venice_client 1.0.20 → 1.0.22

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0e0c6512c72c7b06cbd4e3ce558c715ac5f4f64401fc47fa8f3e0d47563737f9
-  data.tar.gz: 012b71ad8777c5a24e5d21ce36d1388e37076e99ccf99b85d4a6b08883a1319a
+  metadata.gz: 9a4a08bfc501e7685dbe04817ff8ee43adb27a84d7a7bfe844c8b9dc43500229
+  data.tar.gz: 61cfe77caac8fe710f36dae62d9fd04bf5534533876087d52156b71a6f80dd81
 SHA512:
-  metadata.gz: d2d22c8b1c9c4e7674d692eed6fa4a0d943b69d6fd37df6aed5588135443317fcaa329c2a8464b17ed3aa79dee93000d3ba978e2204e5d54c3a4a0469db16709
-  data.tar.gz: fbb5a5f56a924c57c39be06c38158d0e90af6cc497d3f9a7421d0e5b671eee60ab8e17a8955316588136242e9f539b05536547104af2a8578c394aa4ecedf414
+  metadata.gz: 9b6f592470f5a2daacad6aca8fc1339e5d313aadf9d039ef1c93a540d8daa6ecdfc93e1cd6247a19e52860235ba8cf5efbd03579ad4673c897ad41cebd969fb7
+  data.tar.gz: 6d2332825b9670bf95dd38664e28ee3195c8c1c2805bd9876f785e3390325955df41213aa231a85ae742bc698fc96ff56e343a7f9bbea155675a3fb1d144a3c6

data/README.md

@@ -6,7 +6,7 @@ The Venice.ai API.
 
 This SDK is automatically generated by the [OpenAPI Generator](https://openapi-generator.tech) project:
 
-- API version: 20250918.173746
+- API version: 20251209.153516
 - Package version: 1.0.0
 - Generator version: 7.14.0
 - Build package: org.openapitools.codegen.languages.RubyClientCodegen
@@ -111,6 +111,10 @@ Class | Method | HTTP request | Description
 *VeniceClient::PreviewApi* | [**get_character_by_slug**](docs/PreviewApi.md#get_character_by_slug) | **GET** /characters/{slug} | /api/v1/characters/{slug}
 *VeniceClient::PreviewApi* | [**list_characters**](docs/PreviewApi.md#list_characters) | **GET** /characters | /api/v1/characters
 *VeniceClient::SpeechApi* | [**create_speech**](docs/SpeechApi.md#create_speech) | **POST** /audio/speech | /api/v1/audio/speech
+*VeniceClient::VideoApi* | [**complete_video**](docs/VideoApi.md#complete_video) | **POST** /video/complete | /api/v1/video/complete
+*VeniceClient::VideoApi* | [**queue_video**](docs/VideoApi.md#queue_video) | **POST** /video/queue | /api/v1/video/queue
+*VeniceClient::VideoApi* | [**quote_video**](docs/VideoApi.md#quote_video) | **POST** /video/quote | /api/v1/video/quote
+*VeniceClient::VideoApi* | [**retrieve_video**](docs/VideoApi.md#retrieve_video) | **POST** /video/retrieve | /api/v1/video/retrieve
 
 
 ## Documentation for Models
@@ -121,8 +125,10 @@ Class | Method | HTTP request | Description
  - [VeniceClient::AudioModelPricingInput](docs/AudioModelPricingInput.md)
  - [VeniceClient::BillingUsageRequest](docs/BillingUsageRequest.md)
  - [VeniceClient::BillingUsageResponse](docs/BillingUsageResponse.md)
+ - [VeniceClient::CacheControl](docs/CacheControl.md)
  - [VeniceClient::ChatCompletionRequest](docs/ChatCompletionRequest.md)
  - [VeniceClient::ChatCompletionRequestMessagesInner](docs/ChatCompletionRequestMessagesInner.md)
+ - [VeniceClient::ChatCompletionRequestReasoning](docs/ChatCompletionRequestReasoning.md)
  - [VeniceClient::ChatCompletionRequestResponseFormat](docs/ChatCompletionRequestResponseFormat.md)
  - [VeniceClient::ChatCompletionRequestStop](docs/ChatCompletionRequestStop.md)
  - [VeniceClient::ChatCompletionRequestStreamOptions](docs/ChatCompletionRequestStreamOptions.md)
@@ -130,6 +136,8 @@ Class | Method | HTTP request | Description
  - [VeniceClient::ChatCompletionRequestToolChoiceAnyOf](docs/ChatCompletionRequestToolChoiceAnyOf.md)
  - [VeniceClient::ChatCompletionRequestToolChoiceAnyOfFunction](docs/ChatCompletionRequestToolChoiceAnyOfFunction.md)
  - [VeniceClient::ChatCompletionRequestVeniceParameters](docs/ChatCompletionRequestVeniceParameters.md)
+ - [VeniceClient::CompleteVideo200Response](docs/CompleteVideo200Response.md)
+ - [VeniceClient::CompleteVideoRequest](docs/CompleteVideoRequest.md)
  - [VeniceClient::CreateApiKey200Response](docs/CreateApiKey200Response.md)
  - [VeniceClient::CreateApiKey200ResponseData](docs/CreateApiKey200ResponseData.md)
  - [VeniceClient::CreateApiKeyRequest](docs/CreateApiKeyRequest.md)
@@ -208,6 +216,11 @@ Class | Method | HTTP request | Description
  - [VeniceClient::ModelResponseModelSpecPricing](docs/ModelResponseModelSpecPricing.md)
  - [VeniceClient::ObjectsInner](docs/ObjectsInner.md)
  - [VeniceClient::PostApiKeyGenerateWeb3KeyRequest](docs/PostApiKeyGenerateWeb3KeyRequest.md)
+ - [VeniceClient::QueueVideo200Response](docs/QueueVideo200Response.md)
+ - [VeniceClient::QueueVideoRequest](docs/QueueVideoRequest.md)
+ - [VeniceClient::QuoteVideo200Response](docs/QuoteVideo200Response.md)
+ - [VeniceClient::RetrieveVideo200Response](docs/RetrieveVideo200Response.md)
+ - [VeniceClient::RetrieveVideoRequest](docs/RetrieveVideoRequest.md)
  - [VeniceClient::SimpleGenerateImage200Response](docs/SimpleGenerateImage200Response.md)
  - [VeniceClient::SimpleGenerateImage200ResponseDataInner](docs/SimpleGenerateImage200ResponseDataInner.md)
  - [VeniceClient::SimpleGenerateImage200ResponseDataInnerAnyOf](docs/SimpleGenerateImage200ResponseDataInnerAnyOf.md)
@@ -227,6 +240,7 @@ Class | Method | HTTP request | Description
  - [VeniceClient::UpscaleImageRequestEnhance](docs/UpscaleImageRequestEnhance.md)
  - [VeniceClient::UserMessage](docs/UserMessage.md)
  - [VeniceClient::UserMessageContent](docs/UserMessageContent.md)
+ - [VeniceClient::VideoModelConstraints](docs/VideoModelConstraints.md)
 
 
 ## Documentation for Authorization

data/docs/AudioModelPricingInput.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost per million input characters |  |
-| **vcu** | **Float** | VCU cost per million input characters (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost per million input characters |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::AudioModelPricingInput.new(
   usd: 3.5,
-  vcu: 35,
   diem: 35
 )
 ```

data/docs/CacheControl.md

@@ -0,0 +1,20 @@
+# VeniceClient::CacheControl
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **ttl** | **String** | Optional TTL for extended cache duration. Beta feature requiring special header. | [optional] |
+| **type** | **String** | The type of cache control. Currently only \"ephemeral\" is supported. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::CacheControl.new(
+  ttl: 1h,
+  type: ephemeral
+)
+```
+

data/docs/ChatApi.md

@@ -29,7 +29,7 @@ end
 api_instance = VeniceClient::ChatApi.new
 opts = {
   accept_encoding: 'gzip, br', # String | Supported compression encodings (gzip, br). Only applied when stream is false.
-  chat_completion_request: VeniceClient::ChatCompletionRequest.new({messages: [VeniceClient::ChatCompletionRequestMessagesInner.new({content: VeniceClient::SystemMessageContent.new, role: 'system', tool_call_id: 'tool_call_id_example'})], model: 'venice-uncensored'}) # ChatCompletionRequest | 
+  chat_completion_request: VeniceClient::ChatCompletionRequest.new({messages: [VeniceClient::ChatCompletionRequestMessagesInner.new({content: VeniceClient::SystemMessageContent.new, role: 'system', tool_call_id: 'tool_call_id_example'})], model: 'zai-org-glm-4.6'}) # ChatCompletionRequest | 
 }
 
 begin

data/docs/ChatCompletionRequest.md

@@ -16,7 +16,10 @@
 | **model** | **String** | 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. |  |
 | **n** | **Integer** | 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. | [optional][default to 1] |
 | **presence_penalty** | **Float** | 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. | [optional][default to 0] |
+| **prompt_cache_key** | **String** | When supplied, this field may be used to optimize conversation routing to improve cache performance and thus reduce latency. | [optional] |
 | **repetition_penalty** | **Float** | The parameter for repetition penalty. 1.0 means no penalty. Values > 1.0 discourage repetition. | [optional] |
+| **reasoning** | [**ChatCompletionRequestReasoning**](ChatCompletionRequestReasoning.md) |  | [optional] |
+| **reasoning_effort** | **String** | OpenAI-compatible parameter to control reasoning effort level for supported models. Takes precedence over reasoning.effort if both are provided. | [optional] |
 | **seed** | **Integer** | The random seed used to generate the response. This is useful for reproducibility. | [optional] |
 | **stop** | [**ChatCompletionRequestStop**](ChatCompletionRequestStop.md) |  | [optional] |
 | **stop_token_ids** | **Array<Float>** | Array of token IDs where the API will stop generating further tokens. | [optional] |
@@ -47,10 +50,13 @@ instance = VeniceClient::ChatCompletionRequest.new(
   messages: null,
   min_p: 0.05,
   min_temp: 0.1,
-  model: venice-uncensored,
+  model: zai-org-glm-4.6,
   n: null,
   presence_penalty: null,
+  prompt_cache_key: random-string,
   repetition_penalty: 1.2,
+  reasoning: null,
+  reasoning_effort: medium,
   seed: 42,
   stop: null,
   stop_token_ids: [151643,151645],

data/docs/ChatCompletionRequestReasoning.md

@@ -0,0 +1,18 @@
+# VeniceClient::ChatCompletionRequestReasoning
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **effort** | **String** | Controls the reasoning effort level for supported models. Higher effort means more thorough reasoning but increased token usage. Defaults to the model configuration if not specified. | [optional] |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::ChatCompletionRequestReasoning.new(
+  effort: medium
+)
+```
+

data/docs/ChatCompletionRequestVeniceParameters.md

@@ -8,7 +8,8 @@
 | **strip_thinking_response** | **Boolean** | 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. | [optional][default to false] |
 | **disable_thinking** | **Boolean** | On supported reasoning models, will disable thinking and strip the <think></think> blocks from the response. Defaults to false. | [optional][default to false] |
 | **enable_web_search** | **String** | 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. | [optional][default to 'false'] |
-| **enable_web_citations** | **Boolean** | When web search is enabled, this will request that the LLM cite its sources using a [REF]0[/REF] format. Defaults to false. | [optional][default to false] |
+| **enable_web_scraping** | **Boolean** | Enable Venice web scraping of URLs in the latest user message using Firecrawl. Off by default. | [optional][default to false] |
+| **enable_web_citations** | **Boolean** | When web search is enabled, this will request that the LLM cite its sources using a ^index^ or ^i,j^ superscript format (e.g., ^1^). Defaults to false. | [optional][default to false] |
 | **include_search_results_in_stream** | **Boolean** | Experimental feature - When set to true, the LLM will include search results in the stream as the first emitted chunk. Defaults to false. | [optional][default to false] |
 | **return_search_results_as_documents** | **Boolean** | When set, search results are also surfaced in an OpenAI-compatible tool call named \"venice_web_search_documents\" to ease LangChain consumption. | [optional] |
 | **include_venice_system_prompt** | **Boolean** | Whether to include the Venice supplied system prompts along side specified system prompts. Defaults to true. | [optional][default to true] |
@@ -23,6 +24,7 @@ instance = VeniceClient::ChatCompletionRequestVeniceParameters.new(
   strip_thinking_response: false,
   disable_thinking: false,
   enable_web_search: false,
+  enable_web_scraping: false,
   enable_web_citations: null,
   include_search_results_in_stream: null,
   return_search_results_as_documents: null,

data/docs/CompleteVideo200Response.md

@@ -0,0 +1,18 @@
+# VeniceClient::CompleteVideo200Response
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **success** | **Boolean** | Indicates whether the video cleanup was successful. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::CompleteVideo200Response.new(
+  success: true
+)
+```
+

data/docs/CompleteVideoRequest.md

@@ -0,0 +1,20 @@
+# VeniceClient::CompleteVideoRequest
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **model** | **String** | The ID of the model used for video generation. |  |
+| **queue_id** | **String** | The ID of the video generation request. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::CompleteVideoRequest.new(
+  model: video-model-123,
+  queue_id: 123e4567-e89b-12d3-a456-426614174000
+)
+```
+

data/docs/CreateChatCompletion200Response.md

@@ -22,7 +22,7 @@ instance = VeniceClient::CreateChatCompletion200Response.new(
   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: 1677858240,
   id: chatcmpl-abc123,
-  model: venice-uncensored,
+  model: zai-org-glm-4.6,
   object: chat.completion,
   prompt_logprobs: null,
   usage: null,

data/docs/CreateChatCompletion200ResponseVeniceParameters.md

@@ -6,6 +6,7 @@
 | ---- | ---- | ----------- | ----- |
 | **enable_web_search** | **String** | Did the request enable web search? |  |
 | **enable_web_citations** | **Boolean** | Did the request enable web citations? |  |
+| **enable_web_scraping** | **Boolean** | Did the request enable web scraping of URLs via Firecrawl? |  |
 | **include_venice_system_prompt** | **Boolean** | Did the request include the Venice system prompt? |  |
 | **include_search_results_in_stream** | **Boolean** | Did the request include search results in the stream? |  |
 | **return_search_results_as_documents** | **Boolean** | Did the request also return search results as a tool-call documents block? |  |
@@ -22,6 +23,7 @@ require 'venice_client'
 instance = VeniceClient::CreateChatCompletion200ResponseVeniceParameters.new(
   enable_web_search: auto,
   enable_web_citations: true,
+  enable_web_scraping: false,
   include_venice_system_prompt: true,
   include_search_results_in_stream: false,
   return_search_results_as_documents: true,

data/docs/GenerateImageRequest.md

@@ -18,8 +18,11 @@
 | **variants** | **Integer** | Number of images to generate (1–4). Only supported when return_binary is false. | [optional] |
 | **safe_mode** | **Boolean** | Whether to use safe mode. If enabled, this will blur images that are classified as having adult content. | [optional][default to true] |
 | **seed** | **Integer** | Random seed for generation. If not provided, a random seed will be used. | [optional][default to 0] |
-| **steps** | **Integer** | Number of inference steps. The following models have reduced max steps from the global max: venice-sd35: 30 max steps, hidream: 50 max steps, flux.1-krea: 30 max steps, flux-dev: 30 max steps, flux-dev-uncensored: 30 max steps, lustify-sdxl: 50 max steps, lustify-v7: 25 max steps, pony-realism: 50 max steps, qwen-image: 8 max steps, stable-diffusion-3.5: 30 max steps, wai-Illustrious: 30 max steps. These constraints are exposed in the model list endpoint for each model. | [optional][default to 20] |
+| **steps** | **Integer** | Number of inference steps. This model does not support steps - this field is ignored. | [optional][default to 0] |
 | **style_preset** | **String** | An image style to apply to the image. Visit https://docs.venice.ai/api-reference/endpoint/image/styles for more details. | [optional] |
+| **aspect_ratio** | **String** | Aspect ratio (utilized by certain image models including Nano Banana). Examples: \"1:1\", \"16:9\". | [optional] |
+| **resolution** | **String** | Resolution (utilized by certain image models including Nano Banana). Examples: \"1024x1024\", \"512x512\". | [optional] |
+| **enable_web_search** | **Boolean** | Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image. Only supported by certain models. If web search is used, additional credits are getting charged. | [optional] |
 | **width** | **Integer** | Width of the generated image. Each model has a specific height and width divisor listed in the widthHeightDivisor constraint in the model list endpoint. | [optional][default to 1024] |
 
 ## Example
@@ -35,15 +38,18 @@ instance = VeniceClient::GenerateImageRequest.new(
   hide_watermark: false,
   inpaint: null,
   lora_strength: 50,
-  model: hidream,
+  model: z-image-turbo,
   negative_prompt: Clouds, Rain, Snow,
   prompt: A beautiful sunset over a mountain range,
   return_binary: false,
   variants: 3,
   safe_mode: false,
   seed: 123456789,
-  steps: 20,
+  steps: 0,
   style_preset: 3D Model,
+  aspect_ratio: 61,
+  resolution: 1024x1024,
+  enable_web_search: false,
   width: 1024
 )
 ```

data/docs/GetApiKeyRateLimitLogs200ResponseDataInner.md

@@ -5,7 +5,7 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **api_key_id** | **String** | The ID of the API key that exceeded the limit. |  |
-| **model_id** | **String** | The ID of the model that was used when the rate limit was exceeded. | [default to 'venice-uncensored'] |
+| **model_id** | **String** | The ID of the model that was used when the rate limit was exceeded. | [default to 'zai-org-glm-4.6'] |
 | **rate_limit_tier** | **String** | The API tier of the rate limit. |  |
 | **rate_limit_type** | **String** | The type of rate limit that was exceeded. |  |
 | **timestamp** | **String** | The timestamp when the rate limit was exceeded. |  |

data/docs/GetApiKeyRateLimits200Response.md

@@ -4,7 +4,6 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **warning_message** | **String** | A warning message to disambiguate staked DIEM balance from legacy DIEM (formerly VCU) balance | [optional] |
 | **data** | [**GetApiKeyRateLimits200ResponseData**](GetApiKeyRateLimits200ResponseData.md) |  |  |
 
 ## Example
@@ -13,7 +12,6 @@
 require 'venice_client'
 
 instance = VeniceClient::GetApiKeyRateLimits200Response.new(
-  warning_message: null,
   data: null
 )
 ```

data/docs/GetApiKeyRateLimits200ResponseDataBalances.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | The USD balance of the key. | [optional] |
-| **vcu** | **Float** | The VCU balance of the key. VCU is being deprecated in favor of Diem. | [optional] |
 | **diem** | **Float** | The Diem balance of the key. | [optional] |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::GetApiKeyRateLimits200ResponseDataBalances.new(
   usd: 50.23,
-  vcu: 100.023,
   diem: 100.023
 )
 ```

data/docs/GetApiKeyRateLimits200ResponseDataRateLimitsInner.md

@@ -13,7 +13,7 @@
 require 'venice_client'
 
 instance = VeniceClient::GetApiKeyRateLimits200ResponseDataRateLimitsInner.new(
-  api_model_id: venice-uncensored,
+  api_model_id: zai-org-glm-4.6,
   rate_limits: null
 )
 ```

data/docs/ImageApi.md

@@ -104,7 +104,7 @@ end
 api_instance = VeniceClient::ImageApi.new
 opts = {
   accept_encoding: 'gzip, br', # String | Supported compression encodings (gzip, br). Only applied when return_binary is false.
-  generate_image_request: VeniceClient::GenerateImageRequest.new({model: 'hidream', prompt: 'A beautiful sunset over a mountain range'}) # GenerateImageRequest | 
+  generate_image_request: VeniceClient::GenerateImageRequest.new({model: 'z-image-turbo', prompt: 'A beautiful sunset over a mountain range'}) # GenerateImageRequest | 
 }
 
 begin

data/docs/ImageModelPricingGeneration.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost per image generation |  |
-| **vcu** | **Float** | VCU cost per image generation (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost per image generation |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::ImageModelPricingGeneration.new(
   usd: 0.01,
-  vcu: 0.1,
   diem: 0.1
 )
 ```

data/docs/ImageModelPricingUpscale2x.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost for 2x upscale |  |
-| **vcu** | **Float** | VCU cost for 2x upscale (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost for 2x upscale |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::ImageModelPricingUpscale2x.new(
   usd: 0.02,
-  vcu: 0.2,
   diem: 0.2
 )
 ```

data/docs/ImageModelPricingUpscale4x.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost for 4x upscale |  |
-| **vcu** | **Float** | VCU cost for 4x upscale (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost for 4x upscale |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::ImageModelPricingUpscale4x.new(
   usd: 0.08,
-  vcu: 0.8,
   diem: 0.8
 )
 ```

data/docs/ImageUrl.md

@@ -4,6 +4,7 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
+| **cache_control** | [**CacheControl**](CacheControl.md) |  | [optional] |
 | **image_url** | [**ImageURLObject**](ImageURLObject.md) |  |  |
 | **type** | **String** |  |  |
 
@@ -13,6 +14,7 @@
 require 'venice_client'
 
 instance = VeniceClient::ImageUrl.new(
+  cache_control: null,
   image_url: null,
   type: null
 )

data/docs/LLMModelPricingInput.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost per million input tokens |  |
-| **vcu** | **Float** | VCU cost per million input tokens (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost per million input tokens |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::LLMModelPricingInput.new(
   usd: 0.7,
-  vcu: 7,
   diem: 7
 )
 ```

data/docs/LLMModelPricingOutput.md

@@ -5,7 +5,6 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **usd** | **Float** | USD cost per million output tokens |  |
-| **vcu** | **Float** | VCU cost per million output tokens (deprecated - use Diem instead) |  |
 | **diem** | **Float** | Diem cost per million output tokens |  |
 
 ## Example
@@ -15,7 +14,6 @@ require 'venice_client'
 
 instance = VeniceClient::LLMModelPricingOutput.new(
   usd: 2.8,
-  vcu: 28,
   diem: 28
 )
 ```

data/docs/ModelResponseModelSpec.md

@@ -6,6 +6,7 @@
 | ---- | ---- | ----------- | ----- |
 | **available_context_tokens** | **Float** | The context length supported by the model. Only applicable for text models. | [optional] |
 | **beta** | **Boolean** | Is this model in beta? | [optional] |
+| **privacy** | **String** | The privacy mode of the model. Private models have zero data retention. Anonymized models Venice can not guarantee privacy on, but requests are not affiliated with a user | [optional] |
 | **capabilities** | [**ModelResponseModelSpecCapabilities**](ModelResponseModelSpecCapabilities.md) |  | [optional] |
 | **constraints** | [**ModelResponseModelSpecConstraints**](ModelResponseModelSpecConstraints.md) |  | [optional] |
 | **name** | **String** | The name of the model. | [optional] |
@@ -23,6 +24,7 @@ require 'venice_client'
 instance = VeniceClient::ModelResponseModelSpec.new(
   available_context_tokens: 32768,
   beta: false,
+  privacy: private,
   capabilities: null,
   constraints: null,
   name: Venice Uncensored 1.1,

data/docs/ModelResponseModelSpecConstraints.md

@@ -9,6 +9,12 @@
 | **width_height_divisor** | **Float** | The requested width and height of the image generation must be divisible by this value. |  |
 | **temperature** | [**TextModelConstraintsTemperature**](TextModelConstraintsTemperature.md) |  |  |
 | **top_p** | [**TextModelConstraintsTopP**](TextModelConstraintsTopP.md) |  |  |
+| **aspect_ratios** | **Array<String>** | The aspect ratios supported by the model. Empty array means the model does not support a defined aspect ratio. |  |
+| **resolutions** | **Array<String>** | The resolutions supported by the model. Empty array means the model does not support a defined resolution. |  |
+| **durations** | **Array<String>** | The durations supported by the model. Empty array means the model does not support a defined duration. |  |
+| **model_type** | **String** | The type of video model. |  |
+| **audio** | **Boolean** | Does the model support audio generation? |  |
+| **audio_configurable** | **Boolean** | Can audio be enabled or disabled for the video generation? |  |
 
 ## Example
 
@@ -20,7 +26,13 @@ instance = VeniceClient::ModelResponseModelSpecConstraints.new(
   steps: null,
   width_height_divisor: 8,
   temperature: null,
-  top_p: null
+  top_p: null,
+  aspect_ratios: [969, 556],
+  resolutions: [1080p, 720p, 480p],
+  durations: [5s, 10s, 15s, 20s, 30s],
+  model_type: image-to-video,
+  audio: true,
+  audio_configurable: true
 )
 ```
 

data/docs/ModelsApi.md

@@ -30,7 +30,7 @@ end
 
 api_instance = VeniceClient::ModelsApi.new
 opts = {
-  type: 'embedding' # String | 
+  type: 'asr' # String | 
 }
 
 begin
@@ -101,7 +101,7 @@ end
 
 api_instance = VeniceClient::ModelsApi.new
 opts = {
-  type: 'embedding' # String | 
+  type: 'asr' # String | 
 }
 
 begin

data/docs/QueueVideo200Response.md

@@ -0,0 +1,20 @@
+# VeniceClient::QueueVideo200Response
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **model** | **String** | The ID of the model used for video generation. |  |
+| **queue_id** | **String** | The ID of the video generation request. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::QueueVideo200Response.new(
+  model: video-model-123,
+  queue_id: 123e4567-e89b-12d3-a456-426614174000
+)
+```
+

data/docs/QueueVideoRequest.md

@@ -0,0 +1,32 @@
+# VeniceClient::QueueVideoRequest
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **model** | **String** | The model to use for image generation. |  |
+| **prompt** | **String** | The prompt to use for video generation. The maximum length is 2500 characters. |  |
+| **negative_prompt** | **String** | The negative prompt to use for video generation. The maximum length is 2500 characters. | [optional][default to 'low resolution, error, worst quality, low quality, defects'] |
+| **duration** | **String** | The duration of the video to generate. |  |
+| **aspect_ratio** | **Object** | The aspect ratio of the video to generate. | [optional] |
+| **resolution** | **String** | The resolution of the video to generate. | [optional][default to '720p'] |
+| **audio** | **Object** | For models which support audio generation and configuration, indicates if audio should be generated. Defaults to true. | [optional] |
+| **image_url** | **String** | For image to video models, the reference image to use for video generation. Must be either a URL (starting with \"http://\" or \"https://\") or a data URL (starting with \"data:\"). |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::QueueVideoRequest.new(
+  model: wan-2.5-preview-image-to-video,
+  prompt: Commerce being conducted in the city of Venice, Italy.,
+  negative_prompt: low resolution, error, worst quality, low quality, defects,
+  duration: 5s,
+  aspect_ratio: 969,
+  resolution: 720p,
+  audio: true,
+  image_url: data:image/png;base64,iVBORw0K...
+)
+```
+

data/docs/QuoteVideo200Response.md

@@ -0,0 +1,18 @@
+# VeniceClient::QuoteVideo200Response
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **quote** | **Float** |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::QuoteVideo200Response.new(
+  quote: null
+)
+```
+

data/docs/RetrieveVideo200Response.md

@@ -0,0 +1,22 @@
+# VeniceClient::RetrieveVideo200Response
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **status** | **String** | The status of the video generation request. |  |
+| **average_execution_time** | **Float** | The average execution time of the video generation request in milliseconds. |  |
+| **execution_duration** | **Float** | The current duration of the video generation request in milliseconds. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::RetrieveVideo200Response.new(
+  status: PROCESSING,
+  average_execution_time: 145000,
+  execution_duration: 53200
+)
+```
+

data/docs/RetrieveVideoRequest.md

@@ -0,0 +1,22 @@
+# VeniceClient::RetrieveVideoRequest
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **model** | **String** | The ID of the model used for video generation. |  |
+| **queue_id** | **String** | The ID of the video generation request. |  |
+| **delete_media_on_completion** | **Boolean** | If true, the video media will be deleted from storage after the request is completed. If false, you can use the complete endpoint to remove the media once you have successfully downloaded the video. | [optional][default to false] |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::RetrieveVideoRequest.new(
+  model: video-model-123,
+  queue_id: 123e4567-e89b-12d3-a456-426614174000,
+  delete_media_on_completion: false
+)
+```
+