venice_client 1.0.23 → 1.0.25

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 40b365f471185fed66c7e1166e210433fd45033bc96a1d4b768d05799604a2ae
-  data.tar.gz: 2e423b5c204e079654dbbb1cd39e0414089e406415f709c163633224cee37224
+  metadata.gz: 264ea2bbc31ea7eb1c44aede57d37a613aeb2defab8cfffab368511acd6b1a4c
+  data.tar.gz: 61c42b0e6b7fb48c7512cb072922b695e488df69bb9aa434498708ece872ba7c
 SHA512:
-  metadata.gz: 70f8c36c77bf2bf4b417967aed60d9198886c994ff9957545c4761ebe7ff27249b0981d4acb680670336f13387c3d47b42d7aebabd1448687ac10ecf11348400
-  data.tar.gz: 2a088907b0ae32217b3e474593b99607d63beb47e107a0a523524717a345029d89d8dc1d5617e2ebf1c64b0e32cb6965ef21cc39bf37e75c5d30698b6e852f18
+  metadata.gz: 10426c948343fc2c899b33d8866b5a6147bf68374a1a26fef4c20ebcb07ef558eda8fe84e6902481a2121dd99dbda8c4bec3416b3a89dbaaf9eb54e43acdb270
+  data.tar.gz: c68b8a8396027e85a6b5b71e4a7fe9bc8f2e960db3f44a19d3ddd271ba6dbd0fdf0347950a17a5fcb19b0f94012c06034a371e3829ced4395f77e625d06d739d

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: 20251209.153516
+- API version: 20251218.042551
 - Package version: 1.0.0
 - Generator version: 7.14.0
 - Build package: org.openapitools.codegen.languages.RubyClientCodegen
@@ -121,11 +121,14 @@ Class | Method | HTTP request | Description
 
  - [VeniceClient::AssistantMessage](docs/AssistantMessage.md)
  - [VeniceClient::AssistantMessageContent](docs/AssistantMessageContent.md)
+ - [VeniceClient::AssistantMessageReasoningDetailsInner](docs/AssistantMessageReasoningDetailsInner.md)
  - [VeniceClient::AudioModelPricing](docs/AudioModelPricing.md)
  - [VeniceClient::AudioModelPricingInput](docs/AudioModelPricingInput.md)
  - [VeniceClient::BillingUsageRequest](docs/BillingUsageRequest.md)
  - [VeniceClient::BillingUsageResponse](docs/BillingUsageResponse.md)
  - [VeniceClient::CacheControl](docs/CacheControl.md)
+ - [VeniceClient::ChatCompletionContentPartInputAudio](docs/ChatCompletionContentPartInputAudio.md)
+ - [VeniceClient::ChatCompletionContentPartVideoUrl](docs/ChatCompletionContentPartVideoUrl.md)
  - [VeniceClient::ChatCompletionRequest](docs/ChatCompletionRequest.md)
  - [VeniceClient::ChatCompletionRequestMessagesInner](docs/ChatCompletionRequestMessagesInner.md)
  - [VeniceClient::ChatCompletionRequestReasoning](docs/ChatCompletionRequestReasoning.md)
@@ -196,6 +199,8 @@ Class | Method | HTTP request | Description
  - [VeniceClient::ImageStylesGet200Response](docs/ImageStylesGet200Response.md)
  - [VeniceClient::ImageURLObject](docs/ImageURLObject.md)
  - [VeniceClient::ImageUrl](docs/ImageUrl.md)
+ - [VeniceClient::InputAudio](docs/InputAudio.md)
+ - [VeniceClient::InputAudioObject](docs/InputAudioObject.md)
  - [VeniceClient::JsonObject](docs/JsonObject.md)
  - [VeniceClient::JsonSchema](docs/JsonSchema.md)
  - [VeniceClient::LLMModelPricing](docs/LLMModelPricing.md)
@@ -241,6 +246,8 @@ Class | Method | HTTP request | Description
  - [VeniceClient::UserMessage](docs/UserMessage.md)
  - [VeniceClient::UserMessageContent](docs/UserMessageContent.md)
  - [VeniceClient::VideoModelConstraints](docs/VideoModelConstraints.md)
+ - [VeniceClient::VideoURLObject](docs/VideoURLObject.md)
+ - [VeniceClient::VideoUrl](docs/VideoUrl.md)
 
 
 ## Documentation for Authorization

data/docs/AssistantMessage.md

@@ -7,6 +7,7 @@
 | **content** | [**AssistantMessageContent**](AssistantMessageContent.md) |  | [optional] |
 | **name** | **String** |  | [optional] |
 | **reasoning_content** | **String** |  | [optional] |
+| **reasoning_details** | [**Array<AssistantMessageReasoningDetailsInner>**](AssistantMessageReasoningDetailsInner.md) | Reasoning details returned by certain reasoning models that support this feature (e.g., Gemini 3 Pro). Not all reasoning models return this field. For multi-turn conversations with tool calls on supported models, pass back the reasoning_details exactly as received to preserve thought signatures. | [optional] |
 | **role** | **String** |  |  |
 | **tool_calls** | **Array<Object>** |  | [optional] |
 
@@ -19,6 +20,7 @@ instance = VeniceClient::AssistantMessage.new(
   content: null,
   name: null,
   reasoning_content: null,
+  reasoning_details: null,
   role: null,
   tool_calls: null
 )

data/docs/AssistantMessageReasoningDetailsInner.md

@@ -0,0 +1,28 @@
+# VeniceClient::AssistantMessageReasoningDetailsInner
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **data** | **String** |  | [optional] |
+| **format** | **String** |  | [optional] |
+| **id** | **String** |  | [optional] |
+| **index** | **Float** |  | [optional] |
+| **text** | **String** |  | [optional] |
+| **type** | **String** |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::AssistantMessageReasoningDetailsInner.new(
+  data: null,
+  format: null,
+  id: null,
+  index: null,
+  text: null,
+  type: null
+)
+```
+

data/docs/ChatApi.md

@@ -13,7 +13,7 @@ All URIs are relative to *https://api.venice.ai/api/v1*
 
 /api/v1/chat/completions
 
-Run text inference based on the supplied parameters. Long running requests should use the streaming API by setting stream=true in your request.
+Run text inference based on the supplied parameters. Supports multimodal inputs including text, images (image_url), audio (input_audio), and video (video_url) for compatible models. Long running requests should use the streaming API by setting stream=true in your request.
 
 ### Examples
 

data/docs/ChatCompletionContentPartInputAudio.md

@@ -0,0 +1,22 @@
+# VeniceClient::ChatCompletionContentPartInputAudio
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **cache_control** | [**CacheControl**](CacheControl.md) |  | [optional] |
+| **input_audio** | [**InputAudioObject**](InputAudioObject.md) |  |  |
+| **type** | **String** |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::ChatCompletionContentPartInputAudio.new(
+  cache_control: null,
+  input_audio: null,
+  type: null
+)
+```
+

data/docs/ChatCompletionContentPartVideoUrl.md

@@ -0,0 +1,22 @@
+# VeniceClient::ChatCompletionContentPartVideoUrl
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **cache_control** | [**CacheControl**](CacheControl.md) |  | [optional] |
+| **type** | **String** |  |  |
+| **video_url** | [**VideoURLObject**](VideoURLObject.md) |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::ChatCompletionContentPartVideoUrl.new(
+  cache_control: null,
+  type: null,
+  video_url: null
+)
+```
+

data/docs/ChatCompletionRequestMessagesInner.md

@@ -5,9 +5,10 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **content** | [**SystemMessageContent**](SystemMessageContent.md) |  |  |
-| **role** | **String** |  |  |
 | **name** | **String** |  | [optional] |
+| **role** | **String** |  |  |
 | **reasoning_content** | **String** |  | [optional] |
+| **reasoning_details** | [**Array<AssistantMessageReasoningDetailsInner>**](AssistantMessageReasoningDetailsInner.md) | Reasoning details returned by certain reasoning models that support this feature (e.g., Gemini 3 Pro). Not all reasoning models return this field. For multi-turn conversations with tool calls on supported models, pass back the reasoning_details exactly as received to preserve thought signatures. | [optional] |
 | **tool_calls** | **Array<Object>** |  | [optional] |
 | **tool_call_id** | **String** |  |  |
 
@@ -18,9 +19,10 @@ require 'venice_client'
 
 instance = VeniceClient::ChatCompletionRequestMessagesInner.new(
   content: null,
-  role: null,
   name: null,
+  role: null,
   reasoning_content: null,
+  reasoning_details: null,
   tool_calls: null,
   tool_call_id: null
 )

data/docs/CreateChatCompletion200Response.md

@@ -4,7 +4,7 @@
 
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
-| **choices** | [**Array<CreateChatCompletion200ResponseChoicesInner>**](CreateChatCompletion200ResponseChoicesInner.md) | A list of chat completion choices. Can be more than one if n is greater than 1. |  |
+| **choices** | [**Array<CreateChatCompletion200ResponseChoicesInner>**](CreateChatCompletion200ResponseChoicesInner.md) | A list of chat completion choices. Can be more than one if n is greater than 1. Certain models may not return this field under certain conditions. | [optional] |
 | **created** | **Integer** | The time at which the request was created. |  |
 | **id** | **String** | The ID of the request. |  |
 | **model** | **String** | The model id used for the request. |  |

data/docs/CreateChatCompletion200ResponseChoicesInnerMessage.md

@@ -7,6 +7,7 @@
 | **content** | **String** |  |  |
 | **name** | **String** |  | [optional] |
 | **reasoning_content** | **String** |  | [optional] |
+| **reasoning_details** | [**Array<AssistantMessageReasoningDetailsInner>**](AssistantMessageReasoningDetailsInner.md) | Reasoning details returned by certain reasoning models that support this feature (e.g., Gemini 3 Pro). Not all reasoning models return this field. For multi-turn conversations with tool calls on supported models, pass back the reasoning_details exactly as received to preserve thought signatures. | [optional] |
 | **role** | **String** |  |  |
 | **tool_calls** | **Array<Object>** |  | [optional] |
 | **tool_call_id** | **String** |  |  |
@@ -20,6 +21,7 @@ instance = VeniceClient::CreateChatCompletion200ResponseChoicesInnerMessage.new(
   content: null,
   name: null,
   reasoning_content: null,
+  reasoning_details: null,
   role: null,
   tool_calls: null,
   tool_call_id: null

data/docs/GenerateImageRequest.md

@@ -21,7 +21,7 @@
 | **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] |
+| **resolution** | **String** | Resolution (utilized by certain image models including Nano Banana). Examples: \"1K\", \"2K\", \"4K\". | [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] |
 
@@ -48,7 +48,7 @@ instance = VeniceClient::GenerateImageRequest.new(
   steps: 0,
   style_preset: 3D Model,
   aspect_ratio: 61,
-  resolution: 1024x1024,
+  resolution: 1K,
   enable_web_search: false,
   width: 1024
 )

data/docs/InputAudio.md

@@ -0,0 +1,22 @@
+# VeniceClient::InputAudio
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **cache_control** | [**CacheControl**](CacheControl.md) |  | [optional] |
+| **input_audio** | [**InputAudioObject**](InputAudioObject.md) |  |  |
+| **type** | **String** |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::InputAudio.new(
+  cache_control: null,
+  input_audio: null,
+  type: null
+)
+```
+

data/docs/InputAudioObject.md

@@ -0,0 +1,20 @@
+# VeniceClient::InputAudioObject
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **data** | **String** | Base64-encoded audio data. Direct URLs are not supported for audio content. |  |
+| **format** | **String** | The format of the audio file. Common formats include wav, mp3, aac, ogg, flac, m4a. Defaults to wav. | [optional][default to 'wav'] |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::InputAudioObject.new(
+  data: null,
+  format: wav
+)
+```
+

data/docs/ObjectsInner.md

@@ -15,7 +15,9 @@ VeniceClient::ObjectsInner.openapi_one_of
 # =>
 # [
 #   :'ImageUrl',
-#   :'Text'
+#   :'InputAudio',
+#   :'Text',
+#   :'VideoUrl'
 # ]
 ```
 
@@ -44,6 +46,8 @@ VeniceClient::ObjectsInner.build(data_that_doesnt_match)
 #### Return type
 
 - `ImageUrl`
+- `InputAudio`
 - `Text`
+- `VideoUrl`
 - `nil` (if no type matches)
 

data/docs/UserMessage.md

@@ -5,6 +5,7 @@
 | Name | Type | Description | Notes |
 | ---- | ---- | ----------- | ----- |
 | **content** | [**UserMessageContent**](UserMessageContent.md) |  |  |
+| **name** | **String** |  | [optional] |
 | **role** | **String** |  |  |
 
 ## Example
@@ -14,6 +15,7 @@ require 'venice_client'
 
 instance = VeniceClient::UserMessage.new(
   content: null,
+  name: null,
   role: null
 )
 ```

data/docs/VideoURLObject.md

@@ -0,0 +1,18 @@
+# VeniceClient::VideoURLObject
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **url** | **String** | The URL of the video. Can be a direct URL (including YouTube links for some providers), or a base64-encoded data URL (e.g., data:video/mp4;base64,...). Supported formats: mp4, mpeg, mov, webm. |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::VideoURLObject.new(
+  url: null
+)
+```
+

data/docs/VideoUrl.md

@@ -0,0 +1,22 @@
+# VeniceClient::VideoUrl
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **cache_control** | [**CacheControl**](CacheControl.md) |  | [optional] |
+| **type** | **String** |  |  |
+| **video_url** | [**VideoURLObject**](VideoURLObject.md) |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::VideoUrl.new(
+  cache_control: null,
+  type: null,
+  video_url: null
+)
+```
+

data/lib/venice_client/api/api_keys_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/audio_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/billing_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/characters_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/chat_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0
@@ -20,7 +20,7 @@ module VeniceClient
       @api_client = api_client
     end
     # /api/v1/chat/completions
-    # Run text inference based on the supplied parameters. Long running requests should use the streaming API by setting stream=true in your request.
+    # Run text inference based on the supplied parameters. Supports multimodal inputs including text, images (image_url), audio (input_audio), and video (video_url) for compatible models. Long running requests should use the streaming API by setting stream=true in your request.
     # @param [Hash] opts the optional parameters
     # @option opts [String] :accept_encoding Supported compression encodings (gzip, br). Only applied when stream is false.
     # @option opts [ChatCompletionRequest] :chat_completion_request 
@@ -31,7 +31,7 @@ module VeniceClient
     end
 
     # /api/v1/chat/completions
-    # Run text inference based on the supplied parameters. Long running requests should use the streaming API by setting stream=true in your request.
+    # Run text inference based on the supplied parameters. Supports multimodal inputs including text, images (image_url), audio (input_audio), and video (video_url) for compatible models. Long running requests should use the streaming API by setting stream=true in your request.
     # @param [Hash] opts the optional parameters
     # @option opts [String] :accept_encoding Supported compression encodings (gzip, br). Only applied when stream is false.
     # @option opts [ChatCompletionRequest] :chat_completion_request 

data/lib/venice_client/api/embeddings_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/image_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/models_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/preview_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/speech_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api/video_api.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api_client.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/api_error.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/configuration.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0

data/lib/venice_client/models/assistant_message.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0
@@ -22,6 +22,9 @@ module VeniceClient
 
     attr_accessor :reasoning_content
 
+    # Reasoning details returned by certain reasoning models that support this feature (e.g., Gemini 3 Pro). Not all reasoning models return this field. For multi-turn conversations with tool calls on supported models, pass back the reasoning_details exactly as received to preserve thought signatures.
+    attr_accessor :reasoning_details
+
     attr_accessor :role
 
     attr_accessor :tool_calls
@@ -54,6 +57,7 @@ module VeniceClient
         :'content' => :'content',
         :'name' => :'name',
         :'reasoning_content' => :'reasoning_content',
+        :'reasoning_details' => :'reasoning_details',
         :'role' => :'role',
         :'tool_calls' => :'tool_calls'
       }
@@ -75,6 +79,7 @@ module VeniceClient
         :'content' => :'AssistantMessageContent',
         :'name' => :'String',
         :'reasoning_content' => :'String',
+        :'reasoning_details' => :'Array<AssistantMessageReasoningDetailsInner>',
         :'role' => :'String',
         :'tool_calls' => :'Array<Object>'
       }
@@ -84,6 +89,7 @@ module VeniceClient
     def self.openapi_nullable
       Set.new([
         :'content',
+        :'name',
         :'reasoning_content',
         :'tool_calls'
       ])
@@ -117,6 +123,12 @@ module VeniceClient
         self.reasoning_content = attributes[:'reasoning_content']
       end
 
+      if attributes.key?(:'reasoning_details')
+        if (value = attributes[:'reasoning_details']).is_a?(Array)
+          self.reasoning_details = value
+        end
+      end
+
       if attributes.key?(:'role')
         self.role = attributes[:'role']
       else
@@ -170,6 +182,7 @@ module VeniceClient
           content == o.content &&
           name == o.name &&
           reasoning_content == o.reasoning_content &&
+          reasoning_details == o.reasoning_details &&
           role == o.role &&
           tool_calls == o.tool_calls
     end
@@ -183,7 +196,7 @@ module VeniceClient
     # Calculates hash code according to all attributes.
     # @return [Integer] Hash code
     def hash
-      [content, name, reasoning_content, role, tool_calls].hash
+      [content, name, reasoning_content, reasoning_details, role, tool_calls].hash
     end
 
     # Builds the object from hash

data/lib/venice_client/models/assistant_message_content.rb

@@ -3,7 +3,7 @@
 
 #The Venice.ai API.
 
-The version of the OpenAPI document: 20251209.153516
+The version of the OpenAPI document: 20251218.042551
 
 Generated by: https://openapi-generator.tech
 Generator version: 7.14.0