made separate NonOpenAIExtensions

Author: AyushSawant18588

chat.go

@@ -248,6 +248,12 @@ func (r *ChatCompletionResponseFormatJSONSchema) UnmarshalJSON(data []byte) erro
 	return nil
 }
 
+// NonOpenAIExtensions contains non-standard OpenAI API extensions
+type NonOpenAIExtensions struct {
+	// GuidedChoice restricts output to a set of predefined choices.
+	GuidedChoice []string `json:"guided_choice,omitempty"`
+}
+
 // ChatCompletionRequest represents a request structure for chat completion API.
 type ChatCompletionRequest struct {
 	Model    string                  `json:"model"`
@@ -307,10 +313,8 @@ type ChatCompletionRequest struct {
 	// Such as think mode for qwen3. "chat_template_kwargs": {"enable_thinking": false}
 	// https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes
 	ChatTemplateKwargs map[string]any `json:"chat_template_kwargs,omitempty"`
-	// Specifies the latency tier to use for processing the request.
-	ServiceTier ServiceTier `json:"service_tier,omitempty"`
-	// GuidedChoice restricts output to a set of predefined choices.
-	GuidedChoice []string `json:"guided_choice,omitempty"`
+	// Embedded struct for non-OpenAI extensions
+	NonOpenAIExtensions `json:",inline"`
 }
 
 type StreamOptions struct {
@@ -394,15 +398,6 @@ const (
 	FinishReasonNull          FinishReason = "null"
 )
 
-type ServiceTier string
-
-const (
-	ServiceTierAuto     ServiceTier = "auto"
-	ServiceTierDefault  ServiceTier = "default"
-	ServiceTierFlex     ServiceTier = "flex"
-	ServiceTierPriority ServiceTier = "priority"
-)
-
 func (r FinishReason) MarshalJSON() ([]byte, error) {
 	if r == FinishReasonNull || r == "" {
 		return []byte("null"), nil
@@ -435,7 +430,6 @@ type ChatCompletionResponse struct {
 	Usage               Usage                  `json:"usage"`
 	SystemFingerprint   string                 `json:"system_fingerprint"`
 	PromptFilterResults []PromptFilterResult   `json:"prompt_filter_results,omitempty"`
-	ServiceTier         ServiceTier            `json:"service_tier,omitempty"`
 
 	httpHeader
 }