venice_client 1.0.1 → 1.0.2

data/docs/AudioApi.md

@@ -2,48 +2,71 @@
 
 All URIs are relative to *https://api.venice.ai/api/v1*
 
-Method | HTTP request | Description
-------------- | ------------- | -------------
-[**create_speech**](AudioApi.md#create_speech) | **POST** /audio/speech | /api/v1/audio/speech
+| Method | HTTP request | Description |
+| ------ | ------------ | ----------- |
+| [**create_speech**](AudioApi.md#create_speech) | **POST** /audio/speech | /api/v1/audio/speech |
 
-# **create_speech**
-> String create_speech(opts)
+
+## create_speech
+
+> File create_speech(opts)
 
 /api/v1/audio/speech
 
 Converts text to speech using various voice models and formats.
 
-### Example
+### Examples
+
 ```ruby
-# load the gem
+require 'time'
 require 'venice_client'
 # setup authorization
 VeniceClient.configure do |config|
+  # Configure Bearer authorization (JWT): BearerAuth
+  config.access_token = 'YOUR_BEARER_TOKEN'
 end
 
 api_instance = VeniceClient::AudioApi.new
-opts = { 
-  body: VeniceClient::CreateSpeechRequestSchema.new # CreateSpeechRequestSchema | 
+opts = {
+  create_speech_request_schema: VeniceClient::CreateSpeechRequestSchema.new({input: 'Hello, this is a test of the text to speech system.'}) # CreateSpeechRequestSchema | 
 }
 
 begin
-  #/api/v1/audio/speech
+  # /api/v1/audio/speech
   result = api_instance.create_speech(opts)
   p result
 rescue VeniceClient::ApiError => e
-  puts "Exception when calling AudioApi->create_speech: #{e}"
+  puts "Error when calling AudioApi->create_speech: #{e}"
+end
+```
+
+#### Using the create_speech_with_http_info variant
+
+This returns an Array which contains the response data, status code and headers.
+
+> <Array(File, Integer, Hash)> create_speech_with_http_info(opts)
+
+```ruby
+begin
+  # /api/v1/audio/speech
+  data, status_code, headers = api_instance.create_speech_with_http_info(opts)
+  p status_code # => 2xx
+  p headers # => { ... }
+  p data # => File
+rescue VeniceClient::ApiError => e
+  puts "Error when calling AudioApi->create_speech_with_http_info: #{e}"
 end
 ```
 
 ### Parameters
 
-Name | Type | Description  | Notes
-------------- | ------------- | ------------- | -------------
- **body** | [**CreateSpeechRequestSchema**](CreateSpeechRequestSchema.md)|  | [optional] 
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **create_speech_request_schema** | [**CreateSpeechRequestSchema**](CreateSpeechRequestSchema.md) |  | [optional] |
 
 ### Return type
 
-**String**
+**File**
 
 ### Authorization
 
@@ -51,8 +74,6 @@ Name | Type | Description  | Notes
 
 ### HTTP request headers
 
- - **Content-Type**: application/json
- - **Accept**: audio/aac, audio/flac, audio/mpeg, audio/opus, audio/pcm, audio/wav, application/json
-
-
+- **Content-Type**: application/json
+- **Accept**: audio/aac, audio/flac, audio/mpeg, audio/opus, audio/pcm, audio/wav, application/json
 

data/docs/AudioModelPricing.md

@@ -0,0 +1,18 @@
+# VeniceClient::AudioModelPricing
+
+## Properties
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **input** | [**AudioModelPricingInput**](AudioModelPricingInput.md) |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::AudioModelPricing.new(
+  input: null
+)
+```
+

data/docs/AudioModelPricingInput.md

@@ -0,0 +1,22 @@
+# VeniceClient::AudioModelPricingInput
+
+## Properties
+
+| 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
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::AudioModelPricingInput.new(
+  usd: 3.5,
+  vcu: 35,
+  diem: 35
+)
+```
+

data/docs/BillingApi.md

@@ -2,60 +2,83 @@
 
 All URIs are relative to *https://api.venice.ai/api/v1*
 
-Method | HTTP request | Description
-------------- | ------------- | -------------
-[**get_billing_usage**](BillingApi.md#get_billing_usage) | **GET** /billing/usage | /api/v1/billing/usage
+| Method | HTTP request | Description |
+| ------ | ------------ | ----------- |
+| [**get_billing_usage**](BillingApi.md#get_billing_usage) | **GET** /billing/usage | /api/v1/billing/usage |
 
-# **get_billing_usage**
-> InlineResponse20015 get_billing_usage(opts)
+
+## get_billing_usage
+
+> <GetBillingUsage200Response> get_billing_usage(opts)
 
 /api/v1/billing/usage
 
 Get paginated billing usage data for the authenticated user. NOTE: This is a beta endpoint and may be subject to change.
 
-### Example
+### Examples
+
 ```ruby
-# load the gem
+require 'time'
 require 'venice_client'
 # setup authorization
 VeniceClient.configure do |config|
+  # Configure Bearer authorization (JWT): BearerAuth
+  config.access_token = 'YOUR_BEARER_TOKEN'
 end
 
 api_instance = VeniceClient::BillingApi.new
-opts = { 
-  accept: 'accept_example', # String | Accept header to specify the response format
-  currency: 'currency_example', # String | 
-  end_date: DateTime.parse('2013-10-20T19:20:30+01:00'), # DateTime | 
+opts = {
+  accept: 'application/json, text/csv', # String | Accept header to specify the response format
+  currency: 'USD', # String | 
+  end_date: Time.parse('2024-12-31T23:59:59Z'), # Time | 
   limit: 200, # Integer | 
   page: 1, # Integer | 
-  sort_order: 'desc', # String | 
-  start_date: DateTime.parse('2013-10-20T19:20:30+01:00') # DateTime | 
+  sort_order: 'asc', # String | 
+  start_date: Time.parse('2024-01-01T00:00Z') # Time | 
 }
 
 begin
-  #/api/v1/billing/usage
+  # /api/v1/billing/usage
   result = api_instance.get_billing_usage(opts)
   p result
 rescue VeniceClient::ApiError => e
-  puts "Exception when calling BillingApi->get_billing_usage: #{e}"
+  puts "Error when calling BillingApi->get_billing_usage: #{e}"
+end
+```
+
+#### Using the get_billing_usage_with_http_info variant
+
+This returns an Array which contains the response data, status code and headers.
+
+> <Array(<GetBillingUsage200Response>, Integer, Hash)> get_billing_usage_with_http_info(opts)
+
+```ruby
+begin
+  # /api/v1/billing/usage
+  data, status_code, headers = api_instance.get_billing_usage_with_http_info(opts)
+  p status_code # => 2xx
+  p headers # => { ... }
+  p data # => <GetBillingUsage200Response>
+rescue VeniceClient::ApiError => e
+  puts "Error when calling BillingApi->get_billing_usage_with_http_info: #{e}"
 end
 ```
 
 ### Parameters
 
-Name | Type | Description  | Notes
-------------- | ------------- | ------------- | -------------
- **accept** | **String**| Accept header to specify the response format | [optional] 
- **currency** | **String**|  | [optional] 
- **end_date** | **DateTime**|  | [optional] 
- **limit** | **Integer**|  | [optional] [default to 200]
- **page** | **Integer**|  | [optional] [default to 1]
- **sort_order** | **String**|  | [optional] [default to desc]
- **start_date** | **DateTime**|  | [optional] 
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **accept** | **String** | Accept header to specify the response format | [optional] |
+| **currency** | **String** |  | [optional] |
+| **end_date** | **Time** |  | [optional] |
+| **limit** | **Integer** |  | [optional][default to 200] |
+| **page** | **Integer** |  | [optional][default to 1] |
+| **sort_order** | **String** |  | [optional][default to &#39;desc&#39;] |
+| **start_date** | **Time** |  | [optional] |
 
 ### Return type
 
-[**InlineResponse20015**](InlineResponse20015.md)
+[**GetBillingUsage200Response**](GetBillingUsage200Response.md)
 
 ### Authorization
 
@@ -63,8 +86,6 @@ Name | Type | Description  | Notes
 
 ### HTTP request headers
 
- - **Content-Type**: Not defined
- - **Accept**: application/json, text/csv
-
-
+- **Content-Type**: Not defined
+- **Accept**: application/json, text/csv
 

data/docs/BillingUsageRequest.md

@@ -1,12 +1,28 @@
 # VeniceClient::BillingUsageRequest
 
 ## Properties
-Name | Type | Description | Notes
------------- | ------------- | ------------- | -------------
-**currency** | **String** | Filter by currency | [optional] 
-**end_date** | **DateTime** | End date for filtering records (ISO 8601) | [optional] 
-**limit** | **Integer** | Number of items per page | [optional] [default to 200]
-**page** | **Integer** | Page number for pagination | [optional] [default to 1]
-**sort_order** | **String** | Sort order for createdAt field | [optional] [default to 'desc']
-**start_date** | **DateTime** | Start date for filtering records (ISO 8601) | [optional] 
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **currency** | **String** | Filter by currency | [optional] |
+| **end_date** | **Time** | End date for filtering records (ISO 8601) | [optional] |
+| **limit** | **Integer** | Number of items per page | [optional][default to 200] |
+| **page** | **Integer** | Page number for pagination | [optional][default to 1] |
+| **sort_order** | **String** | Sort order for createdAt field | [optional][default to 'desc'] |
+| **start_date** | **Time** | Start date for filtering records (ISO 8601) | [optional] |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::BillingUsageRequest.new(
+  currency: USD,
+  end_date: 2024-12-31T23:59:59Z,
+  limit: 200,
+  page: 1,
+  sort_order: desc,
+  start_date: 2024-01-01T00:00Z
+)
+```
 

data/docs/BillingUsageResponse.md

@@ -1,8 +1,20 @@
 # VeniceClient::BillingUsageResponse
 
 ## Properties
-Name | Type | Description | Notes
------------- | ------------- | ------------- | -------------
-**data** | [**Array<BillingUsageResponseData>**](BillingUsageResponseData.md) |  | 
-**pagination** | [**BillingUsageResponsePagination**](BillingUsageResponsePagination.md) |  | 
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **data** | [**Array<GetBillingUsage200ResponseDataInner>**](GetBillingUsage200ResponseDataInner.md) |  |  |
+| **pagination** | [**GetBillingUsage200ResponsePagination**](GetBillingUsage200ResponsePagination.md) |  |  |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::BillingUsageResponse.new(
+  data: null,
+  pagination: null
+)
+```
 

data/docs/CharactersApi.md

@@ -2,42 +2,66 @@
 
 All URIs are relative to *https://api.venice.ai/api/v1*
 
-Method | HTTP request | Description
-------------- | ------------- | -------------
-[**list_characters**](CharactersApi.md#list_characters) | **GET** /characters | /api/v1/characters
+| Method | HTTP request | Description |
+| ------ | ------------ | ----------- |
+| [**list_characters**](CharactersApi.md#list_characters) | **GET** /characters | /api/v1/characters |
 
-# **list_characters**
-> InlineResponse20013 list_characters
+
+## list_characters
+
+> <ListCharacters200Response> list_characters
 
 /api/v1/characters
 
 This is a preview API and may change. Returns a list of characters supported in the API.
 
-### Example
+### Examples
+
 ```ruby
-# load the gem
+require 'time'
 require 'venice_client'
 # setup authorization
 VeniceClient.configure do |config|
+  # Configure Bearer authorization (JWT): BearerAuth
+  config.access_token = 'YOUR_BEARER_TOKEN'
 end
 
 api_instance = VeniceClient::CharactersApi.new
 
 begin
-  #/api/v1/characters
+  # /api/v1/characters
   result = api_instance.list_characters
   p result
 rescue VeniceClient::ApiError => e
-  puts "Exception when calling CharactersApi->list_characters: #{e}"
+  puts "Error when calling CharactersApi->list_characters: #{e}"
+end
+```
+
+#### Using the list_characters_with_http_info variant
+
+This returns an Array which contains the response data, status code and headers.
+
+> <Array(<ListCharacters200Response>, Integer, Hash)> list_characters_with_http_info
+
+```ruby
+begin
+  # /api/v1/characters
+  data, status_code, headers = api_instance.list_characters_with_http_info
+  p status_code # => 2xx
+  p headers # => { ... }
+  p data # => <ListCharacters200Response>
+rescue VeniceClient::ApiError => e
+  puts "Error when calling CharactersApi->list_characters_with_http_info: #{e}"
 end
 ```
 
 ### Parameters
+
 This endpoint does not need any parameter.
 
 ### Return type
 
-[**InlineResponse20013**](InlineResponse20013.md)
+[**ListCharacters200Response**](ListCharacters200Response.md)
 
 ### Authorization
 
@@ -45,8 +69,6 @@ This endpoint does not need any parameter.
 
 ### HTTP request headers
 
- - **Content-Type**: Not defined
- - **Accept**: application/json
-
-
+- **Content-Type**: Not defined
+- **Accept**: application/json
 

data/docs/ChatApi.md

@@ -2,50 +2,73 @@
 
 All URIs are relative to *https://api.venice.ai/api/v1*
 
-Method | HTTP request | Description
-------------- | ------------- | -------------
-[**create_chat_completion**](ChatApi.md#create_chat_completion) | **POST** /chat/completions | /api/v1/chat/completions
+| Method | HTTP request | Description |
+| ------ | ------------ | ----------- |
+| [**create_chat_completion**](ChatApi.md#create_chat_completion) | **POST** /chat/completions | /api/v1/chat/completions |
 
-# **create_chat_completion**
-> InlineResponse200 create_chat_completion(opts)
+
+## create_chat_completion
+
+> <CreateChatCompletion200Response> create_chat_completion(opts)
 
 /api/v1/chat/completions
 
-Run text inference based on the supplied parameters.
+Run text inference based on the supplied parameters. Long running requests should use the streaming API by setting stream=true in your request.
+
+### Examples
 
-### Example
 ```ruby
-# load the gem
+require 'time'
 require 'venice_client'
 # setup authorization
 VeniceClient.configure do |config|
+  # Configure Bearer authorization (JWT): BearerAuth
+  config.access_token = 'YOUR_BEARER_TOKEN'
 end
 
 api_instance = VeniceClient::ChatApi.new
-opts = { 
-  body: VeniceClient::ChatCompletionRequest.new # ChatCompletionRequest | 
-  accept_encoding: 'accept_encoding_example' # String | Supported compression encodings (gzip, br). Only applied when stream is false.
+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 | 
 }
 
 begin
-  #/api/v1/chat/completions
+  # /api/v1/chat/completions
   result = api_instance.create_chat_completion(opts)
   p result
 rescue VeniceClient::ApiError => e
-  puts "Exception when calling ChatApi->create_chat_completion: #{e}"
+  puts "Error when calling ChatApi->create_chat_completion: #{e}"
+end
+```
+
+#### Using the create_chat_completion_with_http_info variant
+
+This returns an Array which contains the response data, status code and headers.
+
+> <Array(<CreateChatCompletion200Response>, Integer, Hash)> create_chat_completion_with_http_info(opts)
+
+```ruby
+begin
+  # /api/v1/chat/completions
+  data, status_code, headers = api_instance.create_chat_completion_with_http_info(opts)
+  p status_code # => 2xx
+  p headers # => { ... }
+  p data # => <CreateChatCompletion200Response>
+rescue VeniceClient::ApiError => e
+  puts "Error when calling ChatApi->create_chat_completion_with_http_info: #{e}"
 end
 ```
 
 ### Parameters
 
-Name | Type | Description  | Notes
-------------- | ------------- | ------------- | -------------
- **body** | [**ChatCompletionRequest**](ChatCompletionRequest.md)|  | [optional] 
- **accept_encoding** | **String**| Supported compression encodings (gzip, br). Only applied when stream is false. | [optional] 
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **accept_encoding** | **String** | Supported compression encodings (gzip, br). Only applied when stream is false. | [optional] |
+| **chat_completion_request** | [**ChatCompletionRequest**](ChatCompletionRequest.md) |  | [optional] |
 
 ### Return type
 
-[**InlineResponse200**](InlineResponse200.md)
+[**CreateChatCompletion200Response**](CreateChatCompletion200Response.md)
 
 ### Authorization
 
@@ -53,8 +76,6 @@ Name | Type | Description  | Notes
 
 ### HTTP request headers
 
- - **Content-Type**: application/json
- - **Accept**: application/json
-
-
+- **Content-Type**: application/json
+- **Accept**: application/json
 

data/docs/ChatCompletionRequest.md

@@ -1,32 +1,70 @@
 # VeniceClient::ChatCompletionRequest
 
 ## Properties
-Name | Type | Description | Notes
------------- | ------------- | ------------- | -------------
-**frequency_penalty** | [**BigDecimal**](BigDecimal.md) | 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. | [optional] [default to 0]
-**logprobs** | **BOOLEAN** | Whether to include log probabilities in the response. This is not supported by all models. | [optional] 
-**max_completion_tokens** | **Integer** | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. | [optional] 
-**max_temp** | [**BigDecimal**](BigDecimal.md) | Maximum temperature value for dynamic temperature scaling. | [optional] 
-**max_tokens** | **Integer** | 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. | [optional] 
-**messages** | [**Array<AnyOfChatCompletionRequestMessagesItems>**](.md) | 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** | [**BigDecimal**](BigDecimal.md) | Sets a minimum probability threshold for token selection. Tokens with probabilities below this value are filtered out. | [optional] 
-**min_temp** | [**BigDecimal**](BigDecimal.md) | Minimum temperature value for dynamic temperature scaling. | [optional] 
-**model** | **String** | The ID of the model you wish to prompt. May also be a model trait, or a 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** | [**BigDecimal**](BigDecimal.md) | 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]
-**repetition_penalty** | [**BigDecimal**](BigDecimal.md) | The parameter for repetition penalty. 1.0 means no penalty. Values > 1.0 discourage repetition. | [optional] 
-**seed** | **Integer** | The random seed used to generate the response. This is useful for reproducibility. | [optional] 
-**stop** | [**AnyOfChatCompletionRequestStop**](AnyOfChatCompletionRequestStop.md) | Up to 4 sequences where the API will stop generating further tokens. Defaults to null. | [optional] 
-**stop_token_ids** | [**Array<BigDecimal>**](BigDecimal.md) | Array of token IDs where the API will stop generating further tokens. | [optional] 
-**stream** | **BOOLEAN** | Whether to stream back partial progress. Defaults to false. | [optional] 
-**stream_options** | [**ChatCompletionRequestStreamOptions**](ChatCompletionRequestStreamOptions.md) |  | [optional] 
-**temperature** | [**BigDecimal**](BigDecimal.md) | 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. | [optional] [default to 0.3]
-**top_k** | **Integer** | The number of highest probability vocabulary tokens to keep for top-k-filtering. | [optional] 
-**top_p** | [**BigDecimal**](BigDecimal.md) | 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. | [optional] [default to 1]
-**user** | **String** | This field is discarded on the request but is supported in the Venice API for compatibility with OpenAPI clients. | [optional] 
-**venice_parameters** | [**ChatCompletionRequestVeniceParameters**](ChatCompletionRequestVeniceParameters.md) |  | [optional] 
-**parallel_tool_calls** | **BOOLEAN** | Whether to enable parallel function calling during tool use. | [optional] [default to true]
-**response_format** | [**OneOfChatCompletionRequestResponseFormat**](OneOfChatCompletionRequestResponseFormat.md) | Format in which the response should be returned. | [optional] 
-**tool_choice** | [**AnyOfChatCompletionRequestToolChoice**](AnyOfChatCompletionRequestToolChoice.md) |  | [optional] 
-**tools** | [**Array<ToolCall>**](ToolCall.md) | 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. | [optional] 
+
+| Name | Type | Description | Notes |
+| ---- | ---- | ----------- | ----- |
+| **frequency_penalty** | **Float** | 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. | [optional][default to 0] |
+| **logprobs** | **Boolean** | Whether to include log probabilities in the response. This is not supported by all models. | [optional] |
+| **top_logprobs** | **Integer** | The number of highest probability tokens to return for each token position. | [optional] |
+| **max_completion_tokens** | **Integer** | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. | [optional] |
+| **max_temp** | **Float** | Maximum temperature value for dynamic temperature scaling. | [optional] |
+| **max_tokens** | **Integer** | 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. | [optional] |
+| **messages** | [**Array<ChatCompletionRequestMessagesInner>**](ChatCompletionRequestMessagesInner.md) | 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** | **Float** | Sets a minimum probability threshold for token selection. Tokens with probabilities below this value are filtered out. | [optional] |
+| **min_temp** | **Float** | Minimum temperature value for dynamic temperature scaling. | [optional] |
+| **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] |
+| **repetition_penalty** | **Float** | The parameter for repetition penalty. 1.0 means no penalty. Values > 1.0 discourage repetition. | [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] |
+| **stream** | **Boolean** | Whether to stream back partial progress. Defaults to false. | [optional] |
+| **stream_options** | [**ChatCompletionRequestStreamOptions**](ChatCompletionRequestStreamOptions.md) |  | [optional] |
+| **temperature** | **Float** | 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. | [optional][default to 0.7] |
+| **top_k** | **Integer** | The number of highest probability vocabulary tokens to keep for top-k-filtering. | [optional] |
+| **top_p** | **Float** | 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. | [optional][default to 0.9] |
+| **user** | **String** | This field is discarded on the request but is supported in the Venice API for compatibility with OpenAI clients. | [optional] |
+| **venice_parameters** | [**ChatCompletionRequestVeniceParameters**](ChatCompletionRequestVeniceParameters.md) |  | [optional] |
+| **parallel_tool_calls** | **Boolean** | Whether to enable parallel function calling during tool use. | [optional][default to true] |
+| **response_format** | [**ChatCompletionRequestResponseFormat**](ChatCompletionRequestResponseFormat.md) |  | [optional] |
+| **tool_choice** | [**ChatCompletionRequestToolChoice**](ChatCompletionRequestToolChoice.md) |  | [optional] |
+| **tools** | [**Array<ToolCall>**](ToolCall.md) | 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. | [optional] |
+
+## Example
+
+```ruby
+require 'venice_client'
+
+instance = VeniceClient::ChatCompletionRequest.new(
+  frequency_penalty: null,
+  logprobs: true,
+  top_logprobs: 1,
+  max_completion_tokens: null,
+  max_temp: 1.5,
+  max_tokens: null,
+  messages: null,
+  min_p: 0.05,
+  min_temp: 0.1,
+  model: venice-uncensored,
+  n: null,
+  presence_penalty: null,
+  repetition_penalty: 1.2,
+  seed: 42,
+  stop: null,
+  stop_token_ids: [151643,151645],
+  stream: true,
+  stream_options: null,
+  temperature: 0.7,
+  top_k: 40,
+  top_p: 0.9,
+  user: null,
+  venice_parameters: null,
+  parallel_tool_calls: false,
+  response_format: null,
+  tool_choice: null,
+  tools: null
+)
+```