diff --git a/controller/relay-text.go b/controller/relay-text.go
index 9ce11601..35b1c543 100644
--- a/controller/relay-text.go
+++ b/controller/relay-text.go
@@ -201,6 +201,10 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			if err != nil {
 				common.SysError("error consuming token remain quota: " + err.Error())
 			}
+			err = model.CacheUpdateUserQuota(userId)
+			if err != nil {
+				common.SysError("error update user quota cache: " + err.Error())
+			}
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
diff --git a/model/cache.go b/model/cache.go
index e25b64f4..284e29ad 100644
--- a/model/cache.go
+++ b/model/cache.go
@@ -83,6 +83,18 @@ func CacheGetUserQuota(id int) (quota int, err error) {
 	return quota, err
 }
 
+func CacheUpdateUserQuota(id int) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	quota, err := GetUserQuota(id)
+	if err != nil {
+		return err
+	}
+	err = common.RedisSet(fmt.Sprintf("user_quota:%d", id), fmt.Sprintf("%d", quota), UserId2QuotaCacheSeconds*time.Second)
+	return err
+}
+
 func CacheIsUserEnabled(userId int) bool {
 	if !common.RedisEnabled {
 		return IsUserEnabled(userId)