fix: fix retry not working (close #1314)

middleware/distributor.go

@@ -39,7 +39,7 @@ func Distribute() func(c *gin.Context) {
 				return
 			}
 		} else {
-			requestModel := c.GetString("request_model")
+			requestModel = c.GetString("request_model")
 			var err error
 			channel, err = model.CacheGetRandomSatisfiedChannel(userGroup, requestModel, false)
 			if err != nil {

relay/adaptor/openai/constants.go

@@ -6,7 +6,7 @@ var ModelList = []string{
 	"gpt-3.5-turbo-instruct",
 	"gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
 	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
-	"gpt-4-turbo-preview",
+	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",

relay/billing/ratio/model.go

@@ -29,6 +29,8 @@ var ModelRatio = map[string]float64{
 	"gpt-4-1106-preview":      5,    // $0.01 / 1K tokens
 	"gpt-4-0125-preview":      5,    // $0.01 / 1K tokens
 	"gpt-4-turbo-preview":     5,    // $0.01 / 1K tokens
+	"gpt-4-turbo":             5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":  5,    // $0.01 / 1K tokens
 	"gpt-4-vision-preview":    5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":           0.25, // $0.0005 / 1K tokens
 	"gpt-3.5-turbo-0301":      0.75,
@@ -256,7 +258,7 @@ func GetCompletionRatio(name string) float64 {
 		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") {
-		if strings.HasSuffix(name, "preview") {
+		if strings.HasPrefix(name, "gpt-4-turbo") {
 			return 3
 		}
 		return 2