feat: add Azure default API version configuration

- Introduce `AZURE_DEFAULT_API_VERSION` environment variable
- Set default Azure API version to `2024-12-01-preview`
- Update README documentation for new environment configuration
- Modify Azure channel relay to use default API version when not specified

README.en.md

@@ -59,6 +59,10 @@
 13. 🎵 Added [Suno API](https://github.com/Suno-API/Suno-API) interface support, [Integration Guide](Suno.md)
 14. 🔄 Support for Rerank models, compatible with Cohere and Jina, can integrate with Dify, [Integration Guide](Rerank.md)
 15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - Support for OpenAI's Realtime API, including Azure channels
+16. 🧠 Support for setting reasoning effort through model name suffix:
+    - Add suffix `-high` to set high reasoning effort (e.g., `o3-mini-high`)
+    - Add suffix `-medium` to set medium reasoning effort
+    - Add suffix `-low` to set low reasoning effort
 
 ## Model Support
 This version additionally supports:
@@ -84,6 +88,7 @@ You can add custom models gpt-4-gizmo-* in channels. These are third-party model
 - `GEMINI_VISION_MAX_IMAGE_NUM`: Gemini model maximum image number, default `16`, set to `-1` to disable
 - `MAX_FILE_DOWNLOAD_MB`: Maximum file download size in MB, default `20`
 - `CRYPTO_SECRET`: Encryption key for encrypting database content
+- `AZURE_DEFAULT_API_VERSION`: Azure channel default API version, if not specified in channel settings, use this version, default `2024-12-01-preview`
 
 ## Deployment
 > [!TIP]

README.md

@@ -94,6 +94,7 @@
 - `GEMINI_VISION_MAX_IMAGE_NUM`：Gemini模型最大图片数量，默认为 `16`，设置为 `-1` 则不限制。
 - `MAX_FILE_DOWNLOAD_MB`: 最大文件下载大小，单位 MB，默认为 `20`。
 - `CRYPTO_SECRET`：加密密钥，用于加密数据库内容。
+- `AZURE_DEFAULT_API_VERSION`：Azure渠道默认API版本，如果渠道设置中未指定API版本，则使用此版本，默认为 `2024-12-01-preview`
 ## 部署
 > [!TIP]
 > 最新版Docker镜像：`calciumion/new-api:latest`  

constant/env.go

@@ -21,6 +21,8 @@ var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STR
 
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
 
+var AzureDefaultAPIVersion = common.GetEnvOrDefaultString("AZURE_DEFAULT_API_VERSION", "2024-12-01-preview")
+
 var GeminiModelMap = map[string]string{
 	"gemini-1.0-pro": "v1",
 }

relay/channel/openai/adaptor.go

@@ -10,6 +10,7 @@ import (
 	"mime/multipart"
 	"net/http"
 	"one-api/common"
+	constant2 "one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
@@ -44,16 +45,20 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 	switch info.ChannelType {
 	case common.ChannelTypeAzure:
+		apiVersion := info.ApiVersion
+		if apiVersion == "" {
+			apiVersion = constant2.AzureDefaultAPIVersion
+		}
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
 		requestURL := strings.Split(info.RequestURLPath, "?")[0]
-		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
+		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
 		task := strings.TrimPrefix(requestURL, "/v1/")
 		model_ := info.UpstreamModelName
 		model_ = strings.Replace(model_, ".", "", -1)
 		// https://github.com/songquanpeng/one-api/issues/67
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
 		if info.RelayMode == constant.RelayModeRealtime {
-			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion)
+			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, apiVersion)
 		}
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
 	case common.ChannelTypeMiniMax:

relay/relay-text.go

@@ -219,7 +219,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		return openaiErr
 	}
 
-	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
+	if strings.HasPrefix(relayInfo.RecodeModelName, "gpt-4o-audio") {
 		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	} else {
 		postConsumeQuota(c, relayInfo, relayInfo.RecodeModelName, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")

service/quota.go

@@ -182,9 +182,9 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	audioOutTokens := usage.CompletionTokenDetails.AudioTokens
 
 	tokenName := ctx.GetString("token_name")
-	completionRatio := common.GetCompletionRatio(relayInfo.UpstreamModelName)
-	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
-	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName)
+	completionRatio := common.GetCompletionRatio(relayInfo.RecodeModelName)
+	audioRatio := common.GetAudioRatio(relayInfo.RecodeModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.RecodeModelName)
 
 	quotaInfo := QuotaInfo{
 		InputDetails: TokenDetails{
@@ -195,7 +195,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 			TextTokens:  textOutTokens,
 			AudioTokens: audioOutTokens,
 		},
-		ModelName:  relayInfo.UpstreamModelName,
+		ModelName:  relayInfo.RecodeModelName,
 		UsePrice:   usePrice,
 		ModelRatio: modelRatio,
 		GroupRatio: groupRatio,
@@ -218,7 +218,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		quota = 0
 		logContent += fmt.Sprintf("（可能是上游超时）")
 		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.UpstreamModelName, preConsumedQuota))
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.RecodeModelName, preConsumedQuota))
 	} else {
 		quotaDelta := quota - preConsumedQuota
 		if quotaDelta != 0 {
@@ -231,7 +231,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	logModel := relayInfo.UpstreamModelName
+	logModel := relayInfo.RecodeModelName
 	if extraContent != "" {
 		logContent += ", " + extraContent
 	}