8.7.0

OpenAI.SDK/ObjectModels/RequestModels/ChatCompletionCreateRequest.cs

@@ -94,7 +94,7 @@ public IList<string>? StopCalculated
 
 
     /// <summary>
-    ///     An upper bound for the number of tokens that can be generated for a completion, 
+    ///     An upper bound for the number of tokens that can be generated for a completion,
     ///     including visible output tokens and reasoning tokens.
     /// </summary>
     /// <see href="https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_completion_tokens" />
@@ -267,6 +267,12 @@ public ResponseFormats? ChatResponseFormat
     [JsonPropertyName("top_logprobs")]
     public int? TopLogprobs { get; set; }
 
+    /// <summary>
+    ///     Whether to enable parallel <a href="https://platform.openai.com/docs/guides/function-calling/parallel-function-calling">function calling</a> during tool use.
+    /// </summary>
+    [JsonPropertyName("parallel_tool_calls")]
+    public bool? ParallelToolCalls { get; set; }
+
     /// <summary>
     ///     ID of the model to use. For models supported see <see cref="OpenAI.ObjectModels.Models" /> start with <c>Gpt_</c>
     /// </summary>
@@ -291,4 +297,15 @@ public IEnumerable<ValidationResult> Validate()
     /// </summary>
     [JsonPropertyName("user")]
     public string User { get; set; }
+
+    /// <summary>
+    /// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:
+    /// If set to 'auto', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.
+    /// If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
+    /// If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
+    /// When not set, the default behavior is 'auto'.
+    /// When this parameter is set, the response body will include the service_tier utilized.
+    /// </summary>
+    [JsonPropertyName("service_tier")]
+    public string? ServiceTier { get; set; }
 }

OpenAI.SDK/ObjectModels/ResponseModels/ChatCompletionCreateResponse.cs

@@ -5,21 +5,48 @@ namespace OpenAI.ObjectModels.ResponseModels;
 
 public record ChatCompletionCreateResponse : BaseResponse, IOpenAiModels.IId, IOpenAiModels.ICreatedAt
 {
+    /// <summary>
+    ///     The model used for the chat completion.
+    /// </summary>
     [JsonPropertyName("model")]
     public string Model { get; set; }
 
+    /// <summary>
+    ///     A list of chat completion choices. Can be more than one if n is greater than 1.
+    /// </summary>
     [JsonPropertyName("choices")]
     public List<ChatChoiceResponse> Choices { get; set; }
 
+    /// <summary>
+    ///     Usage statistics for the completion request.
+    /// </summary>
     [JsonPropertyName("usage")]
     public UsageResponse Usage { get; set; }
 
+    /// <summary>
+    ///     This fingerprint represents the backend configuration that the model runs with.
+    ///     Can be used in conjunction with the seed request parameter to understand when backend changes have been made that
+    ///     might impact determinism.
+    /// </summary>
     [JsonPropertyName("system_fingerprint")]
     public string SystemFingerPrint { get; set; }
 
+    /// <summary>
+    ///     The service tier used for processing the request. This field is only included if the service_tier parameter is
+    ///     specified in the request.
+    /// </summary>
+    [JsonPropertyName("service_tier")]
+    public string? ServiceTier { get; set; }
+
+    /// <summary>
+    ///     The Unix timestamp (in seconds) of when the chat completion was created.
+    /// </summary>
     [JsonPropertyName("created")]
     public int CreatedAt { get; set; }
 
+    /// <summary>
+    ///     A unique identifier for the chat completion.
+    /// </summary>
     [JsonPropertyName("id")]
     public string Id { get; set; }
 }

Readme.md

@@ -118,6 +118,8 @@ Needless to say, I cannot accept responsibility for any damage caused by using t
 ### 8.7.0
 - Added Support for o1 reasing models (`o1-mini` and `o1-preview`). 
 - Added `MaxCompletionTokens` for `chat completions`.
+- Added support for `ParallelToolCalls` for `chat completions`.
+- Added support for `ServiceTier` for `chat completions`.
 - Added support for `ChunkingStrategy` in `Vector Store` and `Vector Store Files`.
 - Added support for `Strict` in `ToolDefinition`.
 - Added support for `MaxNumberResults` and `RankingOptions` for `FileSearchTool`.