feat: /v1/chat/completion -> /v1/response (#2629)

* feat: /v1/chat/completion -> /v1/response

relay/compatible_handler.go

@@ -14,6 +14,7 @@ import (
 	"github.com/QuantumNous/new-api/logger"
 	"github.com/QuantumNous/new-api/model"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	relayconstant "github.com/QuantumNous/new-api/relay/constant"
 	"github.com/QuantumNous/new-api/relay/helper"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/model_setting"
@@ -73,6 +74,28 @@ func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types
 		return types.NewError(fmt.Errorf("invalid api type: %d", info.ApiType), types.ErrorCodeInvalidApiType, types.ErrOptionWithSkipRetry())
 	}
 	adaptor.Init(info)
+
+	if info.RelayMode == relayconstant.RelayModeChatCompletions &&
+		!model_setting.GetGlobalSettings().PassThroughRequestEnabled &&
+		!info.ChannelSetting.PassThroughBodyEnabled &&
+		service.ShouldChatCompletionsUseResponsesGlobal(info.ChannelId, info.OriginModelName) {
+		applySystemPromptIfNeeded(c, info, request)
+		usage, newApiErr := chatCompletionsViaResponses(c, info, adaptor, request)
+		if newApiErr != nil {
+			return newApiErr
+		}
+
+		var containAudioTokens = usage.CompletionTokenDetails.AudioTokens > 0 || usage.PromptTokensDetails.AudioTokens > 0
+		var containsAudioRatios = ratio_setting.ContainsAudioRatio(info.OriginModelName) || ratio_setting.ContainsAudioCompletionRatio(info.OriginModelName)
+
+		if containAudioTokens && containsAudioRatios {
+			service.PostAudioConsumeQuota(c, info, usage, "")
+		} else {
+			postConsumeQuota(c, info, usage)
+		}
+		return nil
+	}
+
 	var requestBody io.Reader
 
 	if model_setting.GetGlobalSettings().PassThroughRequestEnabled || info.ChannelSetting.PassThroughBodyEnabled {