+                              The blue and green light is scattered so well that
+                              you can hardly see it. The sky is colored,
+                              instead, with red and orange light.
+                            date: 2025-04-16T16:55:11
+                            title: Why is the sky blue?
+                            url: https://theconversation.com/why-is-the-sky-blue-246393
+                    required:
+                      - enable_web_search
+                      - enable_web_citations
+                      - include_venice_system_prompt
+                      - include_search_results_in_stream
+                      - strip_thinking_response
+                      - disable_thinking
+                    description: Unique parameters to Venice's API implementation.
+                required:
+                  - choices
+                  - created
+                  - id
+                  - model
+                  - object
+                  - usage
+                example:
+                  choices:
+                    - finish_reason: stop
+                      index: 0
+                      logprobs: null
+                      message:
+                        content: The sky appears blue because of the way Earth's atmosphere scatters
+                          sunlight. When sunlight reaches Earth's atmosphere, it
+                          is made up of various colors of the spectrum, but blue
+                          light waves are shorter and scatter more easily when
+                          they hit the gases and particles in the atmosphere.
+                          This scattering occurs in all directions, but from our
+                          perspective on the ground, it appears as a blue hue
+                          that dominates the sky's color. This phenomenon is
+                          known as Rayleigh scattering. During sunrise and
+                          sunset, the sunlight has to travel further through the
+                          atmosphere, which allows more time for the blue light
+                          to scatter away from our direct line of sight, leaving
+                          the longer wavelengths, such as red, yellow, and
+                          orange, to dominate the sky's color.
+                        reasoning_content: null
+                        role: assistant
+                        tool_calls: []
+                      stop_reason: null
+                  created: 1739928524
+                  id: chatcmpl-a81fbc2d81a7a083bb83ccf9f44c6e5e
+                  model: qwen-2.5-vl
+                  object: chat.completion
+                  prompt_logprobs: null
+                  usage:
+                    completion_tokens: 146
+                    prompt_tokens: 612
+                    prompt_tokens_details: null
+                    total_tokens: 758
+                  venice_parameters:
+                    include_venice_system_prompt: true
+                    include_search_results_in_stream: false
+                    web_search_citations: []
+                    enable_web_search: auto
+                    enable_web_citations: true
+                    strip_thinking_response: true
+                    disable_thinking: true
+                    character_slug: venice
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+        "504":
+          description: The request took too long to complete and was timed-out. For
+            long-running inference requests, use the streaming API by setting
+            stream=true in your request.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The request took too long to complete and was timed-out. For
+                      long-running inference requests, use the streaming API by
+                      setting stream=true in your request.
+                required:
+                  - error
+  /image/generate:
+    post:
+      description: Generate an image based on input parameters
+      operationId: generateImage
+      parameters:
+        - description: Supported compression encodings (gzip, br). Only applied when
+            return_binary is false.
+          in: header
+          name: Accept-Encoding
+          required: false
+          schema:
+            example: gzip, br
+            type: string
+      summary: /api/v1/image/generate
+      tags:
+        - Image
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/GenerateImageRequest"
+      responses:
+        "200":
+          description: Successfully generated image
+          headers:
+            Content-Encoding:
+              description: The encoding used to compress the response
+              schema:
+                enum:
+                  - gzip
+                  - br
+                type: string
+            x-venice-is-blurred:
+              description: Indicates if the generated image is blurred. When Safe Venice is
+                enabled, adult material will be returned blurred.
+              required: false
+              schema:
+                type: boolean
+            x-venice-is-content-violation:
+              description: Indicates if the generated image does not meet Venice terms of
+                service.
+              required: false
+              schema:
+                type: boolean
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  id:
+                    type: string
+                    description: The ID of the request.
+                    example: generate-image-1234567890
+                  images:
+                    type: array
+                    items:
+                      type: string
+                    description: Base64 encoded image data.
+                  request:
+                    nullable: true
+                    description: The original request data sent to the API.
+                  timing:
+                    type: object
+                    properties:
+                      inferenceDuration:
+                        type: number
+                        description: Duration of inference in milliseconds
+                      inferencePreprocessingTime:
+                        type: number
+                        description: Duration of preprocessing in milliseconds
+                      inferenceQueueTime:
+                        type: number
+                        description: Duration of queueing in milliseconds
+                      total:
+                        type: number
+                        description: Total duration of the request in milliseconds
+                    required:
+                      - inferenceDuration
+                      - inferencePreprocessingTime
+                      - inferenceQueueTime
+                      - total
+                required:
+                  - id
+                  - images
+                  - timing
+            image/jpeg:
+              schema:
+                description: Raw image data when return_binary is true and format is jpeg
+                format: binary
+                type: string
+            image/png:
+              schema:
+                description: Raw image data when return_binary is true and format is png
+                format: binary
+                type: string
+            image/webp:
+              schema:
+                description: Raw image data when return_binary is true and format is webp
+                format: binary
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /images/generations:
+    post:
+      description: Generate an image based on input parameters using an OpenAI
+        compatible endpoint. This endpoint does not support the full feature set
+        of the Venice Image Generation endpoint, but is compatible with the
+        existing OpenAI endpoint.
+      operationId: simpleGenerateImage
+      parameters:
+        - description: Supported compression encodings (gzip, br).
+          in: header
+          name: Accept-Encoding
+          required: false
+          schema:
+            example: gzip, br
+            type: string
+      summary: /api/v1/image/generations
+      tags:
+        - Image
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/SimpleGenerateImageRequest"
+      responses:
+        "200":
+          description: Successfully generated image
+          headers:
+            Content-Encoding:
+              description: The encoding used to compress the response
+              schema:
+                enum:
+                  - gzip
+                  - br
+                type: string
+            x-venice-is-blurred:
+              description: Indicates if the generated image is blurred. When Safe Venice is
+                enabled, adult material will be returned blurred.
+              required: false
+              schema:
+                type: boolean
+            x-venice-is-content-violation:
+              description: Indicates if the generated image does not meet Venice terms of
+                service.
+              required: false
+              schema:
+                type: boolean
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  created:
+                    type: integer
+                    description: Unix timestamp for when the request was created
+                    example: 1713833628
+                  data:
+                    type: array
+                    items:
+                      anyOf:
+                        - type: object
+                          properties:
+                            b64_json:
+                              type: string
+                              description: Base64-encoded JSON string of the generated image
+                              example: iVBORw0KGgoAAAANSUhEUgAA...
+                          required:
+                            - b64_json
+                        - type: object
+                          properties:
+                            url:
+                              type: string
+                              description: Data URL of the generated image
+                              example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...
+                          required:
+                            - url
+                required:
+                  - created
+                  - data
+                additionalProperties: false
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /image/styles:
+    get:
+      description: List available image styles that can be used with the generate API.
+      security:
+        - {}
+        - BearerAuth: []
+      summary: /api/v1/image/styles
+      tags:
+        - Image
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: string
+                    description: List of available image styles
+                    example:
+                      - 3D Model
+                      - Analog Film
+                      - Anime
+                      - Cinematic
+                      - Comic Book
+                  object:
+                    type: string
+                    enum:
+                      - list
+                required:
+                  - data
+                  - object
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /image/upscale:
+    post:
+      description: Upscale or enhance an image based on the supplied parameters. Using
+        a scale of 1 with enhance enabled will only run the enhancer. The image
+        can be provided either as a multipart form-data file upload or as a
+        base64-encoded string in a JSON request.
+      operationId: upscaleImage
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/UpscaleImageRequest"
+          multipart/form-data:
+            schema:
+              $ref: "#/components/schemas/UpscaleImageRequest"
+      summary: /api/v1/image/upscale
+      tags:
+        - Image
+      responses:
+        "200":
+          description: OK
+          content:
+            image/png:
+              schema:
+                format: binary
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /image/edit:
+    post:
+      description: Edit or modify an image based on the supplied prompt. The image can
+        be provided either as a multipart form-data file upload or as a
+        base64-encoded string in a JSON request.
+      operationId: editImage
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/EditImageRequest"
+          multipart/form-data:
+            schema:
+              $ref: "#/components/schemas/EditImageRequest"
+      summary: /api/v1/image/edit
+      tags:
+        - Image
+      responses:
+        "200":
+          description: OK
+          content:
+            image/png:
+              schema:
+                format: binary
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /models:
+    get:
+      description: Returns a list of available models supported by the Venice.ai API
+        for both text and image inference.
+      operationId: listModels
+      security:
+        - {}
+        - BearerAuth: []
+      summary: /api/v1/models
+      tags:
+        - Models
+      parameters:
+        - schema:
+            anyOf:
+              - type: string
+                enum:
+                  - embedding
+                  - image
+                  - text
+                  - tts
+                  - upscale
+                  - inpaint
+              - type: string
+                enum:
+                  - all
+                  - code
+            description: Filter models by type. Use "all" to get all model types.
+            example: text
+          required: false
+          name: type
+          in: query
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      $ref: "#/components/schemas/ModelResponse"
+                    description: List of available models
+                  object:
+                    type: string
+                    enum:
+                      - list
+                  type:
+                    anyOf:
+                      - type: string
+                        enum:
+                          - embedding
+                          - image
+                          - text
+                          - tts
+                          - upscale
+                          - inpaint
+                      - type: string
+                        enum:
+                          - all
+                          - code
+                    description: Type of models returned.
+                    example: text
+                required:
+                  - data
+                  - object
+                  - type
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /models/traits:
+    get:
+      description: Returns a list of model traits and the associated model.
+      operationId: listModelTraits
+      security:
+        - {}
+        - BearerAuth: []
+      summary: /api/v1/models/traits
+      tags:
+        - Models
+      parameters:
+        - schema:
+            type: string
+            enum:
+              - embedding
+              - image
+              - text
+              - tts
+              - upscale
+              - inpaint
+            default: text
+            description: Filter models by type.
+            example: text
+          required: false
+          name: type
+          in: query
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    $ref: "#/components/schemas/ModelTraitSchema"
+                  object:
+                    type: string
+                    enum:
+                      - list
+                  type:
+                    anyOf:
+                      - type: string
+                        enum:
+                          - embedding
+                          - image
+                          - text
+                          - tts
+                          - upscale
+                          - inpaint
+                      - type: string
+                        enum:
+                          - all
+                          - code
+                    description: Type of models returned.
+                    example: text
+                required:
+                  - data
+                  - object
+                  - type
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /models/compatibility_mapping:
+    get:
+      description: Returns a list of model compatibility mappings and the associated model.
+      operationId: listModelCompatibilityMapping
+      security:
+        - {}
+        - BearerAuth: []
+      summary: /api/v1/models/compatibility_mapping
+      tags:
+        - Models
+      parameters:
+        - schema:
+            type: string
+            enum:
+              - embedding
+              - image
+              - text
+              - tts
+              - upscale
+              - inpaint
+            default: text
+            description: Filter models by type.
+            example: text
+          required: false
+          name: type
+          in: query
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    $ref: "#/components/schemas/ModelCompatibilitySchema"
+                  object:
+                    type: string
+                    enum:
+                      - list
+                  type:
+                    anyOf:
+                      - type: string
+                        enum:
+                          - embedding
+                          - image
+                          - text
+                          - tts
+                          - upscale
+                          - inpaint
+                      - type: string
+                        enum:
+                          - all
+                          - code
+                    description: Type of models returned.
+                    example: text
+                required:
+                  - data
+                  - object
+                  - type
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /api_keys:
+    get:
+      description: Return a list of API keys.
+      operationId: getApiKeys
+      summary: /api/v1/api_keys
+      tags:
+        - API Keys
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        apiKeyType:
+                          type: string
+                          enum:
+                            - INFERENCE
+                            - ADMIN
+                          description: API Key type
+                          example: ADMIN
+                        consumptionLimits:
+                          type: object
+                          properties:
+                            usd:
+                              anyOf:
+                                - type: number
+                                  minimum: 0
+                                - nullable: true
+                                  title: "null"
+                                - nullable: true
+                                  title: "null"
+                              description: USD limit
+                              example: 50
+                            diem:
+                              anyOf:
+                                - type: number
+                                  minimum: 0
+                                - nullable: true
+                                  title: "null"
+                                - nullable: true
+                                  title: "null"
+                              description: Diem limit
+                              example: 10
+                            vcu:
+                              anyOf:
+                                - type: number
+                                  minimum: 0
+                                - nullable: true
+                                  title: "null"
+                                - nullable: true
+                                  title: "null"
+                              description: VCU limit (deprecated - use Diem instead)
+                              deprecated: true
+                              example: 100
+                          description: The API Key consumption limits for each epoch.
+                          example:
+                            usd: 50
+                            diem: 10
+                        createdAt:
+                          type: string
+                          nullable: true
+                          description: API Key creation date
+                          example: 2023-10-01T12:00:00Z
+                        description:
+                          type: string
+                          description: API Key description
+                          example: Example API Key
+                        expiresAt:
+                          type: string
+                          nullable: true
+                          description: API Key expiration date
+                          example: 2023-10-01T12:00:00Z
+                        id:
+                          type: string
+                          description: API Key ID
+                          example: e28e82dc-9df2-4b47-b726-d0a222ef2ab5
+                        last6Chars:
+                          type: string
+                          description: Last 6 characters of the API Key
+                          example: 2V2jNW
+                        lastUsedAt:
+                          type: string
+                          nullable: true
+                          description: API Key last used date
+                          example: 2023-10-01T12:00:00Z
+                        usage:
+                          type: object
+                          properties:
+                            trailingSevenDays:
+                              type: object
+                              properties:
+                                usd:
+                                  type: string
+                                  description: USD usage in the trailing 7 days
+                                  example: "10.2424"
+                                vcu:
+                                  type: string
+                                  description: VCU usage in the trailing 7 days (deprecated - use Diem instead)
+                                  deprecated: true
+                                  example: "42.2315"
+                                diem:
+                                  type: string
+                                  description: Diem usage in the trailing 7 days
+                                  example: "4.2231"
+                              required:
+                                - usd
+                                - vcu
+                                - diem
+                          required:
+                            - trailingSevenDays
+                      required:
+                        - apiKeyType
+                        - consumptionLimits
+                        - createdAt
+                        - expiresAt
+                        - id
+                        - last6Chars
+                        - lastUsedAt
+                      additionalProperties: false
+                    description: List of active API keys
+                  object:
+                    type: string
+                    enum:
+                      - list
+                required:
+                  - data
+                  - object
+                additionalProperties: false
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+    delete:
+      description: Delete an API key.
+      operationId: deleteApiKey
+      parameters:
+        - description: The ID of the API key to delete
+          in: query
+          name: id
+          required: false
+          schema:
+            type: string
+      summary: /api/v1/api_keys
+      tags:
+        - API Keys
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  success:
+                    type: boolean
+                required:
+                  - success
+                additionalProperties: false
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+    post:
+      description: Create a new API key.
+      operationId: createApiKey
+      summary: /api/v1/api_keys
+      tags:
+        - API Keys
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                apiKeyType:
+                  type: string
+                  enum:
+                    - INFERENCE
+                    - ADMIN
+                  description: The API Key type. Admin keys have full access to the API while
+                    inference keys are only able to call inference endpoints.
+                  example: ADMIN
+                consumptionLimit:
+                  type: object
+                  properties:
+                    usd:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: USD limit
+                      example: 50
+                    diem:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: Diem limit
+                      example: 10
+                    vcu:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: VCU limit (deprecated - use Diem instead)
+                      deprecated: true
+                      example: 100
+                  description: The API Key consumption limits for each epoch.
+                  example:
+                    usd: 50
+                    diem: 10
+                description:
+                  type: string
+                  description: The API Key description
+                  example: Example API Key
+                expiresAt:
+                  anyOf:
+                    - type: string
+                      enum:
+                        - ""
+                    - type: string
+                      pattern: ^\d{4}-\d{2}-\d{2}$
+                    - type: string
+                      pattern: ^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d{3})?Z$
+                  description: The API Key expiration date. If not provided, the key will not
+                    expire.
+                  example: 2023-10-01T12:00:00Z
+              required:
+                - apiKeyType
+                - description
+              additionalProperties: false
+              description: The request body for creating a new API key. API key creation is
+                rate limited to 20 requests per minute and a maximum of 500
+                active API keys per user. VCU is being deprecated in favor of
+                Diem. Please update your API calls to use Diem instead.
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: object
+                    properties:
+                      apiKey:
+                        type: string
+                        description: The API Key. This is only shown once, so make sure to save it
+                          somewhere safe.
+                      apiKeyType:
+                        type: string
+                        enum:
+                          - INFERENCE
+                          - ADMIN
+                        description: The API Key type
+                        example: ADMIN
+                      consumptionLimit:
+                        type: object
+                        properties:
+                          usd:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: USD limit
+                            example: 50
+                          diem:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: Diem limit
+                            example: 10
+                          vcu:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: VCU limit (deprecated - use Diem instead)
+                            deprecated: true
+                            example: 100
+                        description: The API Key consumption limits for each epoch.
+                        example:
+                          usd: 50
+                          diem: 10
+                      description:
+                        type: string
+                        description: The API Key description
+                        example: Example API Key
+                      expiresAt:
+                        type: string
+                        nullable: true
+                        description: The API Key expiration date
+                        example: 2023-10-01T12:00:00Z
+                      id:
+                        type: string
+                        description: The API Key ID
+                        example: e28e82dc-9df2-4b47-b726-d0a222ef2ab5
+                    required:
+                      - apiKey
+                      - apiKeyType
+                      - consumptionLimit
+                      - expiresAt
+                      - id
+                    additionalProperties: false
+                  success:
+                    type: boolean
+                required:
+                  - data
+                  - success
+                additionalProperties: false
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /api_keys/rate_limits:
+    get:
+      description: Return details about user balances and rate limits.
+      operationId: getApiKeyRateLimits
+      summary: /api/v1/api_keys/rate_limits
+      tags:
+        - API Keys
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: object
+                    properties:
+                      accessPermitted:
+                        type: boolean
+                        description: Does the API key have access to consume the inference APIs?
+                        example: true
+                      apiTier:
+                        type: object
+                        properties:
+                          id:
+                            type: string
+                            description: The ID of the API tier.
+                            example: paid
+                          isCharged:
+                            type: boolean
+                            description: Is the API key pay per use (in Diem or USD).
+                            example: true
+                        required:
+                          - id
+                          - isCharged
+                      balances:
+                        type: object
+                        properties:
+                          USD:
+                            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.
+                            example: 100.023
+                      keyExpiration:
+                        type: string
+                        nullable: true
+                        description: The timestamp the API key expires. If null, the key never expires.
+                        example: 2025-06-01T00:00:00Z
+                      nextEpochBegins:
+                        type: string
+                        description: The timestamp when the next epoch begins. This is relevant for rate
+                          limits that reset at the start of each epoch.
+                        example: 2025-05-07T00:00:00.000Z
+                      rateLimits:
+                        type: array
+                        items:
+                          type: object
+                          properties:
+                            apiModelId:
+                              type: string
+                              description: The ID of the API model.
+                              example: venice-uncensored
+                            rateLimits:
+                              type: array
+                              items:
+                                type: object
+                                properties:
+                                  amount:
+                                    type: number
+                                    description: The rate limit for the API model.
+                                    example: 100
+                                  type:
+                                    type: string
+                                    description: The time period for the rate limit. Can be Requests Per Minute
+                                      (RPM), Requests Per Day (RPD), or Tokens
+                                      Per Minute (TPM).
+                                    example: RPM
+                                required:
+                                  - amount
+                                  - type
+                          required:
+                            - rateLimits
+                    required:
+                      - accessPermitted
+                      - apiTier
+                      - balances
+                      - keyExpiration
+                      - nextEpochBegins
+                      - rateLimits
+                required:
+                  - data
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /api_keys/rate_limits/log:
+    get:
+      description: Returns the last 50 rate limits that the account exceeded.
+      operationId: getApiKeyRateLimitLogs
+      summary: /api/v1/api_keys/rate_limits/log
+      tags:
+        - API Keys
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        apiKeyId:
+                          type: string
+                          description: The ID of the API key that exceeded the limit.
+                        modelId:
+                          type: string
+                          default: venice-uncensored
+                          description: The ID of the model that was used when the rate limit was exceeded.
+                        rateLimitTier:
+                          type: string
+                          description: The API tier of the rate limit.
+                          example: paid
+                        rateLimitType:
+                          type: string
+                          description: The type of rate limit that was exceeded.
+                          example: RPM
+                        timestamp:
+                          type: string
+                          description: The timestamp when the rate limit was exceeded.
+                          example: 2023-10-01T12:00:00Z
+                      required:
+                        - apiKeyId
+                        - modelId
+                        - rateLimitTier
+                        - rateLimitType
+                        - timestamp
+                      additionalProperties: false
+                    description: The last 50 rate limit logs for the account.
+                  object:
+                    type: string
+                    enum:
+                      - list
+                required:
+                  - data
+                  - object
+                additionalProperties: false
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /api_keys/generate_web3_key:
+    get:
+      description: Returns the token required to generate an API key via a wallet.
+      operationId: getApiKeyGenerateWeb3Key
+      security: []
+      summary: /api/v1/api_keys/generate_web3_key
+      tags:
+        - API Keys
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: object
+                    properties:
+                      token:
+                        type: string
+                        description: The token to sign with the wallet
+                        example: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6IkpvaG4gRG9lIiwiaWF0IjoxNTE2MjM5MDIyfQ.SflKxwRJSMeKKF2QT4fwpMeJf36POk6yJV_adQssw5c
+                    required:
+                      - token
+                  success:
+                    type: boolean
+                required:
+                  - data
+                  - success
+    post:
+      description: Authenticates a wallet holding sVVV and creates an API key.
+      operationId: postApiKeyGenerateWeb3Key
+      security: []
+      summary: /api/v1/api_keys/generate_web3_key
+      tags:
+        - API Keys
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                apiKeyType:
+                  type: string
+                  enum:
+                    - INFERENCE
+                    - ADMIN
+                  description: The API Key type. Admin keys have full access to the API while
+                    inference keys are only able to call inference endpoints.
+                  example: ADMIN
+                consumptionLimit:
+                  type: object
+                  properties:
+                    usd:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: USD limit
+                      example: 50
+                    diem:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: Diem limit
+                      example: 10
+                    vcu:
+                      anyOf:
+                        - type: number
+                          minimum: 0
+                        - nullable: true
+                          title: "null"
+                        - nullable: true
+                          title: "null"
+                      description: VCU limit (deprecated - use Diem instead)
+                      deprecated: true
+                      example: 100
+                  description: The API Key consumption limits for each epoch.
+                  example:
+                    usd: 50
+                    diem: 10
+                description:
+                  type: string
+                  default: Web3 API Key
+                  description: The API Key description
+                  example: Web3 API Key
+                expiresAt:
+                  anyOf:
+                    - type: string
+                      enum:
+                        - ""
+                    - type: string
+                      pattern: ^\d{4}-\d{2}-\d{2}$
+                    - type: string
+                      pattern: ^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d{3})?Z$
+                  description: The API Key expiration date. If not provided, the key will not
+                    expire.
+                  example: 2023-10-01T12:00:00Z
+                address:
+                  type: string
+                  description: The wallet's address
+                  example: "0x45B73055F3aDcC4577Bb709db10B19d11b5c94eE"
+                signature:
+                  type: string
+                  description: The token, signed with the wallet's private key
+                  example: "0xbb5ff2e177f3a97fa553057864ad892eb64120f3eaf9356b4742a10f9a068d42725\
+                    de895b5e45160b679cbe6961dc4cb552ba10dc97bdd8258d9154810785c\
+                    451c"
+                token:
+                  type: string
+                  description: The token obtained from
+                    https://api.venice.ai/api/v1/api_keys/generate_web3_key
+                  example: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6IkpvaG4gRG9lIiwiaWF0IjoxNTE2MjM5MDIyfQ.SflKxwRJSMeKKF2QT4fwpMeJf36POk6yJV_adQssw5c
+              required:
+                - apiKeyType
+                - address
+                - signature
+                - token
+              additionalProperties: false
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: object
+                    properties:
+                      apiKey:
+                        type: string
+                        description: The API Key. This is only shown once, so make sure to save it
+                          somewhere safe.
+                      apiKeyType:
+                        type: string
+                        enum:
+                          - INFERENCE
+                          - ADMIN
+                        description: The API Key type
+                        example: ADMIN
+                      consumptionLimit:
+                        type: object
+                        properties:
+                          usd:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: USD limit
+                            example: 50
+                          diem:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: Diem limit
+                            example: 10
+                          vcu:
+                            anyOf:
+                              - type: number
+                                minimum: 0
+                              - nullable: true
+                                title: "null"
+                              - nullable: true
+                                title: "null"
+                            description: VCU limit (deprecated - use Diem instead)
+                            deprecated: true
+                            example: 100
+                        description: The API Key consumption limits for each epoch.
+                        example:
+                          usd: 50
+                          diem: 10
+                      description:
+                        type: string
+                        description: The API Key description
+                        example: Example API Key
+                      expiresAt:
+                        type: string
+                        nullable: true
+                        description: The API Key expiration date
+                        example: 2023-10-01T12:00:00Z
+                      id:
+                        type: string
+                        description: The API Key ID
+                        example: e28e82dc-9df2-4b47-b726-d0a222ef2ab5
+                    required:
+                      - apiKey
+                      - apiKeyType
+                      - consumptionLimit
+                      - expiresAt
+                      - id
+                    additionalProperties: false
+                  success:
+                    type: boolean
+                required:
+                  - data
+                  - success
+                additionalProperties: false
+  /characters:
+    get:
+      description: This is a preview API and may change. Returns a list of characters
+        supported in the API.
+      operationId: listCharacters
+      summary: /api/v1/characters
+      tags:
+        - Characters
+        - Preview
+      responses:
+        "200":
+          description: OK
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        adult:
+                          type: boolean
+                          description: Whether the character is considered adult content
+                          example: false
+                        createdAt:
+                          type: string
+                          description: Date when the character was created
+                          example: 2024-12-20T21:28:08.934Z
+                        description:
+                          type: string
+                          nullable: true
+                          description: Description of the character
+                          example: Alan Watts (6 January 1915 – 16 November 1973) was a British and
+                            American writer, speaker, and self-styled
+                            "philosophical entertainer", known for interpreting
+                            and popularizing Buddhist, Taoist, and Hindu
+                            philosophy for a Western audience.
+                        name:
+                          type: string
+                          description: Name of the character
+                          example: Alan Watts
+                        shareUrl:
+                          type: string
+                          nullable: true
+                          description: Share URL of the character
+                          example: https://venice.ai/c/alan-watts
+                        slug:
+                          type: string
+                          description: Slug of the character to be used in the completions API
+                          example: alan-watts
+                        stats:
+                          type: object
+                          properties:
+                            imports:
+                              type: number
+                              description: Number of imports for the character
+                              example: 112
+                          required:
+                            - imports
+                        tags:
+                          type: array
+                          items:
+                            type: string
+                          description: Tags associated with the character
+                          example:
+                            - AlanWatts
+                            - Philosophy
+                            - Buddhism
+                            - Taoist
+                            - Hindu
+                        updatedAt:
+                          type: string
+                          description: Date when the character was last updated
+                          example: 2025-02-09T03:23:53.708Z
+                        webEnabled:
+                          type: boolean
+                          description: Whether the character is enabled for web use
+                          example: true
+                      required:
+                        - adult
+                        - createdAt
+                        - description
+                        - name
+                        - shareUrl
+                        - slug
+                        - stats
+                        - tags
+                        - updatedAt
+                        - webEnabled
+                  object:
+                    type: string
+                    enum:
+                      - list
+                required:
+                  - data
+                  - object
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: An unknown error occurred
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: An unknown error occurred
+                required:
+                  - error
+  /embeddings:
+    post:
+      description: Create embeddings for the supplied input.
+      operationId: createEmbedding
+      parameters:
+        - description: Supported compression encodings (gzip, br)
+          in: header
+          name: Accept-Encoding
+          required: false
+          schema:
+            example: gzip, br
+            type: string
+      summary: /api/v1/embeddings
+      tags:
+        - Embeddings
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/CreateEmbeddingRequestSchema"
+      responses:
+        "200":
+          description: OK
+          headers:
+            Content-Encoding:
+              description: The encoding used to compress the response
+              schema:
+                enum:
+                  - gzip
+                  - br
+                type: string
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        embedding:
+                          type: array
+                          items:
+                            type: number
+                          description: The embedding vector
+                        index:
+                          type: integer
+                          description: The index of this embedding in the list
+                        object:
+                          type: string
+                          enum:
+                            - embedding
+                          description: The object type, which is always "embedding"
+                      required:
+                        - embedding
+                        - index
+                        - object
+                    description: The list of embeddings generated by the model.
+                  model:
+                    type: string
+                    description: The name of the model used to generate the embedding.
+                  object:
+                    type: string
+                    enum:
+                      - list
+                    description: The object type, which is always "list"
+                  usage:
+                    type: object
+                    properties:
+                      prompt_tokens:
+                        type: integer
+                        description: The number of tokens used by the prompt.
+                      total_tokens:
+                        type: integer
+                        description: The total number of tokens used by the request.
+                    required:
+                      - prompt_tokens
+                      - total_tokens
+                    description: The usage information for the request.
+                required:
+                  - data
+                  - model
+                  - object
+                  - usage
+                example:
+                  data:
+                    - embedding:
+                        - 0.0023064255
+                        - -0.009327292
+                        - 0.015797377
+                      index: 0
+                      object: embedding
+                  model: text-embedding-bge-m3
+                  object: list
+                  usage:
+                    prompt_tokens: 8
+                    total_tokens: 8
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /audio/speech:
+    post:
+      description: Converts text to speech using various voice models and formats.
+      operationId: createSpeech
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/CreateSpeechRequestSchema"
+      summary: /api/v1/audio/speech
+      tags:
+        - Audio
+        - Speech
+      responses:
+        "200":
+          description: Audio content generated successfully
+          content:
+            audio/aac:
+              schema:
+                format: binary
+                type: string
+            audio/flac:
+              schema:
+                format: binary
+                type: string
+            audio/mpeg:
+              schema:
+                format: binary
+                type: string
+            audio/opus:
+              schema:
+                format: binary
+                type: string
+            audio/pcm:
+              schema:
+                format: binary
+                type: string
+            audio/wav:
+              schema:
+                format: binary
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "402":
+          description: Insufficient USD or Diem balance to complete request
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Insufficient USD or Diem balance to complete request
+                required:
+                  - error
+        "403":
+          description: Unauthorized access
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Unauthorized access
+                required:
+                  - error
+        "415":
+          description: Invalid request content-type
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request content-type
+                required:
+                  - error
+        "429":
+          description: Rate limit exceeded
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Rate limit exceeded
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error
+        "503":
+          description: The model is at capacity. Please try again later.
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: The model is at capacity. Please try again later.
+                required:
+                  - error
+  /billing/usage:
+    get:
+      description: "Get paginated billing usage data for the authenticated user. NOTE:
+        This is a beta endpoint and may be subject to change."
+      operationId: getBillingUsage
+      parameters:
+        - description: Accept header to specify the response format
+          in: header
+          name: Accept
+          schema:
+            example: application/json, text/csv
+            type: string
+        - schema:
+            type: string
+            description: Filter by currency
+            enum:
+              - USD
+              - VCU
+              - DIEM
+            example: USD
+          required: false
+          name: currency
+          in: query
+        - schema:
+            type: string
+            format: date-time
+            description: End date for filtering records (ISO 8601)
+            example: 2024-12-31T23:59:59Z
+          required: false
+          name: endDate
+          in: query
+        - schema:
+            type: integer
+            minimum: 0
+            exclusiveMinimum: true
+            maximum: 500
+            default: 200
+            description: Number of items per page
+            example: 200
+          required: false
+          name: limit
+          in: query
+        - schema:
+            type: integer
+            minimum: 0
+            exclusiveMinimum: true
+            default: 1
+            description: Page number for pagination
+            example: 1
+          required: false
+          name: page
+          in: query
+        - schema:
+            type: string
+            enum:
+              - asc
+              - desc
+            default: desc
+            description: Sort order for createdAt field
+            example: desc
+          required: false
+          name: sortOrder
+          in: query
+        - schema:
+            type: string
+            format: date-time
+            description: Start date for filtering records (ISO 8601)
+            example: 2024-01-01T00:00:00Z
+          required: false
+          name: startDate
+          in: query
+      summary: /api/v1/billing/usage
+      tags:
+        - Billing
+      responses:
+        "200":
+          description: Successful response
+          headers:
+            Content-Disposition:
+              schema:
+                description: attachment; filename=billing_usage.csv
+                example: attachment; filename=billing_usage.csv
+                type: string
+            x-pagination-limit:
+              schema:
+                description: Number of items per page
+                example: 200
+                type: number
+            x-pagination-page:
+              schema:
+                description: Current page number
+                example: 1
+                type: number
+            x-pagination-total:
+              schema:
+                description: Total number of items
+                example: 1000
+                type: number
+            x-pagination-total-pages:
+              schema:
+                description: Total number of pages
+                example: 5
+                type: number
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  data:
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        amount:
+                          type: number
+                          description: The total amount charged for the billing usage entry
+                        currency:
+                          type: string
+                          enum:
+                            - USD
+                            - VCU
+                            - DIEM
+                          description: The currency charged for the billing usage entry
+                          example: USD
+                        inferenceDetails:
+                          type: object
+                          nullable: true
+                          properties:
+                            completionTokens:
+                              type: number
+                              nullable: true
+                              description: Number of tokens used in the completion. Only present for LLM
+                                usage.
+                            inferenceExecutionTime:
+                              type: number
+                              nullable: true
+                              description: Time taken for inference execution in milliseconds
+                            promptTokens:
+                              type: number
+                              nullable: true
+                              description: Number of tokens requested in the prompt. Only present for LLM
+                                usage.
+                            requestId:
+                              type: string
+                              nullable: true
+                              description: Unique identifier for the inference request
+                          required:
+                            - completionTokens
+                            - inferenceExecutionTime
+                            - promptTokens
+                            - requestId
+                          description: Details about the related inference request, if applicable
+                        notes:
+                          type: string
+                          description: Notes about the billing usage entry
+                        pricePerUnitUsd:
+                          type: number
+                          description: The price per unit in USD
+                        sku:
+                          type: string
+                          description: The product associated with the billing usage entry
+                        timestamp:
+                          type: string
+                          description: The timestamp the billing usage entry was created
+                          example: 2025-01-01T00:00:00Z
+                        units:
+                          type: number
+                          description: The number of units consumed
+                      required:
+                        - amount
+                        - currency
+                        - inferenceDetails
+                        - notes
+                        - pricePerUnitUsd
+                        - sku
+                        - timestamp
+                        - units
+                  pagination:
+                    type: object
+                    properties:
+                      limit:
+                        type: number
+                      page:
+                        type: number
+                      total:
+                        type: number
+                      totalPages:
+                        type: number
+                    required:
+                      - limit
+                      - page
+                      - total
+                      - totalPages
+                required:
+                  - data
+                  - pagination
+                additionalProperties: false
+                description: The response schema for the billing usage endpoint
+                example:
+                  data:
+                    - amount: -0.1
+                      currency: DIEM
+                      inferenceDetails: null
+                      notes: API Inference
+                      pricePerUnitUsd: 0.1
+                      sku: venice-sd35-image-unit
+                      timestamp: {}
+                      units: 1
+                    - amount: -0.06356
+                      currency: DIEM
+                      inferenceDetails:
+                        completionTokens: 227
+                        inferenceExecutionTime: 2964
+                        promptTokens: 339
+                        requestId: chatcmpl-4007fd29f42b7d3c4107f4345e8d174a
+                      notes: API Inference
+                      pricePerUnitUsd: 2.8
+                      sku: llama-3.3-70b-llm-output-mtoken
+                      timestamp: {}
+                      units: 0.000227
+                  pagination:
+                    limit: 1
+                    page: 200
+                    total: 56090
+                    totalPages: 56090
+            text/csv:
+              schema:
+                description: CSV formatted billing usage data
+                type: string
+        "400":
+          description: Invalid request parameters
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  details:
+                    type: object
+                    properties: {}
+                    description: Details about the incorrect input
+                    example:
+                      _errors: []
+                      field:
+                        _errors:
+                          - Field is required
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Invalid request parameters
+                required:
+                  - error
+        "401":
+          description: Authentication failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Authentication failed
+                required:
+                  - error
+        "500":
+          description: Inference processing failed
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  error:
+                    type: string
+                    description: A description of the error
+                    example: Inference processing failed
+                required:
+                  - error