feat: built in retry supported (close #1036 , close #770 )

fix: fix "error update user quota cache: Error 1040: Too many connections"
fix: fix i18n
2025-11-04 15:53:42 +08:00 · 2024-02-25 19:01:49 +08:00 · 2024-02-25 16:58:14 +08:00 · 2024-02-25 16:53:46 +08:00 · 2024-02-25 02:07:34 +08:00 · 2024-02-25 01:59:40 +08:00
146 changed files with 4592 additions and 3918 deletions
--- a/.github/workflows/linux-release.yml
+++ b/.github/workflows/linux-release.yml
@@ -23,7 +23,7 @@ jobs:
      - uses: actions/setup-node@v3
        with:
          node-version: 16
-      - name: Build Frontend (theme default)
+      - name: Build Frontend
        env:
          CI: ""
        run: |
--- a/.github/workflows/macos-release.yml
+++ b/.github/workflows/macos-release.yml
@@ -23,7 +23,7 @@ jobs:
      - uses: actions/setup-node@v3
        with:
          node-version: 16
-      - name: Build Frontend (theme default)
+      - name: Build Frontend
        env:
          CI: ""
        run: |
--- a/.github/workflows/windows-release.yml
+++ b/.github/workflows/windows-release.yml
@@ -26,7 +26,7 @@ jobs:
      - uses: actions/setup-node@v3
        with:
          node-version: 16
-      - name: Build Frontend (theme default)
+      - name: Build Frontend
        env:
          CI: ""
        run: |
--- a/.gitignore
+++ b/.gitignore
@@ -6,4 +6,5 @@ upload
 build
 *.db-journal
 logs
-data
+data
+/web/node_modules
--- a/2
+++ b/2
@@ -23,7 +23,7 @@ ADD go.mod go.sum ./
 RUN go mod download
 COPY . .
 COPY --from=builder /web/build ./web/build
-RUN go build -ldflags "-s -w -X 'one-api/common.Version=$(cat VERSION)' -extldflags '-static'" -o one-api
+RUN go build -ldflags "-s -w -X 'github.com/songquanpeng/one-api/common.Version=$(cat VERSION)' -extldflags '-static'" -o one-api

 FROM alpine

--- a/README.en.md
+++ b/README.en.md
@@ -134,12 +134,12 @@ The initial account username is `root` and password is `123456`.
   git clone https://github.com/songquanpeng/one-api.git
   
   # Build the frontend
-   cd one-api/web
+   cd one-api/web/default
   npm install
   npm run build
   
   # Build the backend
-   cd ..
+   cd ../..
   go mod download
   go build -ldflags "-s -w" -o one-api
   ```
--- a/README.ja.md
+++ b/README.ja.md
@@ -135,12 +135,12 @@ sudo service nginx restart
   git clone https://github.com/songquanpeng/one-api.git

   # フロントエンドのビルド
-   cd one-api/web
+   cd one-api/web/default
   npm install
   npm run build

   # バックエンドのビルド
-   cd ..
+   cd ../..
   go mod download
   go build -ldflags "-s -w" -o one-api
   ```
--- a/README.md
+++ b/README.md
@@ -73,6 +73,9 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
   + [x] [智谱 ChatGLM 系列模型](https://bigmodel.cn)
   + [x] [360 智脑](https://ai.360.cn)
   + [x] [腾讯混元大模型](https://cloud.tencent.com/document/product/1729)
+   + [x] [Moonshot AI](https://platform.moonshot.cn/)
+   + [ ] [字节云雀大模型](https://www.volcengine.com/product/ark) (WIP)
+   + [ ] [MINIMAX](https://api.minimax.chat/) (WIP)
 2. 支持配置镜像以及众多[第三方代理服务](https://iamazing.cn/page/openai-api-third-party-services)。
 3. 支持通过**负载均衡**的方式访问多个渠道。
 4. 支持 **stream 模式**，可以通过流式传输实现打字机效果。
@@ -174,12 +177,12 @@ docker-compose ps
   git clone https://github.com/songquanpeng/one-api.git
   
   # 构建前端
-   cd one-api/web
+   cd one-api/web/default
   npm install
   npm run build
   
   # 构建后端
-   cd ..
+   cd ../..
   go mod download
   go build -ldflags "-s -w" -o one-api
   ````
@@ -414,6 +417,9 @@ https://openai.justsong.cn
 8. 升级之前数据库需要做变更吗？
   + 一般情况下不需要，系统将在初始化的时候自动调整。
   + 如果需要的话，我会在更新日志中说明，并给出脚本。
+9. 手动修改数据库后报错：`数据库一致性已被破坏，请联系管理员`？
+   + 这是检测到 ability 表里有些记录的通道 id 是不存在的，这大概率是因为你删了 channel 表里的记录但是没有同步在 ability 表里清理无效的通道。
+   + 对于每一个通道，其所支持的模型都需要有一个专门的 ability 表的记录，表示该通道支持该模型。

 ## 相关项目
 * [FastGPT](https://github.com/labring/FastGPT): 基于 LLM 大语言模型的知识库问答系统
--- a/common/config/config.go
+++ b/common/config/config.go
@@ -0,0 +1,127 @@
+package config
+
+import (
+	"github.com/songquanpeng/one-api/common/helper"
+	"os"
+	"strconv"
+	"sync"
+	"time"
+
+	"github.com/google/uuid"
+)
+
+var SystemName = "One API"
+var ServerAddress = "http://localhost:3000"
+var Footer = ""
+var Logo = ""
+var TopUpLink = ""
+var ChatLink = ""
+var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
+var DisplayInCurrencyEnabled = true
+var DisplayTokenStatEnabled = true
+
+// Any options with "Secret", "Token" in its key won't be return by GetOptions
+
+var SessionSecret = uuid.New().String()
+
+var OptionMap map[string]string
+var OptionMapRWMutex sync.RWMutex
+
+var ItemsPerPage = 10
+var MaxRecentItems = 100
+
+var PasswordLoginEnabled = true
+var PasswordRegisterEnabled = true
+var EmailVerificationEnabled = false
+var GitHubOAuthEnabled = false
+var WeChatAuthEnabled = false
+var TurnstileCheckEnabled = false
+var RegisterEnabled = true
+
+var EmailDomainRestrictionEnabled = false
+var EmailDomainWhitelist = []string{
+	"gmail.com",
+	"163.com",
+	"126.com",
+	"qq.com",
+	"outlook.com",
+	"hotmail.com",
+	"icloud.com",
+	"yahoo.com",
+	"foxmail.com",
+}
+
+var DebugEnabled = os.Getenv("DEBUG") == "true"
+var MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
+
+var LogConsumeEnabled = true
+
+var SMTPServer = ""
+var SMTPPort = 587
+var SMTPAccount = ""
+var SMTPFrom = ""
+var SMTPToken = ""
+
+var GitHubClientId = ""
+var GitHubClientSecret = ""
+
+var WeChatServerAddress = ""
+var WeChatServerToken = ""
+var WeChatAccountQRCodeImageURL = ""
+
+var TurnstileSiteKey = ""
+var TurnstileSecretKey = ""
+
+var QuotaForNewUser = 0
+var QuotaForInviter = 0
+var QuotaForInvitee = 0
+var ChannelDisableThreshold = 5.0
+var AutomaticDisableChannelEnabled = false
+var AutomaticEnableChannelEnabled = false
+var QuotaRemindThreshold = 1000
+var PreConsumedQuota = 500
+var ApproximateTokenEnabled = false
+var RetryTimes = 0
+
+var RootUserEmail = ""
+
+var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
+
+var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
+var RequestInterval = time.Duration(requestInterval) * time.Second
+
+var SyncFrequency = helper.GetOrDefaultEnvInt("SYNC_FREQUENCY", 10*60) // unit is second
+
+var BatchUpdateEnabled = false
+var BatchUpdateInterval = helper.GetOrDefaultEnvInt("BATCH_UPDATE_INTERVAL", 5)
+
+var RelayTimeout = helper.GetOrDefaultEnvInt("RELAY_TIMEOUT", 0) // unit is second
+
+var GeminiSafetySetting = helper.GetOrDefaultEnvString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+
+var Theme = helper.GetOrDefaultEnvString("THEME", "default")
+var ValidThemes = map[string]bool{
+	"default": true,
+	"berry":   true,
+}
+
+// All duration's unit is seconds
+// Shouldn't larger then RateLimitKeyExpirationDuration
+var (
+	GlobalApiRateLimitNum            = helper.GetOrDefaultEnvInt("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitDuration int64 = 3 * 60
+
+	GlobalWebRateLimitNum            = helper.GetOrDefaultEnvInt("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitDuration int64 = 3 * 60
+
+	UploadRateLimitNum            = 10
+	UploadRateLimitDuration int64 = 60
+
+	DownloadRateLimitNum            = 10
+	DownloadRateLimitDuration int64 = 60
+
+	CriticalRateLimitNum            = 20
+	CriticalRateLimitDuration int64 = 20 * 60
+)
+
+var RateLimitKeyExpirationDuration = 20 * time.Minute
--- a/common/constants.go
+++ b/common/constants.go
@@ -1,114 +1,9 @@
 package common

-import (
-	"os"
-	"strconv"
-	"sync"
-	"time"
-
-	"github.com/google/uuid"
-)
+import "time"

 var StartTime = time.Now().Unix() // unit: second
 var Version = "v0.0.0"            // this hard coding will be replaced automatically when building, no need to manually change
-var SystemName = "One API"
-var ServerAddress = "http://localhost:3000"
-var Footer = ""
-var Logo = ""
-var TopUpLink = ""
-var ChatLink = ""
-var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
-var DisplayInCurrencyEnabled = true
-var DisplayTokenStatEnabled = true
-
-// Any options with "Secret", "Token" in its key won't be return by GetOptions
-
-var SessionSecret = uuid.New().String()
-
-var OptionMap map[string]string
-var OptionMapRWMutex sync.RWMutex
-
-var ItemsPerPage = 10
-var MaxRecentItems = 100
-
-var PasswordLoginEnabled = true
-var PasswordRegisterEnabled = true
-var EmailVerificationEnabled = false
-var GitHubOAuthEnabled = false
-var WeChatAuthEnabled = false
-var TurnstileCheckEnabled = false
-var RegisterEnabled = true
-
-var EmailDomainRestrictionEnabled = false
-var EmailDomainWhitelist = []string{
-	"gmail.com",
-	"163.com",
-	"126.com",
-	"qq.com",
-	"outlook.com",
-	"hotmail.com",
-	"icloud.com",
-	"yahoo.com",
-	"foxmail.com",
-}
-
-var DebugEnabled = os.Getenv("DEBUG") == "true"
-var MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
-
-var LogConsumeEnabled = true
-
-var SMTPServer = ""
-var SMTPPort = 587
-var SMTPAccount = ""
-var SMTPFrom = ""
-var SMTPToken = ""
-
-var GitHubClientId = ""
-var GitHubClientSecret = ""
-
-var WeChatServerAddress = ""
-var WeChatServerToken = ""
-var WeChatAccountQRCodeImageURL = ""
-
-var TurnstileSiteKey = ""
-var TurnstileSecretKey = ""
-
-var QuotaForNewUser = 0
-var QuotaForInviter = 0
-var QuotaForInvitee = 0
-var ChannelDisableThreshold = 5.0
-var AutomaticDisableChannelEnabled = false
-var AutomaticEnableChannelEnabled = false
-var QuotaRemindThreshold = 1000
-var PreConsumedQuota = 500
-var ApproximateTokenEnabled = false
-var RetryTimes = 0
-
-var RootUserEmail = ""
-
-var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
-
-var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
-var RequestInterval = time.Duration(requestInterval) * time.Second
-
-var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 10*60) // unit is second
-
-var BatchUpdateEnabled = false
-var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
-
-var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
-
-var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
-
-var Theme = GetOrDefaultString("THEME", "default")
-var ValidThemes = map[string]bool{
-	"default": true,
-	"berry":   true,
-}
-
-const (
-	RequestIdKey = "X-Oneapi-Request-Id"
-)

 const (
 	RoleGuestUser  = 0
@@ -117,34 +12,6 @@ const (
 	RoleRootUser   = 100
 )

-var (
-	FileUploadPermission    = RoleGuestUser
-	FileDownloadPermission  = RoleGuestUser
-	ImageUploadPermission   = RoleGuestUser
-	ImageDownloadPermission = RoleGuestUser
-)
-
-// All duration's unit is seconds
-// Shouldn't larger then RateLimitKeyExpirationDuration
-var (
-	GlobalApiRateLimitNum            = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
-	GlobalApiRateLimitDuration int64 = 3 * 60
-
-	GlobalWebRateLimitNum            = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
-	GlobalWebRateLimitDuration int64 = 3 * 60
-
-	UploadRateLimitNum            = 10
-	UploadRateLimitDuration int64 = 60
-
-	DownloadRateLimitNum            = 10
-	DownloadRateLimitDuration int64 = 60
-
-	CriticalRateLimitNum            = 20
-	CriticalRateLimitDuration int64 = 20 * 60
-)
-
-var RateLimitKeyExpirationDuration = 20 * time.Minute
-
 const (
 	UserStatusEnabled  = 1 // don't use 0, 0 is the default value!
 	UserStatusDisabled = 2 // also don't use 0
@@ -196,32 +63,42 @@ const (
 	ChannelTypeFastGPT        = 22
 	ChannelTypeTencent        = 23
 	ChannelTypeGemini         = 24
+	ChannelTypeMoonshot       = 25
 )

 var ChannelBaseURLs = []string{
-	"",                                  // 0
-	"https://api.openai.com",            // 1
-	"https://oa.api2d.net",              // 2
-	"",                                  // 3
-	"https://api.closeai-proxy.xyz",     // 4
-	"https://api.openai-sb.com",         // 5
-	"https://api.openaimax.com",         // 6
-	"https://api.ohmygpt.com",           // 7
-	"",                                  // 8
-	"https://api.caipacity.com",         // 9
-	"https://api.aiproxy.io",            // 10
-	"",                                  // 11
-	"https://api.api2gpt.com",           // 12
-	"https://api.aigc2d.com",            // 13
-	"https://api.anthropic.com",         // 14
-	"https://aip.baidubce.com",          // 15
-	"https://open.bigmodel.cn",          // 16
-	"https://dashscope.aliyuncs.com",    // 17
-	"",                                  // 18
-	"https://ai.360.cn",                 // 19
-	"https://openrouter.ai/api",         // 20
-	"https://api.aiproxy.io",            // 21
-	"https://fastgpt.run/api/openapi",   // 22
-	"https://hunyuan.cloud.tencent.com", //23
-	"",                                  //24
+	"",                              // 0
+	"https://api.openai.com",        // 1
+	"https://oa.api2d.net",          // 2
+	"",                              // 3
+	"https://api.closeai-proxy.xyz", // 4
+	"https://api.openai-sb.com",     // 5
+	"https://api.openaimax.com",     // 6
+	"https://api.ohmygpt.com",       // 7
+	"",                              // 8
+	"https://api.caipacity.com",     // 9
+	"https://api.aiproxy.io",        // 10
+	"https://generativelanguage.googleapis.com", // 11
+	"https://api.api2gpt.com",                   // 12
+	"https://api.aigc2d.com",                    // 13
+	"https://api.anthropic.com",                 // 14
+	"https://aip.baidubce.com",                  // 15
+	"https://open.bigmodel.cn",                  // 16
+	"https://dashscope.aliyuncs.com",            // 17
+	"",                                          // 18
+	"https://ai.360.cn",                         // 19
+	"https://openrouter.ai/api",                 // 20
+	"https://api.aiproxy.io",                    // 21
+	"https://fastgpt.run/api/openapi",           // 22
+	"https://hunyuan.cloud.tencent.com",         // 23
+	"https://generativelanguage.googleapis.com", // 24
+	"https://api.moonshot.cn",                   // 25
 }
+
+const (
+	ConfigKeyPrefix = "cfg_"
+
+	ConfigKeyAPIVersion = ConfigKeyPrefix + "api_version"
+	ConfigKeyLibraryID  = ConfigKeyPrefix + "library_id"
+	ConfigKeyPlugin     = ConfigKeyPrefix + "plugin"
+)
--- a/common/database.go
+++ b/common/database.go
@@ -1,7 +1,9 @@
 package common

+import "github.com/songquanpeng/one-api/common/helper"
+
 var UsingSQLite = false
 var UsingPostgreSQL = false

 var SQLitePath = "one-api.db"
-var SQLiteBusyTimeout = GetOrDefault("SQLITE_BUSY_TIMEOUT", 3000)
+var SQLiteBusyTimeout = helper.GetOrDefaultEnvInt("SQLITE_BUSY_TIMEOUT", 3000)
--- a/common/email.go
+++ b/common/email.go
@@ -5,19 +5,20 @@ import (
 	"crypto/tls"
 	"encoding/base64"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/config"
 	"net/smtp"
 	"strings"
 	"time"
 )

 func SendEmail(subject string, receiver string, content string) error {
-	if SMTPFrom == "" { // for compatibility
-		SMTPFrom = SMTPAccount
+	if config.SMTPFrom == "" { // for compatibility
+		config.SMTPFrom = config.SMTPAccount
 	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))

 	// Extract domain from SMTPFrom
-	parts := strings.Split(SMTPFrom, "@")
+	parts := strings.Split(config.SMTPFrom, "@")
 	var domain string
 	if len(parts) > 1 {
 		domain = parts[1]
@@ -36,21 +37,21 @@ func SendEmail(subject string, receiver string, content string) error {
 		"Message-ID: %s\r\n"+ // add Message-ID header to avoid being treated as spam, RFC 5322
 		"Date: %s\r\n"+
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, messageId, time.Now().Format(time.RFC1123Z), content))
-	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
-	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
+		receiver, config.SystemName, config.SMTPFrom, encodedSubject, messageId, time.Now().Format(time.RFC1123Z), content))
+	auth := smtp.PlainAuth("", config.SMTPAccount, config.SMTPToken, config.SMTPServer)
+	addr := fmt.Sprintf("%s:%d", config.SMTPServer, config.SMTPPort)
 	to := strings.Split(receiver, ";")

-	if SMTPPort == 465 {
+	if config.SMTPPort == 465 {
 		tlsConfig := &tls.Config{
 			InsecureSkipVerify: true,
-			ServerName:         SMTPServer,
+			ServerName:         config.SMTPServer,
 		}
-		conn, err := tls.Dial("tcp", fmt.Sprintf("%s:%d", SMTPServer, SMTPPort), tlsConfig)
+		conn, err := tls.Dial("tcp", fmt.Sprintf("%s:%d", config.SMTPServer, config.SMTPPort), tlsConfig)
 		if err != nil {
 			return err
 		}
-		client, err := smtp.NewClient(conn, SMTPServer)
+		client, err := smtp.NewClient(conn, config.SMTPServer)
 		if err != nil {
 			return err
 		}
@@ -58,7 +59,7 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err = client.Auth(auth); err != nil {
 			return err
 		}
-		if err = client.Mail(SMTPFrom); err != nil {
+		if err = client.Mail(config.SMTPFrom); err != nil {
 			return err
 		}
 		receiverEmails := strings.Split(receiver, ";")
@@ -80,7 +81,7 @@ func SendEmail(subject string, receiver string, content string) error {
 			return err
 		}
 	} else {
-		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
+		err = smtp.SendMail(addr, auth, config.SMTPAccount, to, mail)
 	}
 	return err
 }
--- a/common/embed-file-system.go
+++ b/common/embed-file-system.go
@@ -15,10 +15,7 @@ type embedFileSystem struct {

 func (e embedFileSystem) Exists(prefix string, path string) bool {
 	_, err := e.Open(path)
-	if err != nil {
-		return false
-	}
-	return true
+	return err == nil
 }

 func EmbedFolder(fsEmbed embed.FS, targetPath string) static.ServeFileSystem {
--- a/common/gin.go
+++ b/common/gin.go
@@ -31,3 +31,11 @@ func UnmarshalBodyReusable(c *gin.Context, v any) error {
 	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 	return nil
 }
+
+func SetEventStreamHeaders(c *gin.Context) {
+	c.Writer.Header().Set("Content-Type", "text/event-stream")
+	c.Writer.Header().Set("Cache-Control", "no-cache")
+	c.Writer.Header().Set("Connection", "keep-alive")
+	c.Writer.Header().Set("Transfer-Encoding", "chunked")
+	c.Writer.Header().Set("X-Accel-Buffering", "no")
+}
--- a/common/group-ratio.go
+++ b/common/group-ratio.go
@@ -1,6 +1,9 @@
 package common

-import "encoding/json"
+import (
+	"encoding/json"
+	"github.com/songquanpeng/one-api/common/logger"
+)

 var GroupRatio = map[string]float64{
 	"default": 1,
@@ -11,7 +14,7 @@ var GroupRatio = map[string]float64{
 func GroupRatio2JSONString() string {
 	jsonBytes, err := json.Marshal(GroupRatio)
 	if err != nil {
-		SysError("error marshalling model ratio: " + err.Error())
+		logger.SysError("error marshalling model ratio: " + err.Error())
 	}
 	return string(jsonBytes)
 }
@@ -24,7 +27,7 @@ func UpdateGroupRatioByJSONString(jsonStr string) error {
 func GetGroupRatio(name string) float64 {
 	ratio, ok := GroupRatio[name]
 	if !ok {
-		SysError("group ratio not found: " + name)
+		logger.SysError("group ratio not found: " + name)
 		return 1
 	}
 	return ratio
--- a/common/helper/helper.go
+++ b/common/helper/helper.go
@@ -0,0 +1,234 @@
+package helper
+
+import (
+	"fmt"
+	"github.com/google/uuid"
+	"github.com/songquanpeng/one-api/common/logger"
+	"html/template"
+	"log"
+	"math/rand"
+	"net"
+	"os"
+	"os/exec"
+	"runtime"
+	"strconv"
+	"strings"
+	"time"
+)
+
+func OpenBrowser(url string) {
+	var err error
+
+	switch runtime.GOOS {
+	case "linux":
+		err = exec.Command("xdg-open", url).Start()
+	case "windows":
+		err = exec.Command("rundll32", "url.dll,FileProtocolHandler", url).Start()
+	case "darwin":
+		err = exec.Command("open", url).Start()
+	}
+	if err != nil {
+		log.Println(err)
+	}
+}
+
+func GetIp() (ip string) {
+	ips, err := net.InterfaceAddrs()
+	if err != nil {
+		log.Println(err)
+		return ip
+	}
+
+	for _, a := range ips {
+		if ipNet, ok := a.(*net.IPNet); ok && !ipNet.IP.IsLoopback() {
+			if ipNet.IP.To4() != nil {
+				ip = ipNet.IP.String()
+				if strings.HasPrefix(ip, "10") {
+					return
+				}
+				if strings.HasPrefix(ip, "172") {
+					return
+				}
+				if strings.HasPrefix(ip, "192.168") {
+					return
+				}
+				ip = ""
+			}
+		}
+	}
+	return
+}
+
+var sizeKB = 1024
+var sizeMB = sizeKB * 1024
+var sizeGB = sizeMB * 1024
+
+func Bytes2Size(num int64) string {
+	numStr := ""
+	unit := "B"
+	if num/int64(sizeGB) > 1 {
+		numStr = fmt.Sprintf("%.2f", float64(num)/float64(sizeGB))
+		unit = "GB"
+	} else if num/int64(sizeMB) > 1 {
+		numStr = fmt.Sprintf("%d", int(float64(num)/float64(sizeMB)))
+		unit = "MB"
+	} else if num/int64(sizeKB) > 1 {
+		numStr = fmt.Sprintf("%d", int(float64(num)/float64(sizeKB)))
+		unit = "KB"
+	} else {
+		numStr = fmt.Sprintf("%d", num)
+	}
+	return numStr + " " + unit
+}
+
+func Seconds2Time(num int) (time string) {
+	if num/31104000 > 0 {
+		time += strconv.Itoa(num/31104000) + " 年 "
+		num %= 31104000
+	}
+	if num/2592000 > 0 {
+		time += strconv.Itoa(num/2592000) + " 个月 "
+		num %= 2592000
+	}
+	if num/86400 > 0 {
+		time += strconv.Itoa(num/86400) + " 天 "
+		num %= 86400
+	}
+	if num/3600 > 0 {
+		time += strconv.Itoa(num/3600) + " 小时 "
+		num %= 3600
+	}
+	if num/60 > 0 {
+		time += strconv.Itoa(num/60) + " 分钟 "
+		num %= 60
+	}
+	time += strconv.Itoa(num) + " 秒"
+	return
+}
+
+func Interface2String(inter interface{}) string {
+	switch inter := inter.(type) {
+	case string:
+		return inter
+	case int:
+		return fmt.Sprintf("%d", inter)
+	case float64:
+		return fmt.Sprintf("%f", inter)
+	}
+	return "Not Implemented"
+}
+
+func UnescapeHTML(x string) interface{} {
+	return template.HTML(x)
+}
+
+func IntMax(a int, b int) int {
+	if a >= b {
+		return a
+	} else {
+		return b
+	}
+}
+
+func GetUUID() string {
+	code := uuid.New().String()
+	code = strings.Replace(code, "-", "", -1)
+	return code
+}
+
+const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+const keyNumbers = "0123456789"
+
+func init() {
+	rand.Seed(time.Now().UnixNano())
+}
+
+func GenerateKey() string {
+	rand.Seed(time.Now().UnixNano())
+	key := make([]byte, 48)
+	for i := 0; i < 16; i++ {
+		key[i] = keyChars[rand.Intn(len(keyChars))]
+	}
+	uuid_ := GetUUID()
+	for i := 0; i < 32; i++ {
+		c := uuid_[i]
+		if i%2 == 0 && c >= 'a' && c <= 'z' {
+			c = c - 'a' + 'A'
+		}
+		key[i+16] = c
+	}
+	return string(key)
+}
+
+func GetRandomString(length int) string {
+	rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyChars[rand.Intn(len(keyChars))]
+	}
+	return string(key)
+}
+
+func GetRandomNumberString(length int) string {
+	rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyNumbers[rand.Intn(len(keyNumbers))]
+	}
+	return string(key)
+}
+
+func GetTimestamp() int64 {
+	return time.Now().Unix()
+}
+
+func GetTimeString() string {
+	now := time.Now()
+	return fmt.Sprintf("%s%d", now.Format("20060102150405"), now.UnixNano()%1e9)
+}
+
+func Max(a int, b int) int {
+	if a >= b {
+		return a
+	} else {
+		return b
+	}
+}
+
+func GetOrDefaultEnvInt(env string, defaultValue int) int {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.Atoi(os.Getenv(env))
+	if err != nil {
+		logger.SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return num
+}
+
+func GetOrDefaultEnvString(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}
+
+func AssignOrDefault(value string, defaultValue string) string {
+	if len(value) != 0 {
+		return value
+	}
+	return defaultValue
+}
+
+func MessageWithRequestId(message string, id string) string {
+	return fmt.Sprintf("%s (request id: %s)", message, id)
+}
+
+func String2Int(str string) int {
+	num, err := strconv.Atoi(str)
+	if err != nil {
+		return 0
+	}
+	return num
+}
--- a/common/image/image_test.go
+++ b/common/image/image_test.go
@@ -12,7 +12,7 @@ import (
 	"strings"
 	"testing"

-	img "one-api/common/image"
+	img "github.com/songquanpeng/one-api/common/image"

 	"github.com/stretchr/testify/assert"
 	_ "golang.org/x/image/webp"
--- a/common/init.go
+++ b/common/init.go
@@ -3,6 +3,8 @@ package common
 import (
 	"flag"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
 	"log"
 	"os"
 	"path/filepath"
@@ -37,9 +39,9 @@ func init() {

 	if os.Getenv("SESSION_SECRET") != "" {
 		if os.Getenv("SESSION_SECRET") == "random_string" {
-			SysError("SESSION_SECRET is set to an example value, please change it to a random string.")
+			logger.SysError("SESSION_SECRET is set to an example value, please change it to a random string.")
 		} else {
-			SessionSecret = os.Getenv("SESSION_SECRET")
+			config.SessionSecret = os.Getenv("SESSION_SECRET")
 		}
 	}
 	if os.Getenv("SQLITE_PATH") != "" {
@@ -57,5 +59,6 @@ func init() {
 				log.Fatal(err)
 			}
 		}
+		logger.LogDir = *LogDir
 	}
 }
--- a/common/logger/constants.go
+++ b/common/logger/constants.go
@@ -0,0 +1,7 @@
+package logger
+
+const (
+	RequestIdKey = "X-Oneapi-Request-Id"
+)
+
+var LogDir string
--- a/common/logger/logger.go
+++ b/common/logger/logger.go
@@ -1,4 +1,4 @@
-package common
+package logger

 import (
 	"context"
@@ -25,7 +25,7 @@ var setupLogLock sync.Mutex
 var setupLogWorking bool

 func SetupLogger() {
-	if *LogDir != "" {
+	if LogDir != "" {
 		ok := setupLogLock.TryLock()
 		if !ok {
 			log.Println("setup log is already working")
@@ -35,7 +35,7 @@ func SetupLogger() {
 			setupLogLock.Unlock()
 			setupLogWorking = false
 		}()
-		logPath := filepath.Join(*LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102")))
+		logPath := filepath.Join(LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102")))
 		fd, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0644)
 		if err != nil {
 			log.Fatal("failed to open log file")
@@ -55,18 +55,30 @@ func SysError(s string) {
 	_, _ = fmt.Fprintf(gin.DefaultErrorWriter, "[SYS] %v | %s \n", t.Format("2006/01/02 - 15:04:05"), s)
 }

-func LogInfo(ctx context.Context, msg string) {
+func Info(ctx context.Context, msg string) {
 	logHelper(ctx, loggerINFO, msg)
 }

-func LogWarn(ctx context.Context, msg string) {
+func Warn(ctx context.Context, msg string) {
 	logHelper(ctx, loggerWarn, msg)
 }

-func LogError(ctx context.Context, msg string) {
+func Error(ctx context.Context, msg string) {
 	logHelper(ctx, loggerError, msg)
 }

+func Infof(ctx context.Context, format string, a ...any) {
+	Info(ctx, fmt.Sprintf(format, a...))
+}
+
+func Warnf(ctx context.Context, format string, a ...any) {
+	Warn(ctx, fmt.Sprintf(format, a...))
+}
+
+func Errorf(ctx context.Context, format string, a ...any) {
+	Error(ctx, fmt.Sprintf(format, a...))
+}
+
 func logHelper(ctx context.Context, level string, msg string) {
 	writer := gin.DefaultErrorWriter
 	if level == loggerINFO {
@@ -90,11 +102,3 @@ func FatalLog(v ...any) {
 	_, _ = fmt.Fprintf(gin.DefaultErrorWriter, "[FATAL] %v | %v \n", t.Format("2006/01/02 - 15:04:05"), v)
 	os.Exit(1)
 }
-
-func LogQuota(quota int) string {
-	if DisplayInCurrencyEnabled {
-		return fmt.Sprintf("＄%.6f 额度", float64(quota)/QuotaPerUnit)
-	} else {
-		return fmt.Sprintf("%d 点额度", quota)
-	}
-}
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -2,6 +2,7 @@ package common

 import (
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/logger"
 	"strings"
 	"time"
 )
@@ -29,6 +30,12 @@ var DalleImagePromptLengthLimitations = map[string]int{
 	"dall-e-3": 4000,
 }

+const (
+	USD2RMB = 7
+	USD     = 500 // $0.002 = 1 -> $1 = 500
+	RMB     = USD / USD2RMB
+)
+
 // ModelRatio
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
@@ -37,52 +44,60 @@ var DalleImagePromptLengthLimitations = map[string]int{
 // 1 === $0.002 / 1K tokens
 // 1 === ￥0.014 / 1k tokens
 var ModelRatio = map[string]float64{
-	"gpt-4":                     15,
-	"gpt-4-0314":                15,
-	"gpt-4-0613":                15,
-	"gpt-4-32k":                 30,
-	"gpt-4-32k-0314":            30,
-	"gpt-4-32k-0613":            30,
-	"gpt-4-1106-preview":        5,    // $0.01 / 1K tokens
-	"gpt-4-vision-preview":      5,    // $0.01 / 1K tokens
-	"gpt-3.5-turbo":             0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-0301":        0.75,
-	"gpt-3.5-turbo-0613":        0.75,
-	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
-	"gpt-3.5-turbo-16k-0613":    1.5,
-	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-1106":        0.5,  // $0.001 / 1K tokens
-	"davinci-002":               1,    // $0.002 / 1K tokens
-	"babbage-002":               0.2,  // $0.0004 / 1K tokens
-	"text-ada-001":              0.2,
-	"text-babbage-001":          0.25,
-	"text-curie-001":            1,
-	"text-davinci-002":          10,
-	"text-davinci-003":          10,
-	"text-davinci-edit-001":     10,
-	"code-davinci-edit-001":     10,
-	"whisper-1":                 15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
-	"tts-1":                     7.5, // $0.015 / 1K characters
-	"tts-1-1106":                7.5,
-	"tts-1-hd":                  15, // $0.030 / 1K characters
-	"tts-1-hd-1106":             15,
-	"davinci":                   10,
-	"curie":                     10,
-	"babbage":                   10,
-	"ada":                       10,
-	"text-embedding-ada-002":    0.05,
-	"text-search-ada-doc-001":   10,
-	"text-moderation-stable":    0.1,
-	"text-moderation-latest":    0.1,
-	"dall-e-2":                  8,      // $0.016 - $0.020 / image
-	"dall-e-3":                  20,     // $0.040 - $0.120 / image
-	"claude-instant-1":          0.815,  // $1.63 / 1M tokens
-	"claude-2":                  5.51,   // $11.02 / 1M tokens
-	"claude-2.0":                5.51,   // $11.02 / 1M tokens
-	"claude-2.1":                5.51,   // $11.02 / 1M tokens
-	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
-	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
+	// https://openai.com/pricing
+	"gpt-4":                   15,
+	"gpt-4-0314":              15,
+	"gpt-4-0613":              15,
+	"gpt-4-32k":               30,
+	"gpt-4-32k-0314":          30,
+	"gpt-4-32k-0613":          30,
+	"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-vision-preview":    5,    // $0.01 / 1K tokens
+	"gpt-3.5-turbo":           0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-0301":      0.75,
+	"gpt-3.5-turbo-0613":      0.75,
+	"gpt-3.5-turbo-16k":       1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k-0613":  1.5,
+	"gpt-3.5-turbo-instruct":  0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":      0.5,  // $0.001 / 1K tokens
+	"gpt-3.5-turbo-0125":      0.25, // $0.0005 / 1K tokens
+	"davinci-002":             1,    // $0.002 / 1K tokens
+	"babbage-002":             0.2,  // $0.0004 / 1K tokens
+	"text-ada-001":            0.2,
+	"text-babbage-001":        0.25,
+	"text-curie-001":          1,
+	"text-davinci-002":        10,
+	"text-davinci-003":        10,
+	"text-davinci-edit-001":   10,
+	"code-davinci-edit-001":   10,
+	"whisper-1":               15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"tts-1":                   7.5, // $0.015 / 1K characters
+	"tts-1-1106":              7.5,
+	"tts-1-hd":                15, // $0.030 / 1K characters
+	"tts-1-hd-1106":           15,
+	"davinci":                 10,
+	"curie":                   10,
+	"babbage":                 10,
+	"ada":                     10,
+	"text-embedding-ada-002":  0.05,
+	"text-embedding-3-small":  0.01,
+	"text-embedding-3-large":  0.065,
+	"text-search-ada-doc-001": 10,
+	"text-moderation-stable":  0.1,
+	"text-moderation-latest":  0.1,
+	"dall-e-2":                8,     // $0.016 - $0.020 / image
+	"dall-e-3":                20,    // $0.040 - $0.120 / image
+	"claude-instant-1":        0.815, // $1.63 / 1M tokens
+	"claude-2":                5.51,  // $11.02 / 1M tokens
+	"claude-2.0":              5.51,  // $11.02 / 1M tokens
+	"claude-2.1":              5.51,  // $11.02 / 1M tokens
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
+	"ERNIE-Bot":                 0.8572,     // ￥0.012 / 1k tokens
+	"ERNIE-Bot-turbo":           0.5715,     // ￥0.008 / 1k tokens
+	"ERNIE-Bot-4":               0.12 * RMB, // ￥0.12 / 1k tokens
+	"ERNIE-Bot-8k":              0.024 * RMB,
 	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                    1,
 	"gemini-pro":                1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
@@ -97,17 +112,27 @@ var ModelRatio = map[string]float64{
 	"qwen-max-longcontext":      1.4286, // ￥0.02 / 1k tokens
 	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
 	"SparkDesk":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v1.1":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v2.1":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
 	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
 	"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
 	"hunyuan":                   7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
+	"ChatStd":                   0.01 * RMB,
+	"ChatPro":                   0.1 * RMB,
+	// https://platform.moonshot.cn/pricing
+	"moonshot-v1-8k":   0.012 * RMB,
+	"moonshot-v1-32k":  0.024 * RMB,
+	"moonshot-v1-128k": 0.06 * RMB,
 }

 func ModelRatio2JSONString() string {
 	jsonBytes, err := json.Marshal(ModelRatio)
 	if err != nil {
-		SysError("error marshalling model ratio: " + err.Error())
+		logger.SysError("error marshalling model ratio: " + err.Error())
 	}
 	return string(jsonBytes)
 }
@@ -123,14 +148,37 @@ func GetModelRatio(name string) float64 {
 	}
 	ratio, ok := ModelRatio[name]
 	if !ok {
-		SysError("model ratio not found: " + name)
+		logger.SysError("model ratio not found: " + name)
 		return 30
 	}
 	return ratio
 }

+var CompletionRatio = map[string]float64{}
+
+func CompletionRatio2JSONString() string {
+	jsonBytes, err := json.Marshal(CompletionRatio)
+	if err != nil {
+		logger.SysError("error marshalling completion ratio: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func UpdateCompletionRatioByJSONString(jsonStr string) error {
+	CompletionRatio = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &CompletionRatio)
+}
+
 func GetCompletionRatio(name string) float64 {
+	if ratio, ok := CompletionRatio[name]; ok {
+		return ratio
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
+		if strings.HasSuffix(name, "0125") {
+			// https://openai.com/blog/new-embedding-models-and-api-updates
+			// Updated GPT-3.5 Turbo model and lower pricing
+			return 3
+		}
 		if strings.HasSuffix(name, "1106") {
 			return 2
 		}
--- a/common/redis.go
+++ b/common/redis.go
@@ -3,6 +3,7 @@ package common
 import (
 	"context"
 	"github.com/go-redis/redis/v8"
+	"github.com/songquanpeng/one-api/common/logger"
 	"os"
 	"time"
 )
@@ -14,18 +15,18 @@ var RedisEnabled = true
 func InitRedisClient() (err error) {
 	if os.Getenv("REDIS_CONN_STRING") == "" {
 		RedisEnabled = false
-		SysLog("REDIS_CONN_STRING not set, Redis is not enabled")
+		logger.SysLog("REDIS_CONN_STRING not set, Redis is not enabled")
 		return nil
 	}
 	if os.Getenv("SYNC_FREQUENCY") == "" {
 		RedisEnabled = false
-		SysLog("SYNC_FREQUENCY not set, Redis is disabled")
+		logger.SysLog("SYNC_FREQUENCY not set, Redis is disabled")
 		return nil
 	}
-	SysLog("Redis is enabled")
+	logger.SysLog("Redis is enabled")
 	opt, err := redis.ParseURL(os.Getenv("REDIS_CONN_STRING"))
 	if err != nil {
-		FatalLog("failed to parse Redis connection string: " + err.Error())
+		logger.FatalLog("failed to parse Redis connection string: " + err.Error())
 	}
 	RDB = redis.NewClient(opt)

@@ -34,7 +35,7 @@ func InitRedisClient() (err error) {

 	_, err = RDB.Ping(ctx).Result()
 	if err != nil {
-		FatalLog("Redis ping test failed: " + err.Error())
+		logger.FatalLog("Redis ping test failed: " + err.Error())
 	}
 	return err
 }
@@ -42,7 +43,7 @@ func InitRedisClient() (err error) {
 func ParseRedisOption() *redis.Options {
 	opt, err := redis.ParseURL(os.Getenv("REDIS_CONN_STRING"))
 	if err != nil {
-		FatalLog("failed to parse Redis connection string: " + err.Error())
+		logger.FatalLog("failed to parse Redis connection string: " + err.Error())
 	}
 	return opt
 }
--- a/common/utils.go
+++ b/common/utils.go
@@ -2,215 +2,13 @@ package common

 import (
 	"fmt"
-	"github.com/google/uuid"
-	"html/template"
-	"log"
-	"math/rand"
-	"net"
-	"os"
-	"os/exec"
-	"runtime"
-	"strconv"
-	"strings"
-	"time"
+	"github.com/songquanpeng/one-api/common/config"
 )

-func OpenBrowser(url string) {
-	var err error
-
-	switch runtime.GOOS {
-	case "linux":
-		err = exec.Command("xdg-open", url).Start()
-	case "windows":
-		err = exec.Command("rundll32", "url.dll,FileProtocolHandler", url).Start()
-	case "darwin":
-		err = exec.Command("open", url).Start()
-	}
-	if err != nil {
-		log.Println(err)
-	}
-}
-
-func GetIp() (ip string) {
-	ips, err := net.InterfaceAddrs()
-	if err != nil {
-		log.Println(err)
-		return ip
-	}
-
-	for _, a := range ips {
-		if ipNet, ok := a.(*net.IPNet); ok && !ipNet.IP.IsLoopback() {
-			if ipNet.IP.To4() != nil {
-				ip = ipNet.IP.String()
-				if strings.HasPrefix(ip, "10") {
-					return
-				}
-				if strings.HasPrefix(ip, "172") {
-					return
-				}
-				if strings.HasPrefix(ip, "192.168") {
-					return
-				}
-				ip = ""
-			}
-		}
-	}
-	return
-}
-
-var sizeKB = 1024
-var sizeMB = sizeKB * 1024
-var sizeGB = sizeMB * 1024
-
-func Bytes2Size(num int64) string {
-	numStr := ""
-	unit := "B"
-	if num/int64(sizeGB) > 1 {
-		numStr = fmt.Sprintf("%.2f", float64(num)/float64(sizeGB))
-		unit = "GB"
-	} else if num/int64(sizeMB) > 1 {
-		numStr = fmt.Sprintf("%d", int(float64(num)/float64(sizeMB)))
-		unit = "MB"
-	} else if num/int64(sizeKB) > 1 {
-		numStr = fmt.Sprintf("%d", int(float64(num)/float64(sizeKB)))
-		unit = "KB"
+func LogQuota(quota int) string {
+	if config.DisplayInCurrencyEnabled {
+		return fmt.Sprintf("＄%.6f 额度", float64(quota)/config.QuotaPerUnit)
 	} else {
-		numStr = fmt.Sprintf("%d", num)
-	}
-	return numStr + " " + unit
-}
-
-func Seconds2Time(num int) (time string) {
-	if num/31104000 > 0 {
-		time += strconv.Itoa(num/31104000) + " 年 "
-		num %= 31104000
-	}
-	if num/2592000 > 0 {
-		time += strconv.Itoa(num/2592000) + " 个月 "
-		num %= 2592000
-	}
-	if num/86400 > 0 {
-		time += strconv.Itoa(num/86400) + " 天 "
-		num %= 86400
-	}
-	if num/3600 > 0 {
-		time += strconv.Itoa(num/3600) + " 小时 "
-		num %= 3600
-	}
-	if num/60 > 0 {
-		time += strconv.Itoa(num/60) + " 分钟 "
-		num %= 60
-	}
-	time += strconv.Itoa(num) + " 秒"
-	return
-}
-
-func Interface2String(inter interface{}) string {
-	switch inter.(type) {
-	case string:
-		return inter.(string)
-	case int:
-		return fmt.Sprintf("%d", inter.(int))
-	case float64:
-		return fmt.Sprintf("%f", inter.(float64))
-	}
-	return "Not Implemented"
-}
-
-func UnescapeHTML(x string) interface{} {
-	return template.HTML(x)
-}
-
-func IntMax(a int, b int) int {
-	if a >= b {
-		return a
-	} else {
-		return b
+		return fmt.Sprintf("%d 点额度", quota)
 	}
 }
-
-func GetUUID() string {
-	code := uuid.New().String()
-	code = strings.Replace(code, "-", "", -1)
-	return code
-}
-
-const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
-
-func init() {
-	rand.Seed(time.Now().UnixNano())
-}
-
-func GenerateKey() string {
-	rand.Seed(time.Now().UnixNano())
-	key := make([]byte, 48)
-	for i := 0; i < 16; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
-	}
-	uuid_ := GetUUID()
-	for i := 0; i < 32; i++ {
-		c := uuid_[i]
-		if i%2 == 0 && c >= 'a' && c <= 'z' {
-			c = c - 'a' + 'A'
-		}
-		key[i+16] = c
-	}
-	return string(key)
-}
-
-func GetRandomString(length int) string {
-	rand.Seed(time.Now().UnixNano())
-	key := make([]byte, length)
-	for i := 0; i < length; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
-	}
-	return string(key)
-}
-
-func GetTimestamp() int64 {
-	return time.Now().Unix()
-}
-
-func GetTimeString() string {
-	now := time.Now()
-	return fmt.Sprintf("%s%d", now.Format("20060102150405"), now.UnixNano()%1e9)
-}
-
-func Max(a int, b int) int {
-	if a >= b {
-		return a
-	} else {
-		return b
-	}
-}
-
-func GetOrDefault(env string, defaultValue int) int {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	num, err := strconv.Atoi(os.Getenv(env))
-	if err != nil {
-		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
-		return defaultValue
-	}
-	return num
-}
-
-func GetOrDefaultString(env string, defaultValue string) string {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	return os.Getenv(env)
-}
-
-func MessageWithRequestId(message string, id string) string {
-	return fmt.Sprintf("%s (request id: %s)", message, id)
-}
-
-func String2Int(str string) int {
-	num, err := strconv.Atoi(str)
-	if err != nil {
-		return 0
-	}
-	return num
-}
--- a/controller/billing.go
+++ b/controller/billing.go
@@ -2,8 +2,9 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
-	"one-api/common"
-	"one-api/model"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/model"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
 )

 func GetSubscription(c *gin.Context) {
@@ -12,7 +13,7 @@ func GetSubscription(c *gin.Context) {
 	var err error
 	var token *model.Token
 	var expiredTime int64
-	if common.DisplayTokenStatEnabled {
+	if config.DisplayTokenStatEnabled {
 		tokenId := c.GetInt("token_id")
 		token, err = model.GetTokenById(tokenId)
 		expiredTime = token.ExpiredTime
@@ -21,25 +22,27 @@ func GetSubscription(c *gin.Context) {
 	} else {
 		userId := c.GetInt("id")
 		remainQuota, err = model.GetUserQuota(userId)
-		usedQuota, err = model.GetUserUsedQuota(userId)
+		if err != nil {
+			usedQuota, err = model.GetUserUsedQuota(userId)
+		}
 	}
 	if expiredTime <= 0 {
 		expiredTime = 0
 	}
 	if err != nil {
-		openAIError := OpenAIError{
+		Error := relaymodel.Error{
 			Message: err.Error(),
 			Type:    "upstream_error",
 		}
 		c.JSON(200, gin.H{
-			"error": openAIError,
+			"error": Error,
 		})
 		return
 	}
 	quota := remainQuota + usedQuota
 	amount := float64(quota)
-	if common.DisplayInCurrencyEnabled {
-		amount /= common.QuotaPerUnit
+	if config.DisplayInCurrencyEnabled {
+		amount /= config.QuotaPerUnit
 	}
 	if token != nil && token.UnlimitedQuota {
 		amount = 100000000
@@ -60,7 +63,7 @@ func GetUsage(c *gin.Context) {
 	var quota int
 	var err error
 	var token *model.Token
-	if common.DisplayTokenStatEnabled {
+	if config.DisplayTokenStatEnabled {
 		tokenId := c.GetInt("token_id")
 		token, err = model.GetTokenById(tokenId)
 		quota = token.UsedQuota
@@ -69,18 +72,18 @@ func GetUsage(c *gin.Context) {
 		quota, err = model.GetUserUsedQuota(userId)
 	}
 	if err != nil {
-		openAIError := OpenAIError{
+		Error := relaymodel.Error{
 			Message: err.Error(),
 			Type:    "one_api_error",
 		}
 		c.JSON(200, gin.H{
-			"error": openAIError,
+			"error": Error,
 		})
 		return
 	}
 	amount := float64(quota)
-	if common.DisplayInCurrencyEnabled {
-		amount /= common.QuotaPerUnit
+	if config.DisplayInCurrencyEnabled {
+		amount /= config.QuotaPerUnit
 	}
 	usage := OpenAIUsageResponse{
 		Object:     "list",
--- a/controller/channel-billing.go
+++ b/controller/channel-billing.go
@@ -4,10 +4,13 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/model"
+	"github.com/songquanpeng/one-api/relay/util"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"

@@ -92,7 +95,7 @@ func GetResponseBody(method, url string, channel *model.Channel, headers http.He
 	for k := range headers {
 		req.Header.Add(k, headers.Get(k))
 	}
-	res, err := httpClient.Do(req)
+	res, err := util.HTTPClient.Do(req)
 	if err != nil {
 		return nil, err
 	}
@@ -313,7 +316,7 @@ func updateAllChannelsBalance() error {
 				disableChannel(channel.Id, channel.Name, "余额不足")
 			}
 		}
-		time.Sleep(common.RequestInterval)
+		time.Sleep(config.RequestInterval)
 	}
 	return nil
 }
@@ -338,8 +341,8 @@ func UpdateAllChannelsBalance(c *gin.Context) {
 func AutomaticallyUpdateChannels(frequency int) {
 	for {
 		time.Sleep(time.Duration(frequency) * time.Minute)
-		common.SysLog("updating all channels")
+		logger.SysLog("updating all channels")
 		_ = updateAllChannelsBalance()
-		common.SysLog("channels update done")
+		logger.SysLog("channels update done")
 	}
 }
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -5,10 +5,18 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/model"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/helper"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
+	"net/http/httptest"
+	"net/url"
 	"strconv"
 	"sync"
 	"time"
@@ -16,87 +24,13 @@ import (
 	"github.com/gin-gonic/gin"
 )

-func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
-	switch channel.Type {
-	case common.ChannelTypePaLM:
-		fallthrough
-	case common.ChannelTypeGemini:
-		fallthrough
-	case common.ChannelTypeAnthropic:
-		fallthrough
-	case common.ChannelTypeBaidu:
-		fallthrough
-	case common.ChannelTypeZhipu:
-		fallthrough
-	case common.ChannelTypeAli:
-		fallthrough
-	case common.ChannelType360:
-		fallthrough
-	case common.ChannelTypeXunfei:
-		return errors.New("该渠道类型当前版本不支持测试，请手动测试"), nil
-	case common.ChannelTypeAzure:
-		request.Model = "gpt-35-turbo"
-		defer func() {
-			if err != nil {
-				err = errors.New("请确保已在 Azure 上创建了 gpt-35-turbo 模型，并且 apiVersion 已正确填写！")
-			}
-		}()
-	default:
-		request.Model = "gpt-3.5-turbo"
-	}
-	requestURL := common.ChannelBaseURLs[channel.Type]
-	if channel.Type == common.ChannelTypeAzure {
-		requestURL = getFullRequestURL(channel.GetBaseURL(), fmt.Sprintf("/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", request.Model), channel.Type)
-	} else {
-		if baseURL := channel.GetBaseURL(); len(baseURL) > 0 {
-			requestURL = baseURL
-		}
-
-		requestURL = getFullRequestURL(requestURL, "/v1/chat/completions", channel.Type)
-	}
-	jsonData, err := json.Marshal(request)
-	if err != nil {
-		return err, nil
-	}
-	req, err := http.NewRequest("POST", requestURL, bytes.NewBuffer(jsonData))
-	if err != nil {
-		return err, nil
-	}
-	if channel.Type == common.ChannelTypeAzure {
-		req.Header.Set("api-key", channel.Key)
-	} else {
-		req.Header.Set("Authorization", "Bearer "+channel.Key)
-	}
-	req.Header.Set("Content-Type", "application/json")
-	resp, err := httpClient.Do(req)
-	if err != nil {
-		return err, nil
-	}
-	defer resp.Body.Close()
-	var response TextResponse
-	body, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return err, nil
-	}
-	err = json.Unmarshal(body, &response)
-	if err != nil {
-		return fmt.Errorf("Error: %s\nResp body: %s", err, body), nil
-	}
-	if response.Usage.CompletionTokens == 0 {
-		if response.Error.Message == "" {
-			response.Error.Message = "补全 tokens 非预期返回 0"
-		}
-		return errors.New(fmt.Sprintf("type %s, code %v, message %s", response.Error.Type, response.Error.Code, response.Error.Message)), &response.Error
-	}
-	return nil, nil
-}
-
-func buildTestRequest() *ChatRequest {
-	testRequest := &ChatRequest{
-		Model:     "", // this will be set later
+func buildTestRequest() *relaymodel.GeneralOpenAIRequest {
+	testRequest := &relaymodel.GeneralOpenAIRequest{
 		MaxTokens: 1,
+		Stream:    false,
+		Model:     "gpt-3.5-turbo",
 	}
-	testMessage := Message{
+	testMessage := relaymodel.Message{
 		Role:    "user",
 		Content: "hi",
 	}
@@ -104,6 +38,65 @@ func buildTestRequest() *ChatRequest {
 	return testRequest
 }

+func testChannel(channel *model.Channel) (err error, openaiErr *relaymodel.Error) {
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+	c.Request = &http.Request{
+		Method: "POST",
+		URL:    &url.URL{Path: "/v1/chat/completions"},
+		Body:   nil,
+		Header: make(http.Header),
+	}
+	c.Request.Header.Set("Authorization", "Bearer "+channel.Key)
+	c.Request.Header.Set("Content-Type", "application/json")
+	c.Set("channel", channel.Type)
+	c.Set("base_url", channel.GetBaseURL())
+	meta := util.GetRelayMeta(c)
+	apiType := constant.ChannelType2APIType(channel.Type)
+	adaptor := helper.GetAdaptor(apiType)
+	if adaptor == nil {
+		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
+	}
+	adaptor.Init(meta)
+	modelName := adaptor.GetModelList()[0]
+	request := buildTestRequest()
+	request.Model = modelName
+	meta.OriginModelName, meta.ActualModelName = modelName, modelName
+	convertedRequest, err := adaptor.ConvertRequest(c, constant.RelayModeChatCompletions, request)
+	if err != nil {
+		return err, nil
+	}
+	jsonData, err := json.Marshal(convertedRequest)
+	if err != nil {
+		return err, nil
+	}
+	requestBody := bytes.NewBuffer(jsonData)
+	c.Request.Body = io.NopCloser(requestBody)
+	resp, err := adaptor.DoRequest(c, meta, requestBody)
+	if err != nil {
+		return err, nil
+	}
+	if resp.StatusCode != http.StatusOK {
+		err := util.RelayErrorHandler(resp)
+		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), &err.Error
+	}
+	usage, respErr := adaptor.DoResponse(c, resp, meta)
+	if respErr != nil {
+		return fmt.Errorf("%s", respErr.Error.Message), &respErr.Error
+	}
+	if usage == nil {
+		return errors.New("usage is nil"), nil
+	}
+	result := w.Result()
+	// print result.Body
+	respBody, err := io.ReadAll(result.Body)
+	if err != nil {
+		return err, nil
+	}
+	logger.SysLog(fmt.Sprintf("testing channel #%d, response: \n%s", channel.Id, string(respBody)))
+	return nil, nil
+}
+
 func TestChannel(c *gin.Context) {
 	id, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
@@ -121,9 +114,8 @@ func TestChannel(c *gin.Context) {
 		})
 		return
 	}
-	testRequest := buildTestRequest()
 	tik := time.Now()
-	err, _ = testChannel(channel, *testRequest)
+	err, _ = testChannel(channel)
 	tok := time.Now()
 	milliseconds := tok.Sub(tik).Milliseconds()
 	go channel.UpdateResponseTime(milliseconds)
@@ -148,12 +140,12 @@ var testAllChannelsLock sync.Mutex
 var testAllChannelsRunning bool = false

 func notifyRootUser(subject string, content string) {
-	if common.RootUserEmail == "" {
-		common.RootUserEmail = model.GetRootUserEmail()
+	if config.RootUserEmail == "" {
+		config.RootUserEmail = model.GetRootUserEmail()
 	}
-	err := common.SendEmail(subject, common.RootUserEmail, content)
+	err := common.SendEmail(subject, config.RootUserEmail, content)
 	if err != nil {
-		common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
+		logger.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
 	}
 }

@@ -174,8 +166,8 @@ func enableChannel(channelId int, channelName string) {
 }

 func testAllChannels(notify bool) error {
-	if common.RootUserEmail == "" {
-		common.RootUserEmail = model.GetRootUserEmail()
+	if config.RootUserEmail == "" {
+		config.RootUserEmail = model.GetRootUserEmail()
 	}
 	testAllChannelsLock.Lock()
 	if testAllChannelsRunning {
@@ -188,8 +180,7 @@ func testAllChannels(notify bool) error {
 	if err != nil {
 		return err
 	}
-	testRequest := buildTestRequest()
-	var disableThreshold = int64(common.ChannelDisableThreshold * 1000)
+	var disableThreshold = int64(config.ChannelDisableThreshold * 1000)
 	if disableThreshold == 0 {
 		disableThreshold = 10000000 // a impossible value
 	}
@@ -197,29 +188,29 @@ func testAllChannels(notify bool) error {
 		for _, channel := range channels {
 			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
-			err, openaiErr := testChannel(channel, *testRequest)
+			err, openaiErr := testChannel(channel)
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
 			if isChannelEnabled && milliseconds > disableThreshold {
 				err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if isChannelEnabled && shouldDisableChannel(openaiErr, -1) {
+			if isChannelEnabled && util.ShouldDisableChannel(openaiErr, -1) {
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if !isChannelEnabled && shouldEnableChannel(err, openaiErr) {
+			if !isChannelEnabled && util.ShouldEnableChannel(err, openaiErr) {
 				enableChannel(channel.Id, channel.Name)
 			}
 			channel.UpdateResponseTime(milliseconds)
-			time.Sleep(common.RequestInterval)
+			time.Sleep(config.RequestInterval)
 		}
 		testAllChannelsLock.Lock()
 		testAllChannelsRunning = false
 		testAllChannelsLock.Unlock()
 		if notify {
-			err := common.SendEmail("通道测试完成", common.RootUserEmail, "通道测试完成，如果没有收到禁用通知，说明所有通道都正常")
+			err := common.SendEmail("通道测试完成", config.RootUserEmail, "通道测试完成，如果没有收到禁用通知，说明所有通道都正常")
 			if err != nil {
-				common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
+				logger.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
 			}
 		}
 	}()
@@ -245,8 +236,8 @@ func TestAllChannels(c *gin.Context) {
 func AutomaticallyTestChannels(frequency int) {
 	for {
 		time.Sleep(time.Duration(frequency) * time.Minute)
-		common.SysLog("testing all channels")
+		logger.SysLog("testing all channels")
 		_ = testAllChannels(false)
-		common.SysLog("channel test finished")
+		logger.SysLog("channel test finished")
 	}
 }
--- a/controller/channel.go
+++ b/controller/channel.go
@@ -2,9 +2,10 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"strings"
 )
@@ -14,7 +15,7 @@ func GetAllChannels(c *gin.Context) {
 	if p < 0 {
 		p = 0
 	}
-	channels, err := model.GetAllChannels(p*common.ItemsPerPage, common.ItemsPerPage, false)
+	channels, err := model.GetAllChannels(p*config.ItemsPerPage, config.ItemsPerPage, false)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -83,7 +84,7 @@ func AddChannel(c *gin.Context) {
 		})
 		return
 	}
-	channel.CreatedTime = common.GetTimestamp()
+	channel.CreatedTime = helper.GetTimestamp()
 	keys := strings.Split(channel.Key, "\n")
 	channels := make([]model.Channel, 0, len(keys))
 	for _, key := range keys {
--- a/controller/github.go
+++ b/controller/github.go
@@ -7,9 +7,12 @@ import (
 	"fmt"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"
 )
@@ -30,7 +33,7 @@ func getGitHubUserInfoByCode(code string) (*GitHubUser, error) {
 	if code == "" {
 		return nil, errors.New("无效的参数")
 	}
-	values := map[string]string{"client_id": common.GitHubClientId, "client_secret": common.GitHubClientSecret, "code": code}
+	values := map[string]string{"client_id": config.GitHubClientId, "client_secret": config.GitHubClientSecret, "code": code}
 	jsonData, err := json.Marshal(values)
 	if err != nil {
 		return nil, err
@@ -46,7 +49,7 @@ func getGitHubUserInfoByCode(code string) (*GitHubUser, error) {
 	}
 	res, err := client.Do(req)
 	if err != nil {
-		common.SysLog(err.Error())
+		logger.SysLog(err.Error())
 		return nil, errors.New("无法连接至 GitHub 服务器，请稍后重试！")
 	}
 	defer res.Body.Close()
@@ -62,7 +65,7 @@ func getGitHubUserInfoByCode(code string) (*GitHubUser, error) {
 	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", oAuthResponse.AccessToken))
 	res2, err := client.Do(req)
 	if err != nil {
-		common.SysLog(err.Error())
+		logger.SysLog(err.Error())
 		return nil, errors.New("无法连接至 GitHub 服务器，请稍后重试！")
 	}
 	defer res2.Body.Close()
@@ -93,7 +96,7 @@ func GitHubOAuth(c *gin.Context) {
 		return
 	}

-	if !common.GitHubOAuthEnabled {
+	if !config.GitHubOAuthEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "管理员未开启通过 GitHub 登录以及注册",
@@ -122,7 +125,7 @@ func GitHubOAuth(c *gin.Context) {
 			return
 		}
 	} else {
-		if common.RegisterEnabled {
+		if config.RegisterEnabled {
 			user.Username = "github_" + strconv.Itoa(model.GetMaxUserId()+1)
 			if githubUser.Name != "" {
 				user.DisplayName = githubUser.Name
@@ -160,7 +163,7 @@ func GitHubOAuth(c *gin.Context) {
 }

 func GitHubBind(c *gin.Context) {
-	if !common.GitHubOAuthEnabled {
+	if !config.GitHubOAuthEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "管理员未开启通过 GitHub 登录以及注册",
@@ -216,7 +219,7 @@ func GitHubBind(c *gin.Context) {

 func GenerateOAuthCode(c *gin.Context) {
 	session := sessions.Default(c)
-	state := common.GetRandomString(12)
+	state := helper.GetRandomString(12)
 	session.Set("oauth_state", state)
 	err := session.Save()
 	if err != nil {
--- a/controller/group.go
+++ b/controller/group.go
@@ -2,13 +2,13 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
 	"net/http"
-	"one-api/common"
 )

 func GetGroups(c *gin.Context) {
 	groupNames := make([]string, 0)
-	for groupName, _ := range common.GroupRatio {
+	for groupName := range common.GroupRatio {
 		groupNames = append(groupNames, groupName)
 	}
 	c.JSON(http.StatusOK, gin.H{
--- a/controller/log.go
+++ b/controller/log.go
@@ -2,9 +2,9 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 )

@@ -20,7 +20,7 @@ func GetAllLogs(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
 	channel, _ := strconv.Atoi(c.Query("channel"))
-	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*common.ItemsPerPage, common.ItemsPerPage, channel)
+	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*config.ItemsPerPage, config.ItemsPerPage, channel)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -47,7 +47,7 @@ func GetUserLogs(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*common.ItemsPerPage, common.ItemsPerPage)
+	logs, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*config.ItemsPerPage, config.ItemsPerPage)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
--- a/controller/misc.go
+++ b/controller/misc.go
@@ -3,9 +3,10 @@ package controller
 import (
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strings"

 	"github.com/gin-gonic/gin"
@@ -18,55 +19,55 @@ func GetStatus(c *gin.Context) {
 		"data": gin.H{
 			"version":             common.Version,
 			"start_time":          common.StartTime,
-			"email_verification":  common.EmailVerificationEnabled,
-			"github_oauth":        common.GitHubOAuthEnabled,
-			"github_client_id":    common.GitHubClientId,
-			"system_name":         common.SystemName,
-			"logo":                common.Logo,
-			"footer_html":         common.Footer,
-			"wechat_qrcode":       common.WeChatAccountQRCodeImageURL,
-			"wechat_login":        common.WeChatAuthEnabled,
-			"server_address":      common.ServerAddress,
-			"turnstile_check":     common.TurnstileCheckEnabled,
-			"turnstile_site_key":  common.TurnstileSiteKey,
-			"top_up_link":         common.TopUpLink,
-			"chat_link":           common.ChatLink,
-			"quota_per_unit":      common.QuotaPerUnit,
-			"display_in_currency": common.DisplayInCurrencyEnabled,
+			"email_verification":  config.EmailVerificationEnabled,
+			"github_oauth":        config.GitHubOAuthEnabled,
+			"github_client_id":    config.GitHubClientId,
+			"system_name":         config.SystemName,
+			"logo":                config.Logo,
+			"footer_html":         config.Footer,
+			"wechat_qrcode":       config.WeChatAccountQRCodeImageURL,
+			"wechat_login":        config.WeChatAuthEnabled,
+			"server_address":      config.ServerAddress,
+			"turnstile_check":     config.TurnstileCheckEnabled,
+			"turnstile_site_key":  config.TurnstileSiteKey,
+			"top_up_link":         config.TopUpLink,
+			"chat_link":           config.ChatLink,
+			"quota_per_unit":      config.QuotaPerUnit,
+			"display_in_currency": config.DisplayInCurrencyEnabled,
 		},
 	})
 	return
 }

 func GetNotice(c *gin.Context) {
-	common.OptionMapRWMutex.RLock()
-	defer common.OptionMapRWMutex.RUnlock()
+	config.OptionMapRWMutex.RLock()
+	defer config.OptionMapRWMutex.RUnlock()
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    common.OptionMap["Notice"],
+		"data":    config.OptionMap["Notice"],
 	})
 	return
 }

 func GetAbout(c *gin.Context) {
-	common.OptionMapRWMutex.RLock()
-	defer common.OptionMapRWMutex.RUnlock()
+	config.OptionMapRWMutex.RLock()
+	defer config.OptionMapRWMutex.RUnlock()
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    common.OptionMap["About"],
+		"data":    config.OptionMap["About"],
 	})
 	return
 }

 func GetHomePageContent(c *gin.Context) {
-	common.OptionMapRWMutex.RLock()
-	defer common.OptionMapRWMutex.RUnlock()
+	config.OptionMapRWMutex.RLock()
+	defer config.OptionMapRWMutex.RUnlock()
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    common.OptionMap["HomePageContent"],
+		"data":    config.OptionMap["HomePageContent"],
 	})
 	return
 }
@@ -80,9 +81,9 @@ func SendEmailVerification(c *gin.Context) {
 		})
 		return
 	}
-	if common.EmailDomainRestrictionEnabled {
+	if config.EmailDomainRestrictionEnabled {
 		allowed := false
-		for _, domain := range common.EmailDomainWhitelist {
+		for _, domain := range config.EmailDomainWhitelist {
 			if strings.HasSuffix(email, "@"+domain) {
 				allowed = true
 				break
@@ -105,10 +106,10 @@ func SendEmailVerification(c *gin.Context) {
 	}
 	code := common.GenerateVerificationCode(6)
 	common.RegisterVerificationCodeWithKey(email, code, common.EmailVerificationPurpose)
-	subject := fmt.Sprintf("%s邮箱验证邮件", common.SystemName)
+	subject := fmt.Sprintf("%s邮箱验证邮件", config.SystemName)
 	content := fmt.Sprintf("<p>您好，你正在进行%s邮箱验证。</p>"+
 		"<p>您的验证码为: <strong>%s</strong></p>"+
-		"<p>验证码 %d 分钟内有效，如果不是本人操作，请忽略。</p>", common.SystemName, code, common.VerificationValidMinutes)
+		"<p>验证码 %d 分钟内有效，如果不是本人操作，请忽略。</p>", config.SystemName, code, common.VerificationValidMinutes)
 	err := common.SendEmail(subject, email, content)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
@@ -142,12 +143,12 @@ func SendPasswordResetEmail(c *gin.Context) {
 	}
 	code := common.GenerateVerificationCode(0)
 	common.RegisterVerificationCodeWithKey(email, code, common.PasswordResetPurpose)
-	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", common.ServerAddress, email, code)
-	subject := fmt.Sprintf("%s密码重置", common.SystemName)
+	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", config.ServerAddress, email, code)
+	subject := fmt.Sprintf("%s密码重置", config.SystemName)
 	content := fmt.Sprintf("<p>您好，你正在进行%s密码重置。</p>"+
 		"<p>点击 <a href='%s'>此处</a> 进行密码重置。</p>"+
 		"<p>如果链接无法点击，请尝试点击下面的链接或将其复制到浏览器中打开：<br> %s </p>"+
-		"<p>重置链接 %d 分钟内有效，如果不是本人操作，请忽略。</p>", common.SystemName, link, link, common.VerificationValidMinutes)
+		"<p>重置链接 %d 分钟内有效，如果不是本人操作，请忽略。</p>", config.SystemName, link, link, common.VerificationValidMinutes)
 	err := common.SendEmail(subject, email, content)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
--- a/controller/model.go
+++ b/controller/model.go
@@ -2,8 +2,12 @@ package controller

 import (
 	"fmt"
-
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/channel/ai360"
+	"github.com/songquanpeng/one-api/relay/channel/moonshot"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/helper"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
 )

 // https://platform.openai.com/docs/api-reference/models/list
@@ -53,547 +57,46 @@ func init() {
 		IsBlocking:         false,
 	})
 	// https://platform.openai.com/docs/models/model-endpoint-compatibility
-	openAIModels = []OpenAIModels{
-		{
-			Id:         "dall-e-2",
+	for i := 0; i < constant.APITypeDummy; i++ {
+		if i == constant.APITypeAIProxyLibrary {
+			continue
+		}
+		adaptor := helper.GetAdaptor(i)
+		channelName := adaptor.GetChannelName()
+		modelNames := adaptor.GetModelList()
+		for _, modelName := range modelNames {
+			openAIModels = append(openAIModels, OpenAIModels{
+				Id:         modelName,
+				Object:     "model",
+				Created:    1626777600,
+				OwnedBy:    channelName,
+				Permission: permission,
+				Root:       modelName,
+				Parent:     nil,
+			})
+		}
+	}
+	for _, modelName := range ai360.ModelList {
+		openAIModels = append(openAIModels, OpenAIModels{
+			Id:         modelName,
 			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "dall-e-2",
-			Parent:     nil,
-		},
-		{
-			Id:         "dall-e-3",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "dall-e-3",
-			Parent:     nil,
-		},
-		{
-			Id:         "whisper-1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "whisper-1",
-			Parent:     nil,
-		},
-		{
-			Id:         "tts-1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "tts-1",
-			Parent:     nil,
-		},
-		{
-			Id:         "tts-1-1106",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "tts-1-1106",
-			Parent:     nil,
-		},
-		{
-			Id:         "tts-1-hd",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "tts-1-hd",
-			Parent:     nil,
-		},
-		{
-			Id:         "tts-1-hd-1106",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "tts-1-hd-1106",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-0301",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-0301",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-0613",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-0613",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-16k",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-16k",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-16k-0613",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-16k-0613",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-1106",
-			Object:     "model",
-			Created:    1699593571,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-1106",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-3.5-turbo-instruct",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-3.5-turbo-instruct",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-0314",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-0314",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-0613",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-0613",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-32k",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-32k",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-32k-0314",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-32k-0314",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-32k-0613",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-32k-0613",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-1106-preview",
-			Object:     "model",
-			Created:    1699593571,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-1106-preview",
-			Parent:     nil,
-		},
-		{
-			Id:         "gpt-4-vision-preview",
-			Object:     "model",
-			Created:    1699593571,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-vision-preview",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-embedding-ada-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-embedding-ada-002",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-davinci-003",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-davinci-003",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-davinci-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-davinci-002",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-curie-001",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-curie-001",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-babbage-001",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-babbage-001",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-ada-001",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-ada-001",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-moderation-latest",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-moderation-latest",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-moderation-stable",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-moderation-stable",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-davinci-edit-001",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "text-davinci-edit-001",
-			Parent:     nil,
-		},
-		{
-			Id:         "code-davinci-edit-001",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "code-davinci-edit-001",
-			Parent:     nil,
-		},
-		{
-			Id:         "davinci-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "davinci-002",
-			Parent:     nil,
-		},
-		{
-			Id:         "babbage-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "babbage-002",
-			Parent:     nil,
-		},
-		{
-			Id:         "claude-instant-1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "anthropic",
-			Permission: permission,
-			Root:       "claude-instant-1",
-			Parent:     nil,
-		},
-		{
-			Id:         "claude-2",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "anthropic",
-			Permission: permission,
-			Root:       "claude-2",
-			Parent:     nil,
-		},
-		{
-			Id:         "claude-2.1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "anthropic",
-			Permission: permission,
-			Root:       "claude-2.1",
-			Parent:     nil,
-		},
-		{
-			Id:         "claude-2.0",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "anthropic",
-			Permission: permission,
-			Root:       "claude-2.0",
-			Parent:     nil,
-		},
-		{
-			Id:         "ERNIE-Bot",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "baidu",
-			Permission: permission,
-			Root:       "ERNIE-Bot",
-			Parent:     nil,
-		},
-		{
-			Id:         "ERNIE-Bot-turbo",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "baidu",
-			Permission: permission,
-			Root:       "ERNIE-Bot-turbo",
-			Parent:     nil,
-		},
-		{
-			Id:         "ERNIE-Bot-4",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "baidu",
-			Permission: permission,
-			Root:       "ERNIE-Bot-4",
-			Parent:     nil,
-		},
-		{
-			Id:         "Embedding-V1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "baidu",
-			Permission: permission,
-			Root:       "Embedding-V1",
-			Parent:     nil,
-		},
-		{
-			Id:         "PaLM-2",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "google palm",
-			Permission: permission,
-			Root:       "PaLM-2",
-			Parent:     nil,
-		},
-		{
-			Id:         "gemini-pro",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "google gemini",
-			Permission: permission,
-			Root:       "gemini-pro",
-			Parent:     nil,
-		},
-		{
-			Id:         "gemini-pro-vision",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "google gemini",
-			Permission: permission,
-			Root:       "gemini-pro-vision",
-			Parent:     nil,
-		},
-		{
-			Id:         "chatglm_turbo",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "zhipu",
-			Permission: permission,
-			Root:       "chatglm_turbo",
-			Parent:     nil,
-		},
-		{
-			Id:         "chatglm_pro",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "zhipu",
-			Permission: permission,
-			Root:       "chatglm_pro",
-			Parent:     nil,
-		},
-		{
-			Id:         "chatglm_std",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "zhipu",
-			Permission: permission,
-			Root:       "chatglm_std",
-			Parent:     nil,
-		},
-		{
-			Id:         "chatglm_lite",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "zhipu",
-			Permission: permission,
-			Root:       "chatglm_lite",
-			Parent:     nil,
-		},
-		{
-			Id:         "qwen-turbo",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "ali",
-			Permission: permission,
-			Root:       "qwen-turbo",
-			Parent:     nil,
-		},
-		{
-			Id:         "qwen-plus",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "ali",
-			Permission: permission,
-			Root:       "qwen-plus",
-			Parent:     nil,
-		},
-		{
-			Id:         "qwen-max",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "ali",
-			Permission: permission,
-			Root:       "qwen-max",
-			Parent:     nil,
-		},
-		{
-			Id:         "qwen-max-longcontext",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "ali",
-			Permission: permission,
-			Root:       "qwen-max-longcontext",
-			Parent:     nil,
-		},
-		{
-			Id:         "text-embedding-v1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "ali",
-			Permission: permission,
-			Root:       "text-embedding-v1",
-			Parent:     nil,
-		},
-		{
-			Id:         "SparkDesk",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "xunfei",
-			Permission: permission,
-			Root:       "SparkDesk",
-			Parent:     nil,
-		},
-		{
-			Id:         "360GPT_S2_V9",
-			Object:     "model",
-			Created:    1677649963,
+			Created:    1626777600,
 			OwnedBy:    "360",
 			Permission: permission,
-			Root:       "360GPT_S2_V9",
+			Root:       modelName,
 			Parent:     nil,
-		},
-		{
-			Id:         "embedding-bert-512-v1",
+		})
+	}
+	for _, modelName := range moonshot.ModelList {
+		openAIModels = append(openAIModels, OpenAIModels{
+			Id:         modelName,
 			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "360",
+			Created:    1626777600,
+			OwnedBy:    "moonshot",
 			Permission: permission,
-			Root:       "embedding-bert-512-v1",
+			Root:       modelName,
 			Parent:     nil,
-		},
-		{
-			Id:         "embedding_s1_v1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "360",
-			Permission: permission,
-			Root:       "embedding_s1_v1",
-			Parent:     nil,
-		},
-		{
-			Id:         "semantic_similarity_s1_v1",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "360",
-			Permission: permission,
-			Root:       "semantic_similarity_s1_v1",
-			Parent:     nil,
-		},
-		{
-			Id:         "hunyuan",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "tencent",
-			Permission: permission,
-			Root:       "hunyuan",
-			Parent:     nil,
-		},
+		})
 	}
 	openAIModelsMap = make(map[string]OpenAIModels)
 	for _, model := range openAIModels {
@@ -613,14 +116,14 @@ func RetrieveModel(c *gin.Context) {
 	if model, ok := openAIModelsMap[modelId]; ok {
 		c.JSON(200, model)
 	} else {
-		openAIError := OpenAIError{
+		Error := relaymodel.Error{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),
 			Type:    "invalid_request_error",
 			Param:   "model",
 			Code:    "model_not_found",
 		}
 		c.JSON(200, gin.H{
-			"error": openAIError,
+			"error": Error,
 		})
 	}
 }
--- a/controller/option.go
+++ b/controller/option.go
@@ -2,9 +2,10 @@ package controller

 import (
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strings"

 	"github.com/gin-gonic/gin"
@@ -12,17 +13,17 @@ import (

 func GetOptions(c *gin.Context) {
 	var options []*model.Option
-	common.OptionMapRWMutex.Lock()
-	for k, v := range common.OptionMap {
+	config.OptionMapRWMutex.Lock()
+	for k, v := range config.OptionMap {
 		if strings.HasSuffix(k, "Token") || strings.HasSuffix(k, "Secret") {
 			continue
 		}
 		options = append(options, &model.Option{
 			Key:   k,
-			Value: common.Interface2String(v),
+			Value: helper.Interface2String(v),
 		})
 	}
-	common.OptionMapRWMutex.Unlock()
+	config.OptionMapRWMutex.Unlock()
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
@@ -43,7 +44,7 @@ func UpdateOption(c *gin.Context) {
 	}
 	switch option.Key {
 	case "Theme":
-		if !common.ValidThemes[option.Value] {
+		if !config.ValidThemes[option.Value] {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "无效的主题",
@@ -51,7 +52,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "GitHubOAuthEnabled":
-		if option.Value == "true" && common.GitHubClientId == "" {
+		if option.Value == "true" && config.GitHubClientId == "" {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "无法启用 GitHub OAuth，请先填入 GitHub Client Id 以及 GitHub Client Secret！",
@@ -59,7 +60,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "EmailDomainRestrictionEnabled":
-		if option.Value == "true" && len(common.EmailDomainWhitelist) == 0 {
+		if option.Value == "true" && len(config.EmailDomainWhitelist) == 0 {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "无法启用邮箱域名限制，请先填入限制的邮箱域名！",
@@ -67,7 +68,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "WeChatAuthEnabled":
-		if option.Value == "true" && common.WeChatServerAddress == "" {
+		if option.Value == "true" && config.WeChatServerAddress == "" {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "无法启用微信登录，请先填入微信登录相关配置信息！",
@@ -75,7 +76,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "TurnstileCheckEnabled":
-		if option.Value == "true" && common.TurnstileSiteKey == "" {
+		if option.Value == "true" && config.TurnstileSiteKey == "" {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "无法启用 Turnstile 校验，请先填入 Turnstile 校验相关配置信息！",
--- a/controller/redemption.go
+++ b/controller/redemption.go
@@ -2,9 +2,10 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 )

@@ -13,7 +14,7 @@ func GetAllRedemptions(c *gin.Context) {
 	if p < 0 {
 		p = 0
 	}
-	redemptions, err := model.GetAllRedemptions(p*common.ItemsPerPage, common.ItemsPerPage)
+	redemptions, err := model.GetAllRedemptions(p*config.ItemsPerPage, config.ItemsPerPage)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -105,12 +106,12 @@ func AddRedemption(c *gin.Context) {
 	}
 	var keys []string
 	for i := 0; i < redemption.Count; i++ {
-		key := common.GetUUID()
+		key := helper.GetUUID()
 		cleanRedemption := model.Redemption{
 			UserId:      c.GetInt("id"),
 			Name:        redemption.Name,
 			Key:         key,
-			CreatedTime: common.GetTimestamp(),
+			CreatedTime: helper.GetTimestamp(),
 			Quota:       redemption.Quota,
 		}
 		err = cleanRedemption.Insert()
--- a/controller/relay-tencent.go
+++ b/controller/relay-tencent.go
@@ -1,288 +0,0 @@
-package controller
-
-import (
-	"bufio"
-	"crypto/hmac"
-	"crypto/sha1"
-	"encoding/base64"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"github.com/gin-gonic/gin"
-	"io"
-	"net/http"
-	"one-api/common"
-	"sort"
-	"strconv"
-	"strings"
-)
-
-// https://cloud.tencent.com/document/product/1729/97732
-
-type TencentMessage struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
-}
-
-type TencentChatRequest struct {
-	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
-	SecretId string `json:"secret_id"` // 官网 SecretId
-	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
-	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
-	Timestamp int64 `json:"timestamp"`
-	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
-	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
-	Expired int64  `json:"expired"`
-	QueryID string `json:"query_id"` //请求 Id，用于问题排查
-	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
-	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
-	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
-	Temperature float64 `json:"temperature"`
-	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
-	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
-	// 建议该参数和 temperature 只设置1个，不要同时更改
-	TopP float64 `json:"top_p"`
-	// Stream 0：同步，1：流式 （默认，协议：SSE)
-	// 同步请求超时：60s，如果内容较长建议使用流式
-	Stream int `json:"stream"`
-	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
-	// 输入 content 总数最大支持 3000 token。
-	Messages []TencentMessage `json:"messages"`
-}
-
-type TencentError struct {
-	Code    int    `json:"code"`
-	Message string `json:"message"`
-}
-
-type TencentUsage struct {
-	InputTokens  int `json:"input_tokens"`
-	OutputTokens int `json:"output_tokens"`
-	TotalTokens  int `json:"total_tokens"`
-}
-
-type TencentResponseChoices struct {
-	FinishReason string         `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
-	Messages     TencentMessage `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
-	Delta        TencentMessage `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
-}
-
-type TencentChatResponse struct {
-	Choices []TencentResponseChoices `json:"choices,omitempty"` // 结果
-	Created string                   `json:"created,omitempty"` // unix 时间戳的字符串
-	Id      string                   `json:"id,omitempty"`      // 会话 id
-	Usage   Usage                    `json:"usage,omitempty"`   // token 数量
-	Error   TencentError             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
-	Note    string                   `json:"note,omitempty"`    // 注释
-	ReqID   string                   `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
-}
-
-func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
-	messages := make([]TencentMessage, 0, len(request.Messages))
-	for i := 0; i < len(request.Messages); i++ {
-		message := request.Messages[i]
-		if message.Role == "system" {
-			messages = append(messages, TencentMessage{
-				Role:    "user",
-				Content: message.StringContent(),
-			})
-			messages = append(messages, TencentMessage{
-				Role:    "assistant",
-				Content: "Okay",
-			})
-			continue
-		}
-		messages = append(messages, TencentMessage{
-			Content: message.StringContent(),
-			Role:    message.Role,
-		})
-	}
-	stream := 0
-	if request.Stream {
-		stream = 1
-	}
-	return &TencentChatRequest{
-		Timestamp:   common.GetTimestamp(),
-		Expired:     common.GetTimestamp() + 24*60*60,
-		QueryID:     common.GetUUID(),
-		Temperature: request.Temperature,
-		TopP:        request.TopP,
-		Stream:      stream,
-		Messages:    messages,
-	}
-}
-
-func responseTencent2OpenAI(response *TencentChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
-		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Usage:   response.Usage,
-	}
-	if len(response.Choices) > 0 {
-		choice := OpenAITextResponseChoice{
-			Index: 0,
-			Message: Message{
-				Role:    "assistant",
-				Content: response.Choices[0].Messages.Content,
-			},
-			FinishReason: response.Choices[0].FinishReason,
-		}
-		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
-	}
-	return &fullTextResponse
-}
-
-func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *ChatCompletionsStreamResponse {
-	response := ChatCompletionsStreamResponse{
-		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
-		Model:   "tencent-hunyuan",
-	}
-	if len(TencentResponse.Choices) > 0 {
-		var choice ChatCompletionsStreamResponseChoice
-		choice.Delta.Content = TencentResponse.Choices[0].Delta.Content
-		if TencentResponse.Choices[0].FinishReason == "stop" {
-			choice.FinishReason = &stopFinishReason
-		}
-		response.Choices = append(response.Choices, choice)
-	}
-	return &response
-}
-
-func tencentStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
-	var responseText string
-	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
-	setEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var TencentResponse TencentChatResponse
-			err := json.Unmarshal([]byte(data), &TencentResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := streamResponseTencent2OpenAI(&TencentResponse)
-			if len(response.Choices) != 0 {
-				responseText += response.Choices[0].Delta.Content
-			}
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
-		}
-	})
-	err := resp.Body.Close()
-	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
-	}
-	return nil, responseText
-}
-
-func tencentHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var TencentResponse TencentChatResponse
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-	}
-	err = json.Unmarshal(responseBody, &TencentResponse)
-	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-	if TencentResponse.Error.Code != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
-				Message: TencentResponse.Error.Message,
-				Code:    TencentResponse.Error.Code,
-			},
-			StatusCode: resp.StatusCode,
-		}, nil
-	}
-	fullTextResponse := responseTencent2OpenAI(&TencentResponse)
-	fullTextResponse.Model = "hunyuan"
-	jsonResponse, err := json.Marshal(fullTextResponse)
-	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-	c.Writer.Header().Set("Content-Type", "application/json")
-	c.Writer.WriteHeader(resp.StatusCode)
-	_, err = c.Writer.Write(jsonResponse)
-	return nil, &fullTextResponse.Usage
-}
-
-func parseTencentConfig(config string) (appId int64, secretId string, secretKey string, err error) {
-	parts := strings.Split(config, "|")
-	if len(parts) != 3 {
-		err = errors.New("invalid tencent config")
-		return
-	}
-	appId, err = strconv.ParseInt(parts[0], 10, 64)
-	secretId = parts[1]
-	secretKey = parts[2]
-	return
-}
-
-func getTencentSign(req TencentChatRequest, secretKey string) string {
-	params := make([]string, 0)
-	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
-	params = append(params, "secret_id="+req.SecretId)
-	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
-	params = append(params, "query_id="+req.QueryID)
-	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
-	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
-	params = append(params, "stream="+strconv.Itoa(req.Stream))
-	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
-
-	var messageStr string
-	for _, msg := range req.Messages {
-		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
-	}
-	messageStr = strings.TrimSuffix(messageStr, ",")
-	params = append(params, "messages=["+messageStr+"]")
-
-	sort.Sort(sort.StringSlice(params))
-	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
-	mac := hmac.New(sha1.New, []byte(secretKey))
-	signURL := url
-	mac.Write([]byte(signURL))
-	sign := mac.Sum([]byte(nil))
-	return base64.StdEncoding.EncodeToString(sign)
-}
--- a/controller/relay-text.go
+++ b/controller/relay-text.go
@@ -1,689 +0,0 @@
-package controller
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"math"
-	"net/http"
-	"one-api/common"
-	"one-api/model"
-	"strings"
-	"time"
-
-	"github.com/gin-gonic/gin"
-)
-
-const (
-	APITypeOpenAI = iota
-	APITypeClaude
-	APITypePaLM
-	APITypeBaidu
-	APITypeZhipu
-	APITypeAli
-	APITypeXunfei
-	APITypeAIProxyLibrary
-	APITypeTencent
-	APITypeGemini
-)
-
-var httpClient *http.Client
-var impatientHTTPClient *http.Client
-
-func init() {
-	if common.RelayTimeout == 0 {
-		httpClient = &http.Client{}
-	} else {
-		httpClient = &http.Client{
-			Timeout: time.Duration(common.RelayTimeout) * time.Second,
-		}
-	}
-
-	impatientHTTPClient = &http.Client{
-		Timeout: 5 * time.Second,
-	}
-}
-
-func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
-	channelType := c.GetInt("channel")
-	channelId := c.GetInt("channel_id")
-	tokenId := c.GetInt("token_id")
-	userId := c.GetInt("id")
-	group := c.GetString("group")
-	var textRequest GeneralOpenAIRequest
-	err := common.UnmarshalBodyReusable(c, &textRequest)
-	if err != nil {
-		return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
-	}
-	if textRequest.MaxTokens < 0 || textRequest.MaxTokens > math.MaxInt32/2 {
-		return errorWrapper(errors.New("max_tokens is invalid"), "invalid_max_tokens", http.StatusBadRequest)
-	}
-	if relayMode == RelayModeModerations && textRequest.Model == "" {
-		textRequest.Model = "text-moderation-latest"
-	}
-	if relayMode == RelayModeEmbeddings && textRequest.Model == "" {
-		textRequest.Model = c.Param("model")
-	}
-	// request validation
-	if textRequest.Model == "" {
-		return errorWrapper(errors.New("model is required"), "required_field_missing", http.StatusBadRequest)
-	}
-	switch relayMode {
-	case RelayModeCompletions:
-		if textRequest.Prompt == "" {
-			return errorWrapper(errors.New("field prompt is required"), "required_field_missing", http.StatusBadRequest)
-		}
-	case RelayModeChatCompletions:
-		if textRequest.Messages == nil || len(textRequest.Messages) == 0 {
-			return errorWrapper(errors.New("field messages is required"), "required_field_missing", http.StatusBadRequest)
-		}
-	case RelayModeEmbeddings:
-	case RelayModeModerations:
-		if textRequest.Input == "" {
-			return errorWrapper(errors.New("field input is required"), "required_field_missing", http.StatusBadRequest)
-		}
-	case RelayModeEdits:
-		if textRequest.Instruction == "" {
-			return errorWrapper(errors.New("field instruction is required"), "required_field_missing", http.StatusBadRequest)
-		}
-	}
-	// map model name
-	modelMapping := c.GetString("model_mapping")
-	isModelMapped := false
-	if modelMapping != "" && modelMapping != "{}" {
-		modelMap := make(map[string]string)
-		err := json.Unmarshal([]byte(modelMapping), &modelMap)
-		if err != nil {
-			return errorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-		}
-		if modelMap[textRequest.Model] != "" {
-			textRequest.Model = modelMap[textRequest.Model]
-			isModelMapped = true
-		}
-	}
-	apiType := APITypeOpenAI
-	switch channelType {
-	case common.ChannelTypeAnthropic:
-		apiType = APITypeClaude
-	case common.ChannelTypeBaidu:
-		apiType = APITypeBaidu
-	case common.ChannelTypePaLM:
-		apiType = APITypePaLM
-	case common.ChannelTypeZhipu:
-		apiType = APITypeZhipu
-	case common.ChannelTypeAli:
-		apiType = APITypeAli
-	case common.ChannelTypeXunfei:
-		apiType = APITypeXunfei
-	case common.ChannelTypeAIProxyLibrary:
-		apiType = APITypeAIProxyLibrary
-	case common.ChannelTypeTencent:
-		apiType = APITypeTencent
-	case common.ChannelTypeGemini:
-		apiType = APITypeGemini
-	}
-	baseURL := common.ChannelBaseURLs[channelType]
-	requestURL := c.Request.URL.String()
-	if c.GetString("base_url") != "" {
-		baseURL = c.GetString("base_url")
-	}
-	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
-	switch apiType {
-	case APITypeOpenAI:
-		if channelType == common.ChannelTypeAzure {
-			// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
-			apiVersion := GetAPIVersion(c)
-			requestURL := strings.Split(requestURL, "?")[0]
-			requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
-			baseURL = c.GetString("base_url")
-			task := strings.TrimPrefix(requestURL, "/v1/")
-			model_ := textRequest.Model
-			model_ = strings.Replace(model_, ".", "", -1)
-			// https://github.com/songquanpeng/one-api/issues/67
-			model_ = strings.TrimSuffix(model_, "-0301")
-			model_ = strings.TrimSuffix(model_, "-0314")
-			model_ = strings.TrimSuffix(model_, "-0613")
-
-			requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
-			fullRequestURL = getFullRequestURL(baseURL, requestURL, channelType)
-		}
-	case APITypeClaude:
-		fullRequestURL = "https://api.anthropic.com/v1/complete"
-		if baseURL != "" {
-			fullRequestURL = fmt.Sprintf("%s/v1/complete", baseURL)
-		}
-	case APITypeBaidu:
-		switch textRequest.Model {
-		case "ERNIE-Bot":
-			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
-		case "ERNIE-Bot-turbo":
-			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
-		case "ERNIE-Bot-4":
-			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
-		case "BLOOMZ-7B":
-			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
-		case "Embedding-V1":
-			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
-		}
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		var err error
-		if apiKey, err = getBaiduAccessToken(apiKey); err != nil {
-			return errorWrapper(err, "invalid_baidu_config", http.StatusInternalServerError)
-		}
-		fullRequestURL += "?access_token=" + apiKey
-	case APITypePaLM:
-		fullRequestURL = "https://generativelanguage.googleapis.com/v1beta2/models/chat-bison-001:generateMessage"
-		if baseURL != "" {
-			fullRequestURL = fmt.Sprintf("%s/v1beta2/models/chat-bison-001:generateMessage", baseURL)
-		}
-	case APITypeGemini:
-		requestBaseURL := "https://generativelanguage.googleapis.com"
-		if baseURL != "" {
-			requestBaseURL = baseURL
-		}
-		version := "v1"
-		if c.GetString("api_version") != "" {
-			version = c.GetString("api_version")
-		}
-		action := "generateContent"
-		if textRequest.Stream {
-			action = "streamGenerateContent"
-		}
-		fullRequestURL = fmt.Sprintf("%s/%s/models/%s:%s", requestBaseURL, version, textRequest.Model, action)
-	case APITypeZhipu:
-		method := "invoke"
-		if textRequest.Stream {
-			method = "sse-invoke"
-		}
-		fullRequestURL = fmt.Sprintf("https://open.bigmodel.cn/api/paas/v3/model-api/%s/%s", textRequest.Model, method)
-	case APITypeAli:
-		fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation"
-		if relayMode == RelayModeEmbeddings {
-			fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding"
-		}
-	case APITypeTencent:
-		fullRequestURL = "https://hunyuan.cloud.tencent.com/hyllm/v1/chat/completions"
-	case APITypeAIProxyLibrary:
-		fullRequestURL = fmt.Sprintf("%s/api/library/ask", baseURL)
-	}
-	var promptTokens int
-	var completionTokens int
-	switch relayMode {
-	case RelayModeChatCompletions:
-		promptTokens = countTokenMessages(textRequest.Messages, textRequest.Model)
-	case RelayModeCompletions:
-		promptTokens = countTokenInput(textRequest.Prompt, textRequest.Model)
-	case RelayModeModerations:
-		promptTokens = countTokenInput(textRequest.Input, textRequest.Model)
-	}
-	preConsumedTokens := common.PreConsumedQuota
-	if textRequest.MaxTokens != 0 {
-		preConsumedTokens = promptTokens + textRequest.MaxTokens
-	}
-	modelRatio := common.GetModelRatio(textRequest.Model)
-	groupRatio := common.GetGroupRatio(group)
-	ratio := modelRatio * groupRatio
-	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
-	userQuota, err := model.CacheGetUserQuota(userId)
-	if err != nil {
-		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
-	}
-	if userQuota-preConsumedQuota < 0 {
-		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
-	}
-	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
-	if err != nil {
-		return errorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
-	}
-	if userQuota > 100*preConsumedQuota {
-		// in this case, we do not pre-consume quota
-		// because the user has enough quota
-		preConsumedQuota = 0
-		common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d has enough quota %d, trusted and no need to pre-consume", userId, userQuota))
-	}
-	if preConsumedQuota > 0 {
-		err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
-		if err != nil {
-			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
-		}
-	}
-	var requestBody io.Reader
-	if isModelMapped {
-		jsonStr, err := json.Marshal(textRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	} else {
-		requestBody = c.Request.Body
-	}
-	switch apiType {
-	case APITypeClaude:
-		claudeRequest := requestOpenAI2Claude(textRequest)
-		jsonStr, err := json.Marshal(claudeRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeBaidu:
-		var jsonData []byte
-		var err error
-		switch relayMode {
-		case RelayModeEmbeddings:
-			baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(textRequest)
-			jsonData, err = json.Marshal(baiduEmbeddingRequest)
-		default:
-			baiduRequest := requestOpenAI2Baidu(textRequest)
-			jsonData, err = json.Marshal(baiduRequest)
-		}
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonData)
-	case APITypePaLM:
-		palmRequest := requestOpenAI2PaLM(textRequest)
-		jsonStr, err := json.Marshal(palmRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeGemini:
-		geminiChatRequest := requestOpenAI2Gemini(textRequest)
-		jsonStr, err := json.Marshal(geminiChatRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeZhipu:
-		zhipuRequest := requestOpenAI2Zhipu(textRequest)
-		jsonStr, err := json.Marshal(zhipuRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeAli:
-		var jsonStr []byte
-		var err error
-		switch relayMode {
-		case RelayModeEmbeddings:
-			aliEmbeddingRequest := embeddingRequestOpenAI2Ali(textRequest)
-			jsonStr, err = json.Marshal(aliEmbeddingRequest)
-		default:
-			aliRequest := requestOpenAI2Ali(textRequest)
-			jsonStr, err = json.Marshal(aliRequest)
-		}
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeTencent:
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		appId, secretId, secretKey, err := parseTencentConfig(apiKey)
-		if err != nil {
-			return errorWrapper(err, "invalid_tencent_config", http.StatusInternalServerError)
-		}
-		tencentRequest := requestOpenAI2Tencent(textRequest)
-		tencentRequest.AppId = appId
-		tencentRequest.SecretId = secretId
-		jsonStr, err := json.Marshal(tencentRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		sign := getTencentSign(*tencentRequest, secretKey)
-		c.Request.Header.Set("Authorization", sign)
-		requestBody = bytes.NewBuffer(jsonStr)
-	case APITypeAIProxyLibrary:
-		aiProxyLibraryRequest := requestOpenAI2AIProxyLibrary(textRequest)
-		aiProxyLibraryRequest.LibraryId = c.GetString("library_id")
-		jsonStr, err := json.Marshal(aiProxyLibraryRequest)
-		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	}
-
-	var req *http.Request
-	var resp *http.Response
-	isStream := textRequest.Stream
-
-	if apiType != APITypeXunfei { // cause xunfei use websocket
-		req, err = http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
-		if err != nil {
-			return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
-		}
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		switch apiType {
-		case APITypeOpenAI:
-			if channelType == common.ChannelTypeAzure {
-				req.Header.Set("api-key", apiKey)
-			} else {
-				req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
-				if channelType == common.ChannelTypeOpenRouter {
-					req.Header.Set("HTTP-Referer", "https://github.com/songquanpeng/one-api")
-					req.Header.Set("X-Title", "One API")
-				}
-			}
-		case APITypeClaude:
-			req.Header.Set("x-api-key", apiKey)
-			anthropicVersion := c.Request.Header.Get("anthropic-version")
-			if anthropicVersion == "" {
-				anthropicVersion = "2023-06-01"
-			}
-			req.Header.Set("anthropic-version", anthropicVersion)
-		case APITypeZhipu:
-			token := getZhipuToken(apiKey)
-			req.Header.Set("Authorization", token)
-		case APITypeAli:
-			req.Header.Set("Authorization", "Bearer "+apiKey)
-			if textRequest.Stream {
-				req.Header.Set("X-DashScope-SSE", "enable")
-			}
-			if c.GetString("plugin") != "" {
-				req.Header.Set("X-DashScope-Plugin", c.GetString("plugin"))
-			}
-		case APITypeTencent:
-			req.Header.Set("Authorization", apiKey)
-		case APITypePaLM:
-			req.Header.Set("x-goog-api-key", apiKey)
-		case APITypeGemini:
-			req.Header.Set("x-goog-api-key", apiKey)
-		default:
-			req.Header.Set("Authorization", "Bearer "+apiKey)
-		}
-		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
-		if isStream && c.Request.Header.Get("Accept") == "" {
-			req.Header.Set("Accept", "text/event-stream")
-		}
-		//req.Header.Set("Connection", c.Request.Header.Get("Connection"))
-		resp, err = httpClient.Do(req)
-		if err != nil {
-			return errorWrapper(err, "do_request_failed", http.StatusInternalServerError)
-		}
-		err = req.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-		}
-		err = c.Request.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-		}
-		isStream = isStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
-
-		if resp.StatusCode != http.StatusOK {
-			if preConsumedQuota != 0 {
-				go func(ctx context.Context) {
-					// return pre-consumed quota
-					err := model.PostConsumeTokenQuota(tokenId, -preConsumedQuota)
-					if err != nil {
-						common.LogError(ctx, "error return pre-consumed quota: "+err.Error())
-					}
-				}(c.Request.Context())
-			}
-			return relayErrorHandler(resp)
-		}
-	}
-
-	var textResponse TextResponse
-	tokenName := c.GetString("token_name")
-
-	defer func(ctx context.Context) {
-		// c.Writer.Flush()
-		go func() {
-			quota := 0
-			completionRatio := common.GetCompletionRatio(textRequest.Model)
-			promptTokens = textResponse.Usage.PromptTokens
-			completionTokens = textResponse.Usage.CompletionTokens
-			quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
-			if ratio != 0 && quota <= 0 {
-				quota = 1
-			}
-			totalTokens := promptTokens + completionTokens
-			if totalTokens == 0 {
-				// in this case, must be some error happened
-				// we cannot just return, because we may have to return the pre-consumed quota
-				quota = 0
-			}
-			quotaDelta := quota - preConsumedQuota
-			err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
-			if err != nil {
-				common.LogError(ctx, "error consuming token remain quota: "+err.Error())
-			}
-			err = model.CacheUpdateUserQuota(userId)
-			if err != nil {
-				common.LogError(ctx, "error update user quota cache: "+err.Error())
-			}
-			if quota != 0 {
-				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
-				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				model.UpdateChannelUsedQuota(channelId, quota)
-			}
-
-		}()
-	}(c.Request.Context())
-	switch apiType {
-	case APITypeOpenAI:
-		if isStream {
-			err, responseText := openaiStreamHandler(c, resp, relayMode)
-			if err != nil {
-				return err
-			}
-			textResponse.Usage.PromptTokens = promptTokens
-			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
-			return nil
-		} else {
-			err, usage := openaiHandler(c, resp, promptTokens, textRequest.Model)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeClaude:
-		if isStream {
-			err, responseText := claudeStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			textResponse.Usage.PromptTokens = promptTokens
-			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
-			return nil
-		} else {
-			err, usage := claudeHandler(c, resp, promptTokens, textRequest.Model)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeBaidu:
-		if isStream {
-			err, usage := baiduStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		} else {
-			var err *OpenAIErrorWithStatusCode
-			var usage *Usage
-			switch relayMode {
-			case RelayModeEmbeddings:
-				err, usage = baiduEmbeddingHandler(c, resp)
-			default:
-				err, usage = baiduHandler(c, resp)
-			}
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypePaLM:
-		if textRequest.Stream { // PaLM2 API does not support stream
-			err, responseText := palmStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			textResponse.Usage.PromptTokens = promptTokens
-			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
-			return nil
-		} else {
-			err, usage := palmHandler(c, resp, promptTokens, textRequest.Model)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeGemini:
-		if textRequest.Stream {
-			err, responseText := geminiChatStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			textResponse.Usage.PromptTokens = promptTokens
-			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
-			return nil
-		} else {
-			err, usage := geminiChatHandler(c, resp, promptTokens, textRequest.Model)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeZhipu:
-		if isStream {
-			err, usage := zhipuStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			// zhipu's API does not return prompt tokens & completion tokens
-			textResponse.Usage.PromptTokens = textResponse.Usage.TotalTokens
-			return nil
-		} else {
-			err, usage := zhipuHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			// zhipu's API does not return prompt tokens & completion tokens
-			textResponse.Usage.PromptTokens = textResponse.Usage.TotalTokens
-			return nil
-		}
-	case APITypeAli:
-		if isStream {
-			err, usage := aliStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		} else {
-			var err *OpenAIErrorWithStatusCode
-			var usage *Usage
-			switch relayMode {
-			case RelayModeEmbeddings:
-				err, usage = aliEmbeddingHandler(c, resp)
-			default:
-				err, usage = aliHandler(c, resp)
-			}
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeXunfei:
-		auth := c.Request.Header.Get("Authorization")
-		auth = strings.TrimPrefix(auth, "Bearer ")
-		splits := strings.Split(auth, "|")
-		if len(splits) != 3 {
-			return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
-		}
-		var err *OpenAIErrorWithStatusCode
-		var usage *Usage
-		if isStream {
-			err, usage = xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
-		} else {
-			err, usage = xunfeiHandler(c, textRequest, splits[0], splits[1], splits[2])
-		}
-		if err != nil {
-			return err
-		}
-		if usage != nil {
-			textResponse.Usage = *usage
-		}
-		return nil
-	case APITypeAIProxyLibrary:
-		if isStream {
-			err, usage := aiProxyLibraryStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		} else {
-			err, usage := aiProxyLibraryHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	case APITypeTencent:
-		if isStream {
-			err, responseText := tencentStreamHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			textResponse.Usage.PromptTokens = promptTokens
-			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
-			return nil
-		} else {
-			err, usage := tencentHandler(c, resp)
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		}
-	default:
-		return errorWrapper(errors.New("unknown api type"), "unknown_api_type", http.StatusInternalServerError)
-	}
-}
--- a/controller/relay.go
+++ b/controller/relay.go
@@ -1,384 +1,116 @@
 package controller

 import (
+	"context"
 	"fmt"
-	"net/http"
-	"one-api/common"
-	"strconv"
-	"strings"
-
 	"github.com/gin-gonic/gin"
-)
-
-type Message struct {
-	Role    string  `json:"role"`
-	Content any     `json:"content"`
-	Name    *string `json:"name,omitempty"`
-}
-
-type ImageURL struct {
-	Url    string `json:"url,omitempty"`
-	Detail string `json:"detail,omitempty"`
-}
-
-type TextContent struct {
-	Type string `json:"type,omitempty"`
-	Text string `json:"text,omitempty"`
-}
-
-type ImageContent struct {
-	Type     string    `json:"type,omitempty"`
-	ImageURL *ImageURL `json:"image_url,omitempty"`
-}
-
-const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
-)
-
-type OpenAIMessageContent struct {
-	Type     string    `json:"type,omitempty"`
-	Text     string    `json:"text"`
-	ImageURL *ImageURL `json:"image_url,omitempty"`
-}
-
-func (m Message) IsStringContent() bool {
-	_, ok := m.Content.(string)
-	return ok
-}
-
-func (m Message) StringContent() string {
-	content, ok := m.Content.(string)
-	if ok {
-		return content
-	}
-	contentList, ok := m.Content.([]any)
-	if ok {
-		var contentStr string
-		for _, contentItem := range contentList {
-			contentMap, ok := contentItem.(map[string]any)
-			if !ok {
-				continue
-			}
-			if contentMap["type"] == ContentTypeText {
-				if subStr, ok := contentMap["text"].(string); ok {
-					contentStr += subStr
-				}
-			}
-		}
-		return contentStr
-	}
-	return ""
-}
-
-func (m Message) ParseContent() []OpenAIMessageContent {
-	var contentList []OpenAIMessageContent
-	content, ok := m.Content.(string)
-	if ok {
-		contentList = append(contentList, OpenAIMessageContent{
-			Type: ContentTypeText,
-			Text: content,
-		})
-		return contentList
-	}
-	anyList, ok := m.Content.([]any)
-	if ok {
-		for _, contentItem := range anyList {
-			contentMap, ok := contentItem.(map[string]any)
-			if !ok {
-				continue
-			}
-			switch contentMap["type"] {
-			case ContentTypeText:
-				if subStr, ok := contentMap["text"].(string); ok {
-					contentList = append(contentList, OpenAIMessageContent{
-						Type: ContentTypeText,
-						Text: subStr,
-					})
-				}
-			case ContentTypeImageURL:
-				if subObj, ok := contentMap["image_url"].(map[string]any); ok {
-					contentList = append(contentList, OpenAIMessageContent{
-						Type: ContentTypeImageURL,
-						ImageURL: &ImageURL{
-							Url: subObj["url"].(string),
-						},
-					})
-				}
-			}
-		}
-		return contentList
-	}
-	return nil
-}
-
-const (
-	RelayModeUnknown = iota
-	RelayModeChatCompletions
-	RelayModeCompletions
-	RelayModeEmbeddings
-	RelayModeModerations
-	RelayModeImagesGenerations
-	RelayModeEdits
-	RelayModeAudioSpeech
-	RelayModeAudioTranscription
-	RelayModeAudioTranslation
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/middleware"
+	dbmodel "github.com/songquanpeng/one-api/model"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/controller"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"net/http"
 )

 // https://platform.openai.com/docs/api-reference/chat

-type ResponseFormat struct {
-	Type string `json:"type,omitempty"`
-}
-
-type GeneralOpenAIRequest struct {
-	Model            string          `json:"model,omitempty"`
-	Messages         []Message       `json:"messages,omitempty"`
-	Prompt           any             `json:"prompt,omitempty"`
-	Stream           bool            `json:"stream,omitempty"`
-	MaxTokens        int             `json:"max_tokens,omitempty"`
-	Temperature      float64         `json:"temperature,omitempty"`
-	TopP             float64         `json:"top_p,omitempty"`
-	N                int             `json:"n,omitempty"`
-	Input            any             `json:"input,omitempty"`
-	Instruction      string          `json:"instruction,omitempty"`
-	Size             string          `json:"size,omitempty"`
-	Functions        any             `json:"functions,omitempty"`
-	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
-	Seed             float64         `json:"seed,omitempty"`
-	Tools            any             `json:"tools,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
-	User             string          `json:"user,omitempty"`
-}
-
-func (r GeneralOpenAIRequest) ParseInput() []string {
-	if r.Input == nil {
-		return nil
+func relay(c *gin.Context, relayMode int) *model.ErrorWithStatusCode {
+	var err *model.ErrorWithStatusCode
+	switch relayMode {
+	case constant.RelayModeImagesGenerations:
+		err = controller.RelayImageHelper(c, relayMode)
+	case constant.RelayModeAudioSpeech:
+		fallthrough
+	case constant.RelayModeAudioTranslation:
+		fallthrough
+	case constant.RelayModeAudioTranscription:
+		err = controller.RelayAudioHelper(c, relayMode)
+	default:
+		err = controller.RelayTextHelper(c)
 	}
-	var input []string
-	switch r.Input.(type) {
-	case string:
-		input = []string{r.Input.(string)}
-	case []any:
-		input = make([]string, 0, len(r.Input.([]any)))
-		for _, item := range r.Input.([]any) {
-			if str, ok := item.(string); ok {
-				input = append(input, str)
-			}
-		}
-	}
-	return input
-}
-
-type ChatRequest struct {
-	Model     string    `json:"model"`
-	Messages  []Message `json:"messages"`
-	MaxTokens int       `json:"max_tokens"`
-}
-
-type TextRequest struct {
-	Model     string    `json:"model"`
-	Messages  []Message `json:"messages"`
-	Prompt    string    `json:"prompt"`
-	MaxTokens int       `json:"max_tokens"`
-	//Stream   bool      `json:"stream"`
-}
-
-// ImageRequest docs: https://platform.openai.com/docs/api-reference/images/create
-type ImageRequest struct {
-	Model          string `json:"model"`
-	Prompt         string `json:"prompt" binding:"required"`
-	N              int    `json:"n,omitempty"`
-	Size           string `json:"size,omitempty"`
-	Quality        string `json:"quality,omitempty"`
-	ResponseFormat string `json:"response_format,omitempty"`
-	Style          string `json:"style,omitempty"`
-	User           string `json:"user,omitempty"`
-}
-
-type WhisperJSONResponse struct {
-	Text string `json:"text,omitempty"`
-}
-
-type WhisperVerboseJSONResponse struct {
-	Task     string    `json:"task,omitempty"`
-	Language string    `json:"language,omitempty"`
-	Duration float64   `json:"duration,omitempty"`
-	Text     string    `json:"text,omitempty"`
-	Segments []Segment `json:"segments,omitempty"`
-}
-
-type Segment struct {
-	Id               int     `json:"id"`
-	Seek             int     `json:"seek"`
-	Start            float64 `json:"start"`
-	End              float64 `json:"end"`
-	Text             string  `json:"text"`
-	Tokens           []int   `json:"tokens"`
-	Temperature      float64 `json:"temperature"`
-	AvgLogprob       float64 `json:"avg_logprob"`
-	CompressionRatio float64 `json:"compression_ratio"`
-	NoSpeechProb     float64 `json:"no_speech_prob"`
-}
-
-type TextToSpeechRequest struct {
-	Model          string  `json:"model" binding:"required"`
-	Input          string  `json:"input" binding:"required"`
-	Voice          string  `json:"voice" binding:"required"`
-	Speed          float64 `json:"speed"`
-	ResponseFormat string  `json:"response_format"`
-}
-
-type Usage struct {
-	PromptTokens     int `json:"prompt_tokens"`
-	CompletionTokens int `json:"completion_tokens"`
-	TotalTokens      int `json:"total_tokens"`
-}
-
-type OpenAIError struct {
-	Message string `json:"message"`
-	Type    string `json:"type"`
-	Param   string `json:"param"`
-	Code    any    `json:"code"`
-}
-
-type OpenAIErrorWithStatusCode struct {
-	OpenAIError
-	StatusCode int `json:"status_code"`
-}
-
-type TextResponse struct {
-	Choices []OpenAITextResponseChoice `json:"choices"`
-	Usage   `json:"usage"`
-	Error   OpenAIError `json:"error"`
-}
-
-type OpenAITextResponseChoice struct {
-	Index        int `json:"index"`
-	Message      `json:"message"`
-	FinishReason string `json:"finish_reason"`
-}
-
-type OpenAITextResponse struct {
-	Id      string                     `json:"id"`
-	Model   string                     `json:"model,omitempty"`
-	Object  string                     `json:"object"`
-	Created int64                      `json:"created"`
-	Choices []OpenAITextResponseChoice `json:"choices"`
-	Usage   `json:"usage"`
-}
-
-type OpenAIEmbeddingResponseItem struct {
-	Object    string    `json:"object"`
-	Index     int       `json:"index"`
-	Embedding []float64 `json:"embedding"`
-}
-
-type OpenAIEmbeddingResponse struct {
-	Object string                        `json:"object"`
-	Data   []OpenAIEmbeddingResponseItem `json:"data"`
-	Model  string                        `json:"model"`
-	Usage  `json:"usage"`
-}
-
-type ImageResponse struct {
-	Created int `json:"created"`
-	Data    []struct {
-		Url string `json:"url"`
-	}
-}
-
-type ChatCompletionsStreamResponseChoice struct {
-	Delta struct {
-		Content string `json:"content"`
-	} `json:"delta"`
-	FinishReason *string `json:"finish_reason,omitempty"`
-}
-
-type ChatCompletionsStreamResponse struct {
-	Id      string                                `json:"id"`
-	Object  string                                `json:"object"`
-	Created int64                                 `json:"created"`
-	Model   string                                `json:"model"`
-	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
-}
-
-type CompletionsStreamResponse struct {
-	Choices []struct {
-		Text         string `json:"text"`
-		FinishReason string `json:"finish_reason"`
-	} `json:"choices"`
+	return err
 }

 func Relay(c *gin.Context) {
-	relayMode := RelayModeUnknown
-	if strings.HasPrefix(c.Request.URL.Path, "/v1/chat/completions") {
-		relayMode = RelayModeChatCompletions
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/completions") {
-		relayMode = RelayModeCompletions
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/embeddings") {
-		relayMode = RelayModeEmbeddings
-	} else if strings.HasSuffix(c.Request.URL.Path, "embeddings") {
-		relayMode = RelayModeEmbeddings
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
-		relayMode = RelayModeModerations
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
-		relayMode = RelayModeImagesGenerations
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/edits") {
-		relayMode = RelayModeEdits
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
-		relayMode = RelayModeAudioSpeech
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
-		relayMode = RelayModeAudioTranscription
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/translations") {
-		relayMode = RelayModeAudioTranslation
+	ctx := c.Request.Context()
+	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
+	bizErr := relay(c, relayMode)
+	if bizErr == nil {
+		return
 	}
-	var err *OpenAIErrorWithStatusCode
-	switch relayMode {
-	case RelayModeImagesGenerations:
-		err = relayImageHelper(c, relayMode)
-	case RelayModeAudioSpeech:
-		fallthrough
-	case RelayModeAudioTranslation:
-		fallthrough
-	case RelayModeAudioTranscription:
-		err = relayAudioHelper(c, relayMode)
-	default:
-		err = relayTextHelper(c, relayMode)
+	channelId := c.GetInt("channel_id")
+	lastFailedChannelId := channelId
+	channelName := c.GetString("channel_name")
+	group := c.GetString("group")
+	originalModel := c.GetString("original_model")
+	go processChannelRelayError(ctx, channelId, channelName, bizErr)
+	requestId := c.GetString(logger.RequestIdKey)
+	retryTimes := config.RetryTimes
+	if !shouldRetry(bizErr.StatusCode) {
+		logger.Errorf(ctx, "relay error happen, but status code is %d, won't retry in this case", bizErr.StatusCode)
+		retryTimes = 0
 	}
-	if err != nil {
-		requestId := c.GetString(common.RequestIdKey)
-		retryTimesStr := c.Query("retry")
-		retryTimes, _ := strconv.Atoi(retryTimesStr)
-		if retryTimesStr == "" {
-			retryTimes = common.RetryTimes
+	for i := retryTimes; i > 0; i-- {
+		channel, err := dbmodel.CacheGetRandomSatisfiedChannel(group, originalModel)
+		if err != nil {
+			logger.Errorf(ctx, "CacheGetRandomSatisfiedChannel failed: %w", err)
+			break
 		}
-		if retryTimes > 0 {
-			c.Redirect(http.StatusTemporaryRedirect, fmt.Sprintf("%s?retry=%d", c.Request.URL.Path, retryTimes-1))
-		} else {
-			if err.StatusCode == http.StatusTooManyRequests {
-				err.OpenAIError.Message = "当前分组上游负载已饱和，请稍后再试"
-			}
-			err.OpenAIError.Message = common.MessageWithRequestId(err.OpenAIError.Message, requestId)
-			c.JSON(err.StatusCode, gin.H{
-				"error": err.OpenAIError,
-			})
+		logger.Infof(ctx, "using channel #%d to retry (remain times %d)", channel.Id, i)
+		if channel.Id == lastFailedChannelId {
+			continue
+		}
+		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+		bizErr = relay(c, relayMode)
+		if bizErr == nil {
+			return
 		}
 		channelId := c.GetInt("channel_id")
-		common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d): %s", channelId, err.Message))
-		// https://platform.openai.com/docs/guides/error-codes/api-errors
-		if shouldDisableChannel(&err.OpenAIError, err.StatusCode) {
-			channelId := c.GetInt("channel_id")
-			channelName := c.GetString("channel_name")
-			disableChannel(channelId, channelName, err.Message)
+		lastFailedChannelId = channelId
+		channelName := c.GetString("channel_name")
+		go processChannelRelayError(ctx, channelId, channelName, bizErr)
+	}
+	if bizErr != nil {
+		if bizErr.StatusCode == http.StatusTooManyRequests {
+			bizErr.Error.Message = "当前分组上游负载已饱和，请稍后再试"
 		}
+		bizErr.Error.Message = helper.MessageWithRequestId(bizErr.Error.Message, requestId)
+		c.JSON(bizErr.StatusCode, gin.H{
+			"error": bizErr.Error,
+		})
+	}
+}
+
+func shouldRetry(statusCode int) bool {
+	if statusCode == http.StatusTooManyRequests {
+		return true
+	}
+	if statusCode/100 == 5 {
+		return true
+	}
+	if statusCode == http.StatusBadRequest {
+		return false
+	}
+	if statusCode/100 == 2 {
+		return false
+	}
+	return true
+}
+
+func processChannelRelayError(ctx context.Context, channelId int, channelName string, err *model.ErrorWithStatusCode) {
+	logger.Errorf(ctx, "relay error (channel #%d): %s", channelId, err.Message)
+	// https://platform.openai.com/docs/guides/error-codes/api-errors
+	if util.ShouldDisableChannel(&err.Error, err.StatusCode) {
+		disableChannel(channelId, channelName, err.Message)
 	}
 }

 func RelayNotImplemented(c *gin.Context) {
-	err := OpenAIError{
+	err := model.Error{
 		Message: "API not implemented",
 		Type:    "one_api_error",
 		Param:   "",
@@ -390,7 +122,7 @@ func RelayNotImplemented(c *gin.Context) {
 }

 func RelayNotFound(c *gin.Context) {
-	err := OpenAIError{
+	err := model.Error{
 		Message: fmt.Sprintf("Invalid URL (%s %s)", c.Request.Method, c.Request.URL.Path),
 		Type:    "invalid_request_error",
 		Param:   "",
--- a/controller/token.go
+++ b/controller/token.go
@@ -2,9 +2,11 @@ package controller

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 )

@@ -14,7 +16,7 @@ func GetAllTokens(c *gin.Context) {
 	if p < 0 {
 		p = 0
 	}
-	tokens, err := model.GetAllUserTokens(userId, p*common.ItemsPerPage, common.ItemsPerPage)
+	tokens, err := model.GetAllUserTokens(userId, p*config.ItemsPerPage, config.ItemsPerPage)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -119,9 +121,9 @@ func AddToken(c *gin.Context) {
 	cleanToken := model.Token{
 		UserId:         c.GetInt("id"),
 		Name:           token.Name,
-		Key:            common.GenerateKey(),
-		CreatedTime:    common.GetTimestamp(),
-		AccessedTime:   common.GetTimestamp(),
+		Key:            helper.GenerateKey(),
+		CreatedTime:    helper.GetTimestamp(),
+		AccessedTime:   helper.GetTimestamp(),
 		ExpiredTime:    token.ExpiredTime,
 		RemainQuota:    token.RemainQuota,
 		UnlimitedQuota: token.UnlimitedQuota,
@@ -187,7 +189,7 @@ func UpdateToken(c *gin.Context) {
 		return
 	}
 	if token.Status == common.TokenStatusEnabled {
-		if cleanToken.Status == common.TokenStatusExpired && cleanToken.ExpiredTime <= common.GetTimestamp() && cleanToken.ExpiredTime != -1 {
+		if cleanToken.Status == common.TokenStatusExpired && cleanToken.ExpiredTime <= helper.GetTimestamp() && cleanToken.ExpiredTime != -1 {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "令牌已过期，无法启用，请先修改令牌过期时间，或者设置为永不过期",
--- a/controller/user.go
+++ b/controller/user.go
@@ -3,9 +3,11 @@ package controller
 import (
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"

@@ -19,7 +21,7 @@ type LoginRequest struct {
 }

 func Login(c *gin.Context) {
-	if !common.PasswordLoginEnabled {
+	if !config.PasswordLoginEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"message": "管理员关闭了密码登录",
 			"success": false,
@@ -106,14 +108,14 @@ func Logout(c *gin.Context) {
 }

 func Register(c *gin.Context) {
-	if !common.RegisterEnabled {
+	if !config.RegisterEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"message": "管理员关闭了新用户注册",
 			"success": false,
 		})
 		return
 	}
-	if !common.PasswordRegisterEnabled {
+	if !config.PasswordRegisterEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"message": "管理员关闭了通过密码进行注册，请使用第三方账户验证的形式进行注册",
 			"success": false,
@@ -136,7 +138,7 @@ func Register(c *gin.Context) {
 		})
 		return
 	}
-	if common.EmailVerificationEnabled {
+	if config.EmailVerificationEnabled {
 		if user.Email == "" || user.VerificationCode == "" {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -160,7 +162,7 @@ func Register(c *gin.Context) {
 		DisplayName: user.Username,
 		InviterId:   inviterId,
 	}
-	if common.EmailVerificationEnabled {
+	if config.EmailVerificationEnabled {
 		cleanUser.Email = user.Email
 	}
 	if err := cleanUser.Insert(inviterId); err != nil {
@@ -182,7 +184,7 @@ func GetAllUsers(c *gin.Context) {
 	if p < 0 {
 		p = 0
 	}
-	users, err := model.GetAllUsers(p*common.ItemsPerPage, common.ItemsPerPage)
+	users, err := model.GetAllUsers(p*config.ItemsPerPage, config.ItemsPerPage)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -282,7 +284,7 @@ func GenerateAccessToken(c *gin.Context) {
 		})
 		return
 	}
-	user.AccessToken = common.GetUUID()
+	user.AccessToken = helper.GetUUID()

 	if model.DB.Where("access_token = ?", user.AccessToken).First(user).RowsAffected != 0 {
 		c.JSON(http.StatusOK, gin.H{
@@ -319,7 +321,7 @@ func GetAffCode(c *gin.Context) {
 		return
 	}
 	if user.AffCode == "" {
-		user.AffCode = common.GetRandomString(4)
+		user.AffCode = helper.GetRandomString(4)
 		if err := user.Update(false); err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -726,7 +728,7 @@ func EmailBind(c *gin.Context) {
 		return
 	}
 	if user.Role == common.RoleRootUser {
-		common.RootUserEmail = email
+		config.RootUserEmail = email
 	}
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
--- a/controller/wechat.go
+++ b/controller/wechat.go
@@ -5,9 +5,10 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"
 )
@@ -22,11 +23,11 @@ func getWeChatIdByCode(code string) (string, error) {
 	if code == "" {
 		return "", errors.New("无效的参数")
 	}
-	req, err := http.NewRequest("GET", fmt.Sprintf("%s/api/wechat/user?code=%s", common.WeChatServerAddress, code), nil)
+	req, err := http.NewRequest("GET", fmt.Sprintf("%s/api/wechat/user?code=%s", config.WeChatServerAddress, code), nil)
 	if err != nil {
 		return "", err
 	}
-	req.Header.Set("Authorization", common.WeChatServerToken)
+	req.Header.Set("Authorization", config.WeChatServerToken)
 	client := http.Client{
 		Timeout: 5 * time.Second,
 	}
@@ -50,7 +51,7 @@ func getWeChatIdByCode(code string) (string, error) {
 }

 func WeChatAuth(c *gin.Context) {
-	if !common.WeChatAuthEnabled {
+	if !config.WeChatAuthEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"message": "管理员未开启通过微信登录以及注册",
 			"success": false,
@@ -79,7 +80,7 @@ func WeChatAuth(c *gin.Context) {
 			return
 		}
 	} else {
-		if common.RegisterEnabled {
+		if config.RegisterEnabled {
 			user.Username = "wechat_" + strconv.Itoa(model.GetMaxUserId()+1)
 			user.DisplayName = "WeChat User"
 			user.Role = common.RoleCommonUser
@@ -112,7 +113,7 @@ func WeChatAuth(c *gin.Context) {
 }

 func WeChatBind(c *gin.Context) {
-	if !common.WeChatAuthEnabled {
+	if !config.WeChatAuthEnabled {
 		c.JSON(http.StatusOK, gin.H{
 			"message": "管理员未开启通过微信登录以及注册",
 			"success": false,
--- a/go.mod
+++ b/go.mod
@@ -1,4 +1,4 @@
-module one-api
+module github.com/songquanpeng/one-api

 // +heroku goVersion go1.18
 go 1.18
--- a/i18n/en.json
+++ b/i18n/en.json
@@ -456,6 +456,7 @@
  "已绑定的邮箱账户": "Email Account Bound",
  "用户信息更新成功！": "User information updated successfully!",
  "模型倍率 %.2f，分组倍率 %.2f": "model rate %.2f, group rate %.2f",
+  "模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f": "model rate %.2f, group rate %.2f, completion rate %.2f",
  "使用明细（总消耗额度：{renderQuota(stat.quota)}）": "Usage Details (Total Consumption Quota: {renderQuota(stat.quota)})",
  "用户名称": "User Name",
  "令牌名称": "Token Name",
--- a/main.go
+++ b/main.go
@@ -6,11 +6,14 @@ import (
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
-	"one-api/common"
-	"one-api/controller"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/router"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/controller"
+	"github.com/songquanpeng/one-api/middleware"
+	"github.com/songquanpeng/one-api/model"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/router"
 	"os"
 	"strconv"
 )
@@ -19,68 +22,68 @@ import (
 var buildFS embed.FS

 func main() {
-	common.SetupLogger()
-	common.SysLog(fmt.Sprintf("One API %s started", common.Version))
+	logger.SetupLogger()
+	logger.SysLog(fmt.Sprintf("One API %s started", common.Version))
 	if os.Getenv("GIN_MODE") != "debug" {
 		gin.SetMode(gin.ReleaseMode)
 	}
-	if common.DebugEnabled {
-		common.SysLog("running in debug mode")
+	if config.DebugEnabled {
+		logger.SysLog("running in debug mode")
 	}
 	// Initialize SQL Database
 	err := model.InitDB()
 	if err != nil {
-		common.FatalLog("failed to initialize database: " + err.Error())
+		logger.FatalLog("failed to initialize database: " + err.Error())
 	}
 	defer func() {
 		err := model.CloseDB()
 		if err != nil {
-			common.FatalLog("failed to close database: " + err.Error())
+			logger.FatalLog("failed to close database: " + err.Error())
 		}
 	}()

 	// Initialize Redis
 	err = common.InitRedisClient()
 	if err != nil {
-		common.FatalLog("failed to initialize Redis: " + err.Error())
+		logger.FatalLog("failed to initialize Redis: " + err.Error())
 	}

 	// Initialize options
 	model.InitOptionMap()
-	common.SysLog(fmt.Sprintf("using theme %s", common.Theme))
+	logger.SysLog(fmt.Sprintf("using theme %s", config.Theme))
 	if common.RedisEnabled {
 		// for compatibility with old versions
-		common.MemoryCacheEnabled = true
+		config.MemoryCacheEnabled = true
 	}
-	if common.MemoryCacheEnabled {
-		common.SysLog("memory cache enabled")
-		common.SysError(fmt.Sprintf("sync frequency: %d seconds", common.SyncFrequency))
+	if config.MemoryCacheEnabled {
+		logger.SysLog("memory cache enabled")
+		logger.SysError(fmt.Sprintf("sync frequency: %d seconds", config.SyncFrequency))
 		model.InitChannelCache()
 	}
-	if common.MemoryCacheEnabled {
-		go model.SyncOptions(common.SyncFrequency)
-		go model.SyncChannelCache(common.SyncFrequency)
+	if config.MemoryCacheEnabled {
+		go model.SyncOptions(config.SyncFrequency)
+		go model.SyncChannelCache(config.SyncFrequency)
 	}
 	if os.Getenv("CHANNEL_UPDATE_FREQUENCY") != "" {
 		frequency, err := strconv.Atoi(os.Getenv("CHANNEL_UPDATE_FREQUENCY"))
 		if err != nil {
-			common.FatalLog("failed to parse CHANNEL_UPDATE_FREQUENCY: " + err.Error())
+			logger.FatalLog("failed to parse CHANNEL_UPDATE_FREQUENCY: " + err.Error())
 		}
 		go controller.AutomaticallyUpdateChannels(frequency)
 	}
 	if os.Getenv("CHANNEL_TEST_FREQUENCY") != "" {
 		frequency, err := strconv.Atoi(os.Getenv("CHANNEL_TEST_FREQUENCY"))
 		if err != nil {
-			common.FatalLog("failed to parse CHANNEL_TEST_FREQUENCY: " + err.Error())
+			logger.FatalLog("failed to parse CHANNEL_TEST_FREQUENCY: " + err.Error())
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
 	if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
-		common.BatchUpdateEnabled = true
-		common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")
+		config.BatchUpdateEnabled = true
+		logger.SysLog("batch update enabled with interval " + strconv.Itoa(config.BatchUpdateInterval) + "s")
 		model.InitBatchUpdater()
 	}
-	controller.InitTokenEncoders()
+	openai.InitTokenEncoders()

 	// Initialize HTTP server
 	server := gin.New()
@@ -90,7 +93,7 @@ func main() {
 	server.Use(middleware.RequestId())
 	middleware.SetUpLogger(server)
 	// Initialize session store
-	store := cookie.NewStore([]byte(common.SessionSecret))
+	store := cookie.NewStore([]byte(config.SessionSecret))
 	server.Use(sessions.Sessions("session", store))

 	router.SetRouter(server, buildFS)
@@ -100,6 +103,6 @@ func main() {
 	}
 	err = server.Run(":" + port)
 	if err != nil {
-		common.FatalLog("failed to start HTTP server: " + err.Error())
+		logger.FatalLog("failed to start HTTP server: " + err.Error())
 	}
 }
--- a/middleware/auth.go
+++ b/middleware/auth.go
@@ -3,9 +3,9 @@ package middleware
 import (
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strings"
 )

@@ -108,7 +108,7 @@ func TokenAuth() func(c *gin.Context) {
 		c.Set("token_name", token.Name)
 		if len(parts) > 1 {
 			if model.IsAdmin(token.UserId) {
-				c.Set("channelId", parts[1])
+				c.Set("specific_channel_id", parts[1])
 			} else {
 				abortWithMessage(c, http.StatusForbidden, "普通用户不支持指定渠道")
 				return
--- a/middleware/distributor.go
+++ b/middleware/distributor.go
@@ -2,9 +2,10 @@ package middleware

 import (
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/model"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"strings"

@@ -20,8 +21,9 @@ func Distribute() func(c *gin.Context) {
 		userId := c.GetInt("id")
 		userGroup, _ := model.CacheGetUserGroup(userId)
 		c.Set("group", userGroup)
+		var requestModel string
 		var channel *model.Channel
-		channelId, ok := c.Get("channelId")
+		channelId, ok := c.Get("specific_channel_id")
 		if ok {
 			id, err := strconv.Atoi(channelId.(string))
 			if err != nil {
@@ -65,35 +67,46 @@ func Distribute() func(c *gin.Context) {
 					modelRequest.Model = "whisper-1"
 				}
 			}
+			requestModel = modelRequest.Model
 			channel, err = model.CacheGetRandomSatisfiedChannel(userGroup, modelRequest.Model)
 			if err != nil {
 				message := fmt.Sprintf("当前分组 %s 下对于模型 %s 无可用渠道", userGroup, modelRequest.Model)
 				if channel != nil {
-					common.SysError(fmt.Sprintf("渠道不存在：%d", channel.Id))
+					logger.SysError(fmt.Sprintf("渠道不存在：%d", channel.Id))
 					message = "数据库一致性已被破坏，请联系管理员"
 				}
 				abortWithMessage(c, http.StatusServiceUnavailable, message)
 				return
 			}
 		}
-		c.Set("channel", channel.Type)
-		c.Set("channel_id", channel.Id)
-		c.Set("channel_name", channel.Name)
-		c.Set("model_mapping", channel.GetModelMapping())
-		c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
-		c.Set("base_url", channel.GetBaseURL())
-		switch channel.Type {
-		case common.ChannelTypeAzure:
-			c.Set("api_version", channel.Other)
-		case common.ChannelTypeXunfei:
-			c.Set("api_version", channel.Other)
-		case common.ChannelTypeGemini:
-			c.Set("api_version", channel.Other)
-		case common.ChannelTypeAIProxyLibrary:
-			c.Set("library_id", channel.Other)
-		case common.ChannelTypeAli:
-			c.Set("plugin", channel.Other)
-		}
+		SetupContextForSelectedChannel(c, channel, requestModel)
 		c.Next()
 	}
 }
+
+func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, modelName string) {
+	c.Set("channel", channel.Type)
+	c.Set("channel_id", channel.Id)
+	c.Set("channel_name", channel.Name)
+	c.Set("model_mapping", channel.GetModelMapping())
+	c.Set("original_model", modelName) // for retry
+	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
+	c.Set("base_url", channel.GetBaseURL())
+	// this is for backward compatibility
+	switch channel.Type {
+	case common.ChannelTypeAzure:
+		c.Set(common.ConfigKeyAPIVersion, channel.Other)
+	case common.ChannelTypeXunfei:
+		c.Set(common.ConfigKeyAPIVersion, channel.Other)
+	case common.ChannelTypeGemini:
+		c.Set(common.ConfigKeyAPIVersion, channel.Other)
+	case common.ChannelTypeAIProxyLibrary:
+		c.Set(common.ConfigKeyLibraryID, channel.Other)
+	case common.ChannelTypeAli:
+		c.Set(common.ConfigKeyPlugin, channel.Other)
+	}
+	cfg, _ := channel.LoadConfig()
+	for k, v := range cfg {
+		c.Set(common.ConfigKeyPrefix+k, v)
+	}
+}
--- a/middleware/logger.go
+++ b/middleware/logger.go
@@ -3,14 +3,14 @@ package middleware
 import (
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common/logger"
 )

 func SetUpLogger(server *gin.Engine) {
 	server.Use(gin.LoggerWithFormatter(func(param gin.LogFormatterParams) string {
 		var requestID string
 		if param.Keys != nil {
-			requestID = param.Keys[common.RequestIdKey].(string)
+			requestID = param.Keys[logger.RequestIdKey].(string)
 		}
 		return fmt.Sprintf("[GIN] %s | %s | %3d | %13v | %15s | %7s %s\n",
 			param.TimeStamp.Format("2006/01/02 - 15:04:05"),
--- a/middleware/rate-limit.go
+++ b/middleware/rate-limit.go
@@ -4,8 +4,9 @@ import (
 	"context"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
 	"net/http"
-	"one-api/common"
 	"time"
 )

@@ -26,7 +27,7 @@ func redisRateLimiter(c *gin.Context, maxRequestNum int, duration int64, mark st
 	}
 	if listLength < int64(maxRequestNum) {
 		rdb.LPush(ctx, key, time.Now().Format(timeFormat))
-		rdb.Expire(ctx, key, common.RateLimitKeyExpirationDuration)
+		rdb.Expire(ctx, key, config.RateLimitKeyExpirationDuration)
 	} else {
 		oldTimeStr, _ := rdb.LIndex(ctx, key, -1).Result()
 		oldTime, err := time.Parse(timeFormat, oldTimeStr)
@@ -47,14 +48,14 @@ func redisRateLimiter(c *gin.Context, maxRequestNum int, duration int64, mark st
 		// time.Since will return negative number!
 		// See: https://stackoverflow.com/questions/50970900/why-is-time-since-returning-negative-durations-on-windows
 		if int64(nowTime.Sub(oldTime).Seconds()) < duration {
-			rdb.Expire(ctx, key, common.RateLimitKeyExpirationDuration)
+			rdb.Expire(ctx, key, config.RateLimitKeyExpirationDuration)
 			c.Status(http.StatusTooManyRequests)
 			c.Abort()
 			return
 		} else {
 			rdb.LPush(ctx, key, time.Now().Format(timeFormat))
 			rdb.LTrim(ctx, key, 0, int64(maxRequestNum-1))
-			rdb.Expire(ctx, key, common.RateLimitKeyExpirationDuration)
+			rdb.Expire(ctx, key, config.RateLimitKeyExpirationDuration)
 		}
 	}
 }
@@ -75,7 +76,7 @@ func rateLimitFactory(maxRequestNum int, duration int64, mark string) func(c *gi
 		}
 	} else {
 		// It's safe to call multi times.
-		inMemoryRateLimiter.Init(common.RateLimitKeyExpirationDuration)
+		inMemoryRateLimiter.Init(config.RateLimitKeyExpirationDuration)
 		return func(c *gin.Context) {
 			memoryRateLimiter(c, maxRequestNum, duration, mark)
 		}
@@ -83,21 +84,21 @@ func rateLimitFactory(maxRequestNum int, duration int64, mark string) func(c *gi
 }

 func GlobalWebRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.GlobalWebRateLimitNum, common.GlobalWebRateLimitDuration, "GW")
+	return rateLimitFactory(config.GlobalWebRateLimitNum, config.GlobalWebRateLimitDuration, "GW")
 }

 func GlobalAPIRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.GlobalApiRateLimitNum, common.GlobalApiRateLimitDuration, "GA")
+	return rateLimitFactory(config.GlobalApiRateLimitNum, config.GlobalApiRateLimitDuration, "GA")
 }

 func CriticalRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.CriticalRateLimitNum, common.CriticalRateLimitDuration, "CT")
+	return rateLimitFactory(config.CriticalRateLimitNum, config.CriticalRateLimitDuration, "CT")
 }

 func DownloadRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.DownloadRateLimitNum, common.DownloadRateLimitDuration, "DW")
+	return rateLimitFactory(config.DownloadRateLimitNum, config.DownloadRateLimitDuration, "DW")
 }

 func UploadRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.UploadRateLimitNum, common.UploadRateLimitDuration, "UP")
+	return rateLimitFactory(config.UploadRateLimitNum, config.UploadRateLimitDuration, "UP")
 }
--- a/middleware/recover.go
+++ b/middleware/recover.go
@@ -3,8 +3,8 @@ package middleware
 import (
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/logger"
 	"net/http"
-	"one-api/common"
 	"runtime/debug"
 )

@@ -12,8 +12,8 @@ func RelayPanicRecover() gin.HandlerFunc {
 	return func(c *gin.Context) {
 		defer func() {
 			if err := recover(); err != nil {
-				common.SysError(fmt.Sprintf("panic detected: %v", err))
-				common.SysError(fmt.Sprintf("stacktrace from panic: %s", string(debug.Stack())))
+				logger.SysError(fmt.Sprintf("panic detected: %v", err))
+				logger.SysError(fmt.Sprintf("stacktrace from panic: %s", string(debug.Stack())))
 				c.JSON(http.StatusInternalServerError, gin.H{
 					"error": gin.H{
 						"message": fmt.Sprintf("Panic detected, error: %v. Please submit a issue here: https://github.com/songquanpeng/one-api", err),
--- a/middleware/request-id.go
+++ b/middleware/request-id.go
@@ -3,16 +3,17 @@ package middleware
 import (
 	"context"
 	"github.com/gin-gonic/gin"
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 )

 func RequestId() func(c *gin.Context) {
 	return func(c *gin.Context) {
-		id := common.GetTimeString() + common.GetRandomString(8)
-		c.Set(common.RequestIdKey, id)
-		ctx := context.WithValue(c.Request.Context(), common.RequestIdKey, id)
+		id := helper.GetTimeString() + helper.GetRandomNumberString(8)
+		c.Set(logger.RequestIdKey, id)
+		ctx := context.WithValue(c.Request.Context(), logger.RequestIdKey, id)
 		c.Request = c.Request.WithContext(ctx)
-		c.Header(common.RequestIdKey, id)
+		c.Header(logger.RequestIdKey, id)
 		c.Next()
 	}
 }
--- a/middleware/turnstile-check.go
+++ b/middleware/turnstile-check.go
@@ -4,9 +4,10 @@ import (
 	"encoding/json"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
 	"net/http"
 	"net/url"
-	"one-api/common"
 )

 type turnstileCheckResponse struct {
@@ -15,7 +16,7 @@ type turnstileCheckResponse struct {

 func TurnstileCheck() gin.HandlerFunc {
 	return func(c *gin.Context) {
-		if common.TurnstileCheckEnabled {
+		if config.TurnstileCheckEnabled {
 			session := sessions.Default(c)
 			turnstileChecked := session.Get("turnstile")
 			if turnstileChecked != nil {
@@ -32,12 +33,12 @@ func TurnstileCheck() gin.HandlerFunc {
 				return
 			}
 			rawRes, err := http.PostForm("https://challenges.cloudflare.com/turnstile/v0/siteverify", url.Values{
-				"secret":   {common.TurnstileSecretKey},
+				"secret":   {config.TurnstileSecretKey},
 				"response": {response},
 				"remoteip": {c.ClientIP()},
 			})
 			if err != nil {
-				common.SysError(err.Error())
+				logger.SysError(err.Error())
 				c.JSON(http.StatusOK, gin.H{
 					"success": false,
 					"message": err.Error(),
@@ -49,7 +50,7 @@ func TurnstileCheck() gin.HandlerFunc {
 			var res turnstileCheckResponse
 			err = json.NewDecoder(rawRes.Body).Decode(&res)
 			if err != nil {
-				common.SysError(err.Error())
+				logger.SysError(err.Error())
 				c.JSON(http.StatusOK, gin.H{
 					"success": false,
 					"message": err.Error(),
--- a/middleware/utils.go
+++ b/middleware/utils.go
@@ -2,16 +2,17 @@ package middleware

 import (
 	"github.com/gin-gonic/gin"
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 )

 func abortWithMessage(c *gin.Context, statusCode int, message string) {
 	c.JSON(statusCode, gin.H{
 		"error": gin.H{
-			"message": common.MessageWithRequestId(message, c.GetString(common.RequestIdKey)),
+			"message": helper.MessageWithRequestId(message, c.GetString(logger.RequestIdKey)),
 			"type":    "one_api_error",
 		},
 	})
 	c.Abort()
-	common.LogError(c.Request.Context(), message)
+	logger.Error(c.Request.Context(), message)
 }
--- a/model/ability.go
+++ b/model/ability.go
@@ -1,7 +1,7 @@
 package model

 import (
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common"
 	"strings"
 )

--- a/model/cache.go
+++ b/model/cache.go
@@ -4,8 +4,10 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
 	"math/rand"
-	"one-api/common"
 	"sort"
 	"strconv"
 	"strings"
@@ -14,10 +16,10 @@ import (
 )

 var (
-	TokenCacheSeconds         = common.SyncFrequency
-	UserId2GroupCacheSeconds  = common.SyncFrequency
-	UserId2QuotaCacheSeconds  = common.SyncFrequency
-	UserId2StatusCacheSeconds = common.SyncFrequency
+	TokenCacheSeconds         = config.SyncFrequency
+	UserId2GroupCacheSeconds  = config.SyncFrequency
+	UserId2QuotaCacheSeconds  = config.SyncFrequency
+	UserId2StatusCacheSeconds = config.SyncFrequency
 )

 func CacheGetTokenByKey(key string) (*Token, error) {
@@ -42,7 +44,7 @@ func CacheGetTokenByKey(key string) (*Token, error) {
 		}
 		err = common.RedisSet(fmt.Sprintf("token:%s", key), string(jsonBytes), time.Duration(TokenCacheSeconds)*time.Second)
 		if err != nil {
-			common.SysError("Redis set token error: " + err.Error())
+			logger.SysError("Redis set token error: " + err.Error())
 		}
 		return &token, nil
 	}
@@ -62,7 +64,7 @@ func CacheGetUserGroup(id int) (group string, err error) {
 		}
 		err = common.RedisSet(fmt.Sprintf("user_group:%d", id), group, time.Duration(UserId2GroupCacheSeconds)*time.Second)
 		if err != nil {
-			common.SysError("Redis set user group error: " + err.Error())
+			logger.SysError("Redis set user group error: " + err.Error())
 		}
 	}
 	return group, err
@@ -80,7 +82,7 @@ func CacheGetUserQuota(id int) (quota int, err error) {
 		}
 		err = common.RedisSet(fmt.Sprintf("user_quota:%d", id), fmt.Sprintf("%d", quota), time.Duration(UserId2QuotaCacheSeconds)*time.Second)
 		if err != nil {
-			common.SysError("Redis set user quota error: " + err.Error())
+			logger.SysError("Redis set user quota error: " + err.Error())
 		}
 		return quota, err
 	}
@@ -92,7 +94,7 @@ func CacheUpdateUserQuota(id int) error {
 	if !common.RedisEnabled {
 		return nil
 	}
-	quota, err := GetUserQuota(id)
+	quota, err := CacheGetUserQuota(id)
 	if err != nil {
 		return err
 	}
@@ -127,7 +129,7 @@ func CacheIsUserEnabled(userId int) (bool, error) {
 	}
 	err = common.RedisSet(fmt.Sprintf("user_enabled:%d", userId), enabled, time.Duration(UserId2StatusCacheSeconds)*time.Second)
 	if err != nil {
-		common.SysError("Redis set user enabled error: " + err.Error())
+		logger.SysError("Redis set user enabled error: " + err.Error())
 	}
 	return userEnabled, err
 }
@@ -178,19 +180,19 @@ func InitChannelCache() {
 	channelSyncLock.Lock()
 	group2model2channels = newGroup2model2channels
 	channelSyncLock.Unlock()
-	common.SysLog("channels synced from database")
+	logger.SysLog("channels synced from database")
 }

 func SyncChannelCache(frequency int) {
 	for {
 		time.Sleep(time.Duration(frequency) * time.Second)
-		common.SysLog("syncing channels from database")
+		logger.SysLog("syncing channels from database")
 		InitChannelCache()
 	}
 }

 func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
-	if !common.MemoryCacheEnabled {
+	if !config.MemoryCacheEnabled {
 		return GetRandomSatisfiedChannel(group, model)
 	}
 	channelSyncLock.RLock()
--- a/model/channel.go
+++ b/model/channel.go
@@ -1,8 +1,13 @@
 package model

 import (
+	"encoding/json"
+	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 	"gorm.io/gorm"
-	"one-api/common"
 )

 type Channel struct {
@@ -16,7 +21,7 @@ type Channel struct {
 	TestTime           int64   `json:"test_time" gorm:"bigint"`
 	ResponseTime       int     `json:"response_time"` // in milliseconds
 	BaseURL            *string `json:"base_url" gorm:"column:base_url;default:''"`
-	Other              string  `json:"other"`
+	Other              string  `json:"other"`   // DEPRECATED: please save config to field Config
 	Balance            float64 `json:"balance"` // in USD
 	BalanceUpdatedTime int64   `json:"balance_updated_time" gorm:"bigint"`
 	Models             string  `json:"models"`
@@ -24,6 +29,7 @@ type Channel struct {
 	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
 	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
 	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
+	Config             string  `json:"config"`
 }

 func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
@@ -42,7 +48,7 @@ func SearchChannels(keyword string) (channels []*Channel, err error) {
 	if common.UsingPostgreSQL {
 		keyCol = `"key"`
 	}
-	err = DB.Omit("key").Where("id = ? or name LIKE ? or "+keyCol+" = ?", common.String2Int(keyword), keyword+"%", keyword).Find(&channels).Error
+	err = DB.Omit("key").Where("id = ? or name LIKE ? or "+keyCol+" = ?", helper.String2Int(keyword), keyword+"%", keyword).Find(&channels).Error
 	return channels, err
 }

@@ -86,11 +92,17 @@ func (channel *Channel) GetBaseURL() string {
 	return *channel.BaseURL
 }

-func (channel *Channel) GetModelMapping() string {
-	if channel.ModelMapping == nil {
-		return ""
+func (channel *Channel) GetModelMapping() map[string]string {
+	if channel.ModelMapping == nil || *channel.ModelMapping == "" || *channel.ModelMapping == "{}" {
+		return nil
 	}
-	return *channel.ModelMapping
+	modelMapping := make(map[string]string)
+	err := json.Unmarshal([]byte(*channel.ModelMapping), &modelMapping)
+	if err != nil {
+		logger.SysError(fmt.Sprintf("failed to unmarshal model mapping for channel %d, error: %s", channel.Id, err.Error()))
+		return nil
+	}
+	return modelMapping
 }

 func (channel *Channel) Insert() error {
@@ -116,21 +128,21 @@ func (channel *Channel) Update() error {

 func (channel *Channel) UpdateResponseTime(responseTime int64) {
 	err := DB.Model(channel).Select("response_time", "test_time").Updates(Channel{
-		TestTime:     common.GetTimestamp(),
+		TestTime:     helper.GetTimestamp(),
 		ResponseTime: int(responseTime),
 	}).Error
 	if err != nil {
-		common.SysError("failed to update response time: " + err.Error())
+		logger.SysError("failed to update response time: " + err.Error())
 	}
 }

 func (channel *Channel) UpdateBalance(balance float64) {
 	err := DB.Model(channel).Select("balance_updated_time", "balance").Updates(Channel{
-		BalanceUpdatedTime: common.GetTimestamp(),
+		BalanceUpdatedTime: helper.GetTimestamp(),
 		Balance:            balance,
 	}).Error
 	if err != nil {
-		common.SysError("failed to update balance: " + err.Error())
+		logger.SysError("failed to update balance: " + err.Error())
 	}
 }

@@ -144,19 +156,31 @@ func (channel *Channel) Delete() error {
 	return err
 }

+func (channel *Channel) LoadConfig() (map[string]string, error) {
+	if channel.Config == "" {
+		return nil, nil
+	}
+	cfg := make(map[string]string)
+	err := json.Unmarshal([]byte(channel.Config), &cfg)
+	if err != nil {
+		return nil, err
+	}
+	return cfg, nil
+}
+
 func UpdateChannelStatusById(id int, status int) {
 	err := UpdateAbilityStatus(id, status == common.ChannelStatusEnabled)
 	if err != nil {
-		common.SysError("failed to update ability status: " + err.Error())
+		logger.SysError("failed to update ability status: " + err.Error())
 	}
 	err = DB.Model(&Channel{}).Where("id = ?", id).Update("status", status).Error
 	if err != nil {
-		common.SysError("failed to update channel status: " + err.Error())
+		logger.SysError("failed to update channel status: " + err.Error())
 	}
 }

 func UpdateChannelUsedQuota(id int, quota int) {
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeChannelUsedQuota, id, quota)
 		return
 	}
@@ -166,7 +190,7 @@ func UpdateChannelUsedQuota(id int, quota int) {
 func updateChannelUsedQuota(id int, quota int) {
 	err := DB.Model(&Channel{}).Where("id = ?", id).Update("used_quota", gorm.Expr("used_quota + ?", quota)).Error
 	if err != nil {
-		common.SysError("failed to update channel used quota: " + err.Error())
+		logger.SysError("failed to update channel used quota: " + err.Error())
 	}
 }

--- a/model/log.go
+++ b/model/log.go
@@ -3,15 +3,18 @@ package model
 import (
 	"context"
 	"fmt"
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"

 	"gorm.io/gorm"
 )

 type Log struct {
-	Id               int    `json:"id;index:idx_created_at_id,priority:1"`
+	Id               int    `json:"id"`
 	UserId           int    `json:"user_id" gorm:"index"`
-	CreatedAt        int64  `json:"created_at" gorm:"bigint;index:idx_created_at_id,priority:2;index:idx_created_at_type"`
+	CreatedAt        int64  `json:"created_at" gorm:"bigint;index:idx_created_at_type"`
 	Type             int    `json:"type" gorm:"index:idx_created_at_type"`
 	Content          string `json:"content"`
 	Username         string `json:"username" gorm:"index:index_username_model_name,priority:2;default:''"`
@@ -32,31 +35,31 @@ const (
 )

 func RecordLog(userId int, logType int, content string) {
-	if logType == LogTypeConsume && !common.LogConsumeEnabled {
+	if logType == LogTypeConsume && !config.LogConsumeEnabled {
 		return
 	}
 	log := &Log{
 		UserId:    userId,
 		Username:  GetUsernameById(userId),
-		CreatedAt: common.GetTimestamp(),
+		CreatedAt: helper.GetTimestamp(),
 		Type:      logType,
 		Content:   content,
 	}
 	err := DB.Create(log).Error
 	if err != nil {
-		common.SysError("failed to record log: " + err.Error())
+		logger.SysError("failed to record log: " + err.Error())
 	}
 }

 func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string) {
-	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
-	if !common.LogConsumeEnabled {
+	logger.Info(ctx, fmt.Sprintf("record consume log: userId=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
+	if !config.LogConsumeEnabled {
 		return
 	}
 	log := &Log{
 		UserId:           userId,
 		Username:         GetUsernameById(userId),
-		CreatedAt:        common.GetTimestamp(),
+		CreatedAt:        helper.GetTimestamp(),
 		Type:             LogTypeConsume,
 		Content:          content,
 		PromptTokens:     promptTokens,
@@ -68,7 +71,7 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 	}
 	err := DB.Create(log).Error
 	if err != nil {
-		common.LogError(ctx, "failed to record log: "+err.Error())
+		logger.Error(ctx, "failed to record log: "+err.Error())
 	}
 }

@@ -125,12 +128,12 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 }

 func SearchAllLogs(keyword string) (logs []*Log, err error) {
-	err = DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
+	err = DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(config.MaxRecentItems).Find(&logs).Error
 	return logs, err
 }

 func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
-	err = DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
+	err = DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(config.MaxRecentItems).Omit("id").Find(&logs).Error
 	return logs, err
 }

--- a/model/main.go
+++ b/model/main.go
@@ -2,11 +2,14 @@ package model

 import (
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 	"gorm.io/driver/mysql"
 	"gorm.io/driver/postgres"
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
-	"one-api/common"
 	"os"
 	"strings"
 	"time"
@@ -16,9 +19,9 @@ var DB *gorm.DB

 func createRootAccountIfNeed() error {
 	var user User
-	//if user.Status != common.UserStatusEnabled {
+	//if user.Status != util.UserStatusEnabled {
 	if err := DB.First(&user).Error; err != nil {
-		common.SysLog("no user exists, create a root user for you: username is root, password is 123456")
+		logger.SysLog("no user exists, create a root user for you: username is root, password is 123456")
 		hashedPassword, err := common.Password2Hash("123456")
 		if err != nil {
 			return err
@@ -29,7 +32,7 @@ func createRootAccountIfNeed() error {
 			Role:        common.RoleRootUser,
 			Status:      common.UserStatusEnabled,
 			DisplayName: "Root User",
-			AccessToken: common.GetUUID(),
+			AccessToken: helper.GetUUID(),
 			Quota:       100000000,
 		}
 		DB.Create(&rootUser)
@@ -42,7 +45,7 @@ func chooseDB() (*gorm.DB, error) {
 		dsn := os.Getenv("SQL_DSN")
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
-			common.SysLog("using PostgreSQL as database")
+			logger.SysLog("using PostgreSQL as database")
 			common.UsingPostgreSQL = true
 			return gorm.Open(postgres.New(postgres.Config{
 				DSN:                  dsn,
@@ -52,13 +55,13 @@ func chooseDB() (*gorm.DB, error) {
 			})
 		}
 		// Use MySQL
-		common.SysLog("using MySQL as database")
+		logger.SysLog("using MySQL as database")
 		return gorm.Open(mysql.Open(dsn), &gorm.Config{
 			PrepareStmt: true, // precompile SQL
 		})
 	}
 	// Use SQLite
-	common.SysLog("SQL_DSN not set, using SQLite as database")
+	logger.SysLog("SQL_DSN not set, using SQLite as database")
 	common.UsingSQLite = true
 	config := fmt.Sprintf("?_busy_timeout=%d", common.SQLiteBusyTimeout)
 	return gorm.Open(sqlite.Open(common.SQLitePath+config), &gorm.Config{
@@ -69,7 +72,7 @@ func chooseDB() (*gorm.DB, error) {
 func InitDB() (err error) {
 	db, err := chooseDB()
 	if err == nil {
-		if common.DebugEnabled {
+		if config.DebugEnabled {
 			db = db.Debug()
 		}
 		DB = db
@@ -77,14 +80,14 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
-		sqlDB.SetMaxIdleConns(common.GetOrDefault("SQL_MAX_IDLE_CONNS", 100))
-		sqlDB.SetMaxOpenConns(common.GetOrDefault("SQL_MAX_OPEN_CONNS", 1000))
-		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetOrDefault("SQL_MAX_LIFETIME", 60)))
+		sqlDB.SetMaxIdleConns(helper.GetOrDefaultEnvInt("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(helper.GetOrDefaultEnvInt("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(helper.GetOrDefaultEnvInt("SQL_MAX_LIFETIME", 60)))

-		if !common.IsMasterNode {
+		if !config.IsMasterNode {
 			return nil
 		}
-		common.SysLog("database migration started")
+		logger.SysLog("database migration started")
 		err = db.AutoMigrate(&Channel{})
 		if err != nil {
 			return err
@@ -113,11 +116,11 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
-		common.SysLog("database migrated")
+		logger.SysLog("database migrated")
 		err = createRootAccountIfNeed()
 		return err
 	} else {
-		common.FatalLog(err)
+		logger.FatalLog(err)
 	}
 	return err
 }
--- a/model/option.go
+++ b/model/option.go
@@ -1,7 +1,9 @@
 package model

 import (
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
 	"strconv"
 	"strings"
 	"time"
@@ -20,60 +22,57 @@ func AllOption() ([]*Option, error) {
 }

 func InitOptionMap() {
-	common.OptionMapRWMutex.Lock()
-	common.OptionMap = make(map[string]string)
-	common.OptionMap["FileUploadPermission"] = strconv.Itoa(common.FileUploadPermission)
-	common.OptionMap["FileDownloadPermission"] = strconv.Itoa(common.FileDownloadPermission)
-	common.OptionMap["ImageUploadPermission"] = strconv.Itoa(common.ImageUploadPermission)
-	common.OptionMap["ImageDownloadPermission"] = strconv.Itoa(common.ImageDownloadPermission)
-	common.OptionMap["PasswordLoginEnabled"] = strconv.FormatBool(common.PasswordLoginEnabled)
-	common.OptionMap["PasswordRegisterEnabled"] = strconv.FormatBool(common.PasswordRegisterEnabled)
-	common.OptionMap["EmailVerificationEnabled"] = strconv.FormatBool(common.EmailVerificationEnabled)
-	common.OptionMap["GitHubOAuthEnabled"] = strconv.FormatBool(common.GitHubOAuthEnabled)
-	common.OptionMap["WeChatAuthEnabled"] = strconv.FormatBool(common.WeChatAuthEnabled)
-	common.OptionMap["TurnstileCheckEnabled"] = strconv.FormatBool(common.TurnstileCheckEnabled)
-	common.OptionMap["RegisterEnabled"] = strconv.FormatBool(common.RegisterEnabled)
-	common.OptionMap["AutomaticDisableChannelEnabled"] = strconv.FormatBool(common.AutomaticDisableChannelEnabled)
-	common.OptionMap["AutomaticEnableChannelEnabled"] = strconv.FormatBool(common.AutomaticEnableChannelEnabled)
-	common.OptionMap["ApproximateTokenEnabled"] = strconv.FormatBool(common.ApproximateTokenEnabled)
-	common.OptionMap["LogConsumeEnabled"] = strconv.FormatBool(common.LogConsumeEnabled)
-	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
-	common.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(common.DisplayTokenStatEnabled)
-	common.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(common.ChannelDisableThreshold, 'f', -1, 64)
-	common.OptionMap["EmailDomainRestrictionEnabled"] = strconv.FormatBool(common.EmailDomainRestrictionEnabled)
-	common.OptionMap["EmailDomainWhitelist"] = strings.Join(common.EmailDomainWhitelist, ",")
-	common.OptionMap["SMTPServer"] = ""
-	common.OptionMap["SMTPFrom"] = ""
-	common.OptionMap["SMTPPort"] = strconv.Itoa(common.SMTPPort)
-	common.OptionMap["SMTPAccount"] = ""
-	common.OptionMap["SMTPToken"] = ""
-	common.OptionMap["Notice"] = ""
-	common.OptionMap["About"] = ""
-	common.OptionMap["HomePageContent"] = ""
-	common.OptionMap["Footer"] = common.Footer
-	common.OptionMap["SystemName"] = common.SystemName
-	common.OptionMap["Logo"] = common.Logo
-	common.OptionMap["ServerAddress"] = ""
-	common.OptionMap["GitHubClientId"] = ""
-	common.OptionMap["GitHubClientSecret"] = ""
-	common.OptionMap["WeChatServerAddress"] = ""
-	common.OptionMap["WeChatServerToken"] = ""
-	common.OptionMap["WeChatAccountQRCodeImageURL"] = ""
-	common.OptionMap["TurnstileSiteKey"] = ""
-	common.OptionMap["TurnstileSecretKey"] = ""
-	common.OptionMap["QuotaForNewUser"] = strconv.Itoa(common.QuotaForNewUser)
-	common.OptionMap["QuotaForInviter"] = strconv.Itoa(common.QuotaForInviter)
-	common.OptionMap["QuotaForInvitee"] = strconv.Itoa(common.QuotaForInvitee)
-	common.OptionMap["QuotaRemindThreshold"] = strconv.Itoa(common.QuotaRemindThreshold)
-	common.OptionMap["PreConsumedQuota"] = strconv.Itoa(common.PreConsumedQuota)
-	common.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
-	common.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
-	common.OptionMap["TopUpLink"] = common.TopUpLink
-	common.OptionMap["ChatLink"] = common.ChatLink
-	common.OptionMap["QuotaPerUnit"] = strconv.FormatFloat(common.QuotaPerUnit, 'f', -1, 64)
-	common.OptionMap["RetryTimes"] = strconv.Itoa(common.RetryTimes)
-	common.OptionMap["Theme"] = common.Theme
-	common.OptionMapRWMutex.Unlock()
+	config.OptionMapRWMutex.Lock()
+	config.OptionMap = make(map[string]string)
+	config.OptionMap["PasswordLoginEnabled"] = strconv.FormatBool(config.PasswordLoginEnabled)
+	config.OptionMap["PasswordRegisterEnabled"] = strconv.FormatBool(config.PasswordRegisterEnabled)
+	config.OptionMap["EmailVerificationEnabled"] = strconv.FormatBool(config.EmailVerificationEnabled)
+	config.OptionMap["GitHubOAuthEnabled"] = strconv.FormatBool(config.GitHubOAuthEnabled)
+	config.OptionMap["WeChatAuthEnabled"] = strconv.FormatBool(config.WeChatAuthEnabled)
+	config.OptionMap["TurnstileCheckEnabled"] = strconv.FormatBool(config.TurnstileCheckEnabled)
+	config.OptionMap["RegisterEnabled"] = strconv.FormatBool(config.RegisterEnabled)
+	config.OptionMap["AutomaticDisableChannelEnabled"] = strconv.FormatBool(config.AutomaticDisableChannelEnabled)
+	config.OptionMap["AutomaticEnableChannelEnabled"] = strconv.FormatBool(config.AutomaticEnableChannelEnabled)
+	config.OptionMap["ApproximateTokenEnabled"] = strconv.FormatBool(config.ApproximateTokenEnabled)
+	config.OptionMap["LogConsumeEnabled"] = strconv.FormatBool(config.LogConsumeEnabled)
+	config.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(config.DisplayInCurrencyEnabled)
+	config.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(config.DisplayTokenStatEnabled)
+	config.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(config.ChannelDisableThreshold, 'f', -1, 64)
+	config.OptionMap["EmailDomainRestrictionEnabled"] = strconv.FormatBool(config.EmailDomainRestrictionEnabled)
+	config.OptionMap["EmailDomainWhitelist"] = strings.Join(config.EmailDomainWhitelist, ",")
+	config.OptionMap["SMTPServer"] = ""
+	config.OptionMap["SMTPFrom"] = ""
+	config.OptionMap["SMTPPort"] = strconv.Itoa(config.SMTPPort)
+	config.OptionMap["SMTPAccount"] = ""
+	config.OptionMap["SMTPToken"] = ""
+	config.OptionMap["Notice"] = ""
+	config.OptionMap["About"] = ""
+	config.OptionMap["HomePageContent"] = ""
+	config.OptionMap["Footer"] = config.Footer
+	config.OptionMap["SystemName"] = config.SystemName
+	config.OptionMap["Logo"] = config.Logo
+	config.OptionMap["ServerAddress"] = ""
+	config.OptionMap["GitHubClientId"] = ""
+	config.OptionMap["GitHubClientSecret"] = ""
+	config.OptionMap["WeChatServerAddress"] = ""
+	config.OptionMap["WeChatServerToken"] = ""
+	config.OptionMap["WeChatAccountQRCodeImageURL"] = ""
+	config.OptionMap["TurnstileSiteKey"] = ""
+	config.OptionMap["TurnstileSecretKey"] = ""
+	config.OptionMap["QuotaForNewUser"] = strconv.Itoa(config.QuotaForNewUser)
+	config.OptionMap["QuotaForInviter"] = strconv.Itoa(config.QuotaForInviter)
+	config.OptionMap["QuotaForInvitee"] = strconv.Itoa(config.QuotaForInvitee)
+	config.OptionMap["QuotaRemindThreshold"] = strconv.Itoa(config.QuotaRemindThreshold)
+	config.OptionMap["PreConsumedQuota"] = strconv.Itoa(config.PreConsumedQuota)
+	config.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
+	config.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
+	config.OptionMap["CompletionRatio"] = common.CompletionRatio2JSONString()
+	config.OptionMap["TopUpLink"] = config.TopUpLink
+	config.OptionMap["ChatLink"] = config.ChatLink
+	config.OptionMap["QuotaPerUnit"] = strconv.FormatFloat(config.QuotaPerUnit, 'f', -1, 64)
+	config.OptionMap["RetryTimes"] = strconv.Itoa(config.RetryTimes)
+	config.OptionMap["Theme"] = config.Theme
+	config.OptionMapRWMutex.Unlock()
 	loadOptionsFromDatabase()
 }

@@ -82,7 +81,7 @@ func loadOptionsFromDatabase() {
 	for _, option := range options {
 		err := updateOptionMap(option.Key, option.Value)
 		if err != nil {
-			common.SysError("failed to update option map: " + err.Error())
+			logger.SysError("failed to update option map: " + err.Error())
 		}
 	}
 }
@@ -90,7 +89,7 @@ func loadOptionsFromDatabase() {
 func SyncOptions(frequency int) {
 	for {
 		time.Sleep(time.Duration(frequency) * time.Second)
-		common.SysLog("syncing options from database")
+		logger.SysLog("syncing options from database")
 		loadOptionsFromDatabase()
 	}
 }
@@ -112,117 +111,106 @@ func UpdateOption(key string, value string) error {
 }

 func updateOptionMap(key string, value string) (err error) {
-	common.OptionMapRWMutex.Lock()
-	defer common.OptionMapRWMutex.Unlock()
-	common.OptionMap[key] = value
-	if strings.HasSuffix(key, "Permission") {
-		intValue, _ := strconv.Atoi(value)
-		switch key {
-		case "FileUploadPermission":
-			common.FileUploadPermission = intValue
-		case "FileDownloadPermission":
-			common.FileDownloadPermission = intValue
-		case "ImageUploadPermission":
-			common.ImageUploadPermission = intValue
-		case "ImageDownloadPermission":
-			common.ImageDownloadPermission = intValue
-		}
-	}
+	config.OptionMapRWMutex.Lock()
+	defer config.OptionMapRWMutex.Unlock()
+	config.OptionMap[key] = value
 	if strings.HasSuffix(key, "Enabled") {
 		boolValue := value == "true"
 		switch key {
 		case "PasswordRegisterEnabled":
-			common.PasswordRegisterEnabled = boolValue
+			config.PasswordRegisterEnabled = boolValue
 		case "PasswordLoginEnabled":
-			common.PasswordLoginEnabled = boolValue
+			config.PasswordLoginEnabled = boolValue
 		case "EmailVerificationEnabled":
-			common.EmailVerificationEnabled = boolValue
+			config.EmailVerificationEnabled = boolValue
 		case "GitHubOAuthEnabled":
-			common.GitHubOAuthEnabled = boolValue
+			config.GitHubOAuthEnabled = boolValue
 		case "WeChatAuthEnabled":
-			common.WeChatAuthEnabled = boolValue
+			config.WeChatAuthEnabled = boolValue
 		case "TurnstileCheckEnabled":
-			common.TurnstileCheckEnabled = boolValue
+			config.TurnstileCheckEnabled = boolValue
 		case "RegisterEnabled":
-			common.RegisterEnabled = boolValue
+			config.RegisterEnabled = boolValue
 		case "EmailDomainRestrictionEnabled":
-			common.EmailDomainRestrictionEnabled = boolValue
+			config.EmailDomainRestrictionEnabled = boolValue
 		case "AutomaticDisableChannelEnabled":
-			common.AutomaticDisableChannelEnabled = boolValue
+			config.AutomaticDisableChannelEnabled = boolValue
 		case "AutomaticEnableChannelEnabled":
-			common.AutomaticEnableChannelEnabled = boolValue
+			config.AutomaticEnableChannelEnabled = boolValue
 		case "ApproximateTokenEnabled":
-			common.ApproximateTokenEnabled = boolValue
+			config.ApproximateTokenEnabled = boolValue
 		case "LogConsumeEnabled":
-			common.LogConsumeEnabled = boolValue
+			config.LogConsumeEnabled = boolValue
 		case "DisplayInCurrencyEnabled":
-			common.DisplayInCurrencyEnabled = boolValue
+			config.DisplayInCurrencyEnabled = boolValue
 		case "DisplayTokenStatEnabled":
-			common.DisplayTokenStatEnabled = boolValue
+			config.DisplayTokenStatEnabled = boolValue
 		}
 	}
 	switch key {
 	case "EmailDomainWhitelist":
-		common.EmailDomainWhitelist = strings.Split(value, ",")
+		config.EmailDomainWhitelist = strings.Split(value, ",")
 	case "SMTPServer":
-		common.SMTPServer = value
+		config.SMTPServer = value
 	case "SMTPPort":
 		intValue, _ := strconv.Atoi(value)
-		common.SMTPPort = intValue
+		config.SMTPPort = intValue
 	case "SMTPAccount":
-		common.SMTPAccount = value
+		config.SMTPAccount = value
 	case "SMTPFrom":
-		common.SMTPFrom = value
+		config.SMTPFrom = value
 	case "SMTPToken":
-		common.SMTPToken = value
+		config.SMTPToken = value
 	case "ServerAddress":
-		common.ServerAddress = value
+		config.ServerAddress = value
 	case "GitHubClientId":
-		common.GitHubClientId = value
+		config.GitHubClientId = value
 	case "GitHubClientSecret":
-		common.GitHubClientSecret = value
+		config.GitHubClientSecret = value
 	case "Footer":
-		common.Footer = value
+		config.Footer = value
 	case "SystemName":
-		common.SystemName = value
+		config.SystemName = value
 	case "Logo":
-		common.Logo = value
+		config.Logo = value
 	case "WeChatServerAddress":
-		common.WeChatServerAddress = value
+		config.WeChatServerAddress = value
 	case "WeChatServerToken":
-		common.WeChatServerToken = value
+		config.WeChatServerToken = value
 	case "WeChatAccountQRCodeImageURL":
-		common.WeChatAccountQRCodeImageURL = value
+		config.WeChatAccountQRCodeImageURL = value
 	case "TurnstileSiteKey":
-		common.TurnstileSiteKey = value
+		config.TurnstileSiteKey = value
 	case "TurnstileSecretKey":
-		common.TurnstileSecretKey = value
+		config.TurnstileSecretKey = value
 	case "QuotaForNewUser":
-		common.QuotaForNewUser, _ = strconv.Atoi(value)
+		config.QuotaForNewUser, _ = strconv.Atoi(value)
 	case "QuotaForInviter":
-		common.QuotaForInviter, _ = strconv.Atoi(value)
+		config.QuotaForInviter, _ = strconv.Atoi(value)
 	case "QuotaForInvitee":
-		common.QuotaForInvitee, _ = strconv.Atoi(value)
+		config.QuotaForInvitee, _ = strconv.Atoi(value)
 	case "QuotaRemindThreshold":
-		common.QuotaRemindThreshold, _ = strconv.Atoi(value)
+		config.QuotaRemindThreshold, _ = strconv.Atoi(value)
 	case "PreConsumedQuota":
-		common.PreConsumedQuota, _ = strconv.Atoi(value)
+		config.PreConsumedQuota, _ = strconv.Atoi(value)
 	case "RetryTimes":
-		common.RetryTimes, _ = strconv.Atoi(value)
+		config.RetryTimes, _ = strconv.Atoi(value)
 	case "ModelRatio":
 		err = common.UpdateModelRatioByJSONString(value)
 	case "GroupRatio":
 		err = common.UpdateGroupRatioByJSONString(value)
+	case "CompletionRatio":
+		err = common.UpdateCompletionRatioByJSONString(value)
 	case "TopUpLink":
-		common.TopUpLink = value
+		config.TopUpLink = value
 	case "ChatLink":
-		common.ChatLink = value
+		config.ChatLink = value
 	case "ChannelDisableThreshold":
-		common.ChannelDisableThreshold, _ = strconv.ParseFloat(value, 64)
+		config.ChannelDisableThreshold, _ = strconv.ParseFloat(value, 64)
 	case "QuotaPerUnit":
-		common.QuotaPerUnit, _ = strconv.ParseFloat(value, 64)
+		config.QuotaPerUnit, _ = strconv.ParseFloat(value, 64)
 	case "Theme":
-		common.Theme = value
+		config.Theme = value
 	}
 	return err
 }
--- a/model/redemption.go
+++ b/model/redemption.go
@@ -3,8 +3,9 @@ package model
 import (
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
 	"gorm.io/gorm"
-	"one-api/common"
 )

 type Redemption struct {
@@ -67,7 +68,7 @@ func Redeem(key string, userId int) (quota int, err error) {
 		if err != nil {
 			return err
 		}
-		redemption.RedeemedTime = common.GetTimestamp()
+		redemption.RedeemedTime = helper.GetTimestamp()
 		redemption.Status = common.RedemptionCodeStatusUsed
 		err = tx.Save(redemption).Error
 		return err
--- a/model/token.go
+++ b/model/token.go
@@ -3,8 +3,11 @@ package model
 import (
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 	"gorm.io/gorm"
-	"one-api/common"
 )

 type Token struct {
@@ -39,7 +42,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 	}
 	token, err = CacheGetTokenByKey(key)
 	if err != nil {
-		common.SysError("CacheGetTokenByKey failed: " + err.Error())
+		logger.SysError("CacheGetTokenByKey failed: " + err.Error())
 		if errors.Is(err, gorm.ErrRecordNotFound) {
 			return nil, errors.New("无效的令牌")
 		}
@@ -53,12 +56,12 @@ func ValidateUserToken(key string) (token *Token, err error) {
 	if token.Status != common.TokenStatusEnabled {
 		return nil, errors.New("该令牌状态不可用")
 	}
-	if token.ExpiredTime != -1 && token.ExpiredTime < common.GetTimestamp() {
+	if token.ExpiredTime != -1 && token.ExpiredTime < helper.GetTimestamp() {
 		if !common.RedisEnabled {
 			token.Status = common.TokenStatusExpired
 			err := token.SelectUpdate()
 			if err != nil {
-				common.SysError("failed to update token status" + err.Error())
+				logger.SysError("failed to update token status" + err.Error())
 			}
 		}
 		return nil, errors.New("该令牌已过期")
@@ -69,7 +72,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 			token.Status = common.TokenStatusExhausted
 			err := token.SelectUpdate()
 			if err != nil {
-				common.SysError("failed to update token status" + err.Error())
+				logger.SysError("failed to update token status" + err.Error())
 			}
 		}
 		return nil, errors.New("该令牌额度已用尽")
@@ -138,7 +141,7 @@ func IncreaseTokenQuota(id int, quota int) (err error) {
 	if quota < 0 {
 		return errors.New("quota 不能为负数！")
 	}
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeTokenQuota, id, quota)
 		return nil
 	}
@@ -150,7 +153,7 @@ func increaseTokenQuota(id int, quota int) (err error) {
 		map[string]interface{}{
 			"remain_quota":  gorm.Expr("remain_quota + ?", quota),
 			"used_quota":    gorm.Expr("used_quota - ?", quota),
-			"accessed_time": common.GetTimestamp(),
+			"accessed_time": helper.GetTimestamp(),
 		},
 	).Error
 	return err
@@ -160,7 +163,7 @@ func DecreaseTokenQuota(id int, quota int) (err error) {
 	if quota < 0 {
 		return errors.New("quota 不能为负数！")
 	}
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeTokenQuota, id, -quota)
 		return nil
 	}
@@ -172,7 +175,7 @@ func decreaseTokenQuota(id int, quota int) (err error) {
 		map[string]interface{}{
 			"remain_quota":  gorm.Expr("remain_quota - ?", quota),
 			"used_quota":    gorm.Expr("used_quota + ?", quota),
-			"accessed_time": common.GetTimestamp(),
+			"accessed_time": helper.GetTimestamp(),
 		},
 	).Error
 	return err
@@ -196,24 +199,24 @@ func PreConsumeTokenQuota(tokenId int, quota int) (err error) {
 	if userQuota < quota {
 		return errors.New("用户额度不足")
 	}
-	quotaTooLow := userQuota >= common.QuotaRemindThreshold && userQuota-quota < common.QuotaRemindThreshold
+	quotaTooLow := userQuota >= config.QuotaRemindThreshold && userQuota-quota < config.QuotaRemindThreshold
 	noMoreQuota := userQuota-quota <= 0
 	if quotaTooLow || noMoreQuota {
 		go func() {
 			email, err := GetUserEmail(token.UserId)
 			if err != nil {
-				common.SysError("failed to fetch user email: " + err.Error())
+				logger.SysError("failed to fetch user email: " + err.Error())
 			}
 			prompt := "您的额度即将用尽"
 			if noMoreQuota {
 				prompt = "您的额度已用尽"
 			}
 			if email != "" {
-				topUpLink := fmt.Sprintf("%s/topup", common.ServerAddress)
+				topUpLink := fmt.Sprintf("%s/topup", config.ServerAddress)
 				err = common.SendEmail(prompt, email,
 					fmt.Sprintf("%s，当前剩余额度为 %d，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='%s'>%s</a>", prompt, userQuota, topUpLink, topUpLink))
 				if err != nil {
-					common.SysError("failed to send email" + err.Error())
+					logger.SysError("failed to send email" + err.Error())
 				}
 			}
 		}()
--- a/model/user.go
+++ b/model/user.go
@@ -3,8 +3,11 @@ package model
 import (
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
 	"gorm.io/gorm"
-	"one-api/common"
 	"strings"
 )

@@ -15,7 +18,7 @@ type User struct {
 	Username         string `json:"username" gorm:"unique;index" validate:"max=12"`
 	Password         string `json:"password" gorm:"not null;" validate:"min=8,max=20"`
 	DisplayName      string `json:"display_name" gorm:"index" validate:"max=20"`
-	Role             int    `json:"role" gorm:"type:int;default:1"`   // admin, common
+	Role             int    `json:"role" gorm:"type:int;default:1"`   // admin, util
 	Status           int    `json:"status" gorm:"type:int;default:1"` // enabled, disabled
 	Email            string `json:"email" gorm:"index" validate:"max=50"`
 	GitHubId         string `json:"github_id" gorm:"column:github_id;index"`
@@ -89,24 +92,24 @@ func (user *User) Insert(inviterId int) error {
 			return err
 		}
 	}
-	user.Quota = common.QuotaForNewUser
-	user.AccessToken = common.GetUUID()
-	user.AffCode = common.GetRandomString(4)
+	user.Quota = config.QuotaForNewUser
+	user.AccessToken = helper.GetUUID()
+	user.AffCode = helper.GetRandomString(4)
 	result := DB.Create(user)
 	if result.Error != nil {
 		return result.Error
 	}
-	if common.QuotaForNewUser > 0 {
-		RecordLog(user.Id, LogTypeSystem, fmt.Sprintf("新用户注册赠送 %s", common.LogQuota(common.QuotaForNewUser)))
+	if config.QuotaForNewUser > 0 {
+		RecordLog(user.Id, LogTypeSystem, fmt.Sprintf("新用户注册赠送 %s", common.LogQuota(config.QuotaForNewUser)))
 	}
 	if inviterId != 0 {
-		if common.QuotaForInvitee > 0 {
-			_ = IncreaseUserQuota(user.Id, common.QuotaForInvitee)
-			RecordLog(user.Id, LogTypeSystem, fmt.Sprintf("使用邀请码赠送 %s", common.LogQuota(common.QuotaForInvitee)))
+		if config.QuotaForInvitee > 0 {
+			_ = IncreaseUserQuota(user.Id, config.QuotaForInvitee)
+			RecordLog(user.Id, LogTypeSystem, fmt.Sprintf("使用邀请码赠送 %s", common.LogQuota(config.QuotaForInvitee)))
 		}
-		if common.QuotaForInviter > 0 {
-			_ = IncreaseUserQuota(inviterId, common.QuotaForInviter)
-			RecordLog(inviterId, LogTypeSystem, fmt.Sprintf("邀请用户赠送 %s", common.LogQuota(common.QuotaForInviter)))
+		if config.QuotaForInviter > 0 {
+			_ = IncreaseUserQuota(inviterId, config.QuotaForInviter)
+			RecordLog(inviterId, LogTypeSystem, fmt.Sprintf("邀请用户赠送 %s", common.LogQuota(config.QuotaForInviter)))
 		}
 	}
 	return nil
@@ -141,7 +144,15 @@ func (user *User) ValidateAndFill() (err error) {
 	if user.Username == "" || password == "" {
 		return errors.New("用户名或密码为空")
 	}
-	DB.Where(User{Username: user.Username}).First(user)
+	err = DB.Where("username = ?", user.Username).First(user).Error
+	if err != nil {
+		// we must make sure check username firstly
+		// consider this case: a malicious user set his username as other's email
+		err := DB.Where("email = ?", user.Username).First(user).Error
+		if err != nil {
+			return errors.New("用户名或密码错误，或用户已被封禁")
+		}
+	}
 	okay := common.ValidatePasswordAndHash(password, user.Password)
 	if !okay || user.Status != common.UserStatusEnabled {
 		return errors.New("用户名或密码错误，或用户已被封禁")
@@ -224,7 +235,7 @@ func IsAdmin(userId int) bool {
 	var user User
 	err := DB.Where("id = ?", userId).Select("role").Find(&user).Error
 	if err != nil {
-		common.SysError("no such user " + err.Error())
+		logger.SysError("no such user " + err.Error())
 		return false
 	}
 	return user.Role >= common.RoleAdminUser
@@ -283,7 +294,7 @@ func IncreaseUserQuota(id int, quota int) (err error) {
 	if quota < 0 {
 		return errors.New("quota 不能为负数！")
 	}
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeUserQuota, id, quota)
 		return nil
 	}
@@ -299,7 +310,7 @@ func DecreaseUserQuota(id int, quota int) (err error) {
 	if quota < 0 {
 		return errors.New("quota 不能为负数！")
 	}
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeUserQuota, id, -quota)
 		return nil
 	}
@@ -317,7 +328,7 @@ func GetRootUserEmail() (email string) {
 }

 func UpdateUserUsedQuotaAndRequestCount(id int, quota int) {
-	if common.BatchUpdateEnabled {
+	if config.BatchUpdateEnabled {
 		addNewRecord(BatchUpdateTypeUsedQuota, id, quota)
 		addNewRecord(BatchUpdateTypeRequestCount, id, 1)
 		return
@@ -333,7 +344,7 @@ func updateUserUsedQuotaAndRequestCount(id int, quota int, count int) {
 		},
 	).Error
 	if err != nil {
-		common.SysError("failed to update user used quota and request count: " + err.Error())
+		logger.SysError("failed to update user used quota and request count: " + err.Error())
 	}
 }

@@ -344,14 +355,14 @@ func updateUserUsedQuota(id int, quota int) {
 		},
 	).Error
 	if err != nil {
-		common.SysError("failed to update user used quota: " + err.Error())
+		logger.SysError("failed to update user used quota: " + err.Error())
 	}
 }

 func updateUserRequestCount(id int, count int) {
 	err := DB.Model(&User{}).Where("id = ?", id).Update("request_count", gorm.Expr("request_count + ?", count)).Error
 	if err != nil {
-		common.SysError("failed to update user request count: " + err.Error())
+		logger.SysError("failed to update user request count: " + err.Error())
 	}
 }

--- a/model/utils.go
+++ b/model/utils.go
@@ -1,7 +1,8 @@
 package model

 import (
-	"one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
 	"sync"
 	"time"
 )
@@ -28,7 +29,7 @@ func init() {
 func InitBatchUpdater() {
 	go func() {
 		for {
-			time.Sleep(time.Duration(common.BatchUpdateInterval) * time.Second)
+			time.Sleep(time.Duration(config.BatchUpdateInterval) * time.Second)
 			batchUpdate()
 		}
 	}()
@@ -45,7 +46,7 @@ func addNewRecord(type_ int, id int, value int) {
 }

 func batchUpdate() {
-	common.SysLog("batch update started")
+	logger.SysLog("batch update started")
 	for i := 0; i < BatchUpdateTypeCount; i++ {
 		batchUpdateLocks[i].Lock()
 		store := batchUpdateStores[i]
@@ -57,12 +58,12 @@ func batchUpdate() {
 			case BatchUpdateTypeUserQuota:
 				err := increaseUserQuota(key, value)
 				if err != nil {
-					common.SysError("failed to batch update user quota: " + err.Error())
+					logger.SysError("failed to batch update user quota: " + err.Error())
 				}
 			case BatchUpdateTypeTokenQuota:
 				err := increaseTokenQuota(key, value)
 				if err != nil {
-					common.SysError("failed to batch update token quota: " + err.Error())
+					logger.SysError("failed to batch update token quota: " + err.Error())
 				}
 			case BatchUpdateTypeUsedQuota:
 				updateUserUsedQuota(key, value)
@@ -73,5 +74,5 @@ func batchUpdate() {
 			}
 		}
 	}
-	common.SysLog("batch update finished")
+	logger.SysLog("batch update finished")
 }
--- a/relay/channel/ai360/constants.go
+++ b/relay/channel/ai360/constants.go
@@ -0,0 +1,8 @@
+package ai360
+
+var ModelList = []string{
+	"360GPT_S2_V9",
+	"embedding-bert-512-v1",
+	"embedding_s1_v1",
+	"semantic_similarity_s1_v1",
+}
--- a/relay/channel/aiproxy/adaptor.go
+++ b/relay/channel/aiproxy/adaptor.go
@@ -0,0 +1,60 @@
+package aiproxy
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	return fmt.Sprintf("%s/api/library/ask", meta.BaseURL), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("Authorization", "Bearer "+meta.APIKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	aiProxyLibraryRequest := ConvertRequest(*request)
+	aiProxyLibraryRequest.LibraryId = c.GetString(common.ConfigKeyLibraryID)
+	return aiProxyLibraryRequest, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		err, usage = StreamHandler(c, resp)
+	} else {
+		err, usage = Handler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "aiproxy"
+}
--- a/relay/channel/aiproxy/constants.go
+++ b/relay/channel/aiproxy/constants.go
@@ -0,0 +1,9 @@
+package aiproxy
+
+import "github.com/songquanpeng/one-api/relay/channel/openai"
+
+var ModelList = []string{""}
+
+func init() {
+	ModelList = openai.ModelList
+}
--- a/relay/channel/aiproxy/main.go
+++ b/relay/channel/aiproxy/main.go
@@ -1,63 +1,37 @@
-package controller
+package aiproxy

 import (
 	"bufio"
 	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
 	"strconv"
 	"strings"
 )

 // https://docs.aiproxy.io/dev/library#使用已经定制好的知识库进行对话问答

-type AIProxyLibraryRequest struct {
-	Model     string `json:"model"`
-	Query     string `json:"query"`
-	LibraryId string `json:"libraryId"`
-	Stream    bool   `json:"stream"`
-}
-
-type AIProxyLibraryError struct {
-	ErrCode int    `json:"errCode"`
-	Message string `json:"message"`
-}
-
-type AIProxyLibraryDocument struct {
-	Title string `json:"title"`
-	URL   string `json:"url"`
-}
-
-type AIProxyLibraryResponse struct {
-	Success   bool                     `json:"success"`
-	Answer    string                   `json:"answer"`
-	Documents []AIProxyLibraryDocument `json:"documents"`
-	AIProxyLibraryError
-}
-
-type AIProxyLibraryStreamResponse struct {
-	Content   string                   `json:"content"`
-	Finish    bool                     `json:"finish"`
-	Model     string                   `json:"model"`
-	Documents []AIProxyLibraryDocument `json:"documents"`
-}
-
-func requestOpenAI2AIProxyLibrary(request GeneralOpenAIRequest) *AIProxyLibraryRequest {
+func ConvertRequest(request model.GeneralOpenAIRequest) *LibraryRequest {
 	query := ""
 	if len(request.Messages) != 0 {
 		query = request.Messages[len(request.Messages)-1].StringContent()
 	}
-	return &AIProxyLibraryRequest{
+	return &LibraryRequest{
 		Model:  request.Model,
 		Stream: request.Stream,
 		Query:  query,
 	}
 }

-func aiProxyDocuments2Markdown(documents []AIProxyLibraryDocument) string {
+func aiProxyDocuments2Markdown(documents []LibraryDocument) string {
 	if len(documents) == 0 {
 		return ""
 	}
@@ -68,52 +42,52 @@ func aiProxyDocuments2Markdown(documents []AIProxyLibraryDocument) string {
 	return content
 }

-func responseAIProxyLibrary2OpenAI(response *AIProxyLibraryResponse) *OpenAITextResponse {
+func responseAIProxyLibrary2OpenAI(response *LibraryResponse) *openai.TextResponse {
 	content := response.Answer + aiProxyDocuments2Markdown(response.Documents)
-	choice := OpenAITextResponseChoice{
+	choice := openai.TextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: model.Message{
 			Role:    "assistant",
 			Content: content,
 		},
 		FinishReason: "stop",
 	}
-	fullTextResponse := OpenAITextResponse{
-		Id:      common.GetUUID(),
+	fullTextResponse := openai.TextResponse{
+		Id:      helper.GetUUID(),
 		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
+		Created: helper.GetTimestamp(),
+		Choices: []openai.TextResponseChoice{choice},
 	}
 	return &fullTextResponse
 }

-func documentsAIProxyLibrary(documents []AIProxyLibraryDocument) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func documentsAIProxyLibrary(documents []LibraryDocument) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = aiProxyDocuments2Markdown(documents)
-	choice.FinishReason = &stopFinishReason
-	return &ChatCompletionsStreamResponse{
-		Id:      common.GetUUID(),
+	choice.FinishReason = &constant.StopFinishReason
+	return &openai.ChatCompletionsStreamResponse{
+		Id:      helper.GetUUID(),
 		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
+		Created: helper.GetTimestamp(),
 		Model:   "",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []openai.ChatCompletionsStreamResponseChoice{choice},
 	}
 }

-func streamResponseAIProxyLibrary2OpenAI(response *AIProxyLibraryStreamResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseAIProxyLibrary2OpenAI(response *LibraryStreamResponse) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = response.Content
-	return &ChatCompletionsStreamResponse{
-		Id:      common.GetUUID(),
+	return &openai.ChatCompletionsStreamResponse{
+		Id:      helper.GetUUID(),
 		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
+		Created: helper.GetTimestamp(),
 		Model:   response.Model,
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []openai.ChatCompletionsStreamResponseChoice{choice},
 	}
 }

-func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var usage model.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -143,15 +117,15 @@ func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIEr
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
-	var documents []AIProxyLibraryDocument
+	common.SetEventStreamHeaders(c)
+	var documents []LibraryDocument
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
-			var AIProxyLibraryResponse AIProxyLibraryStreamResponse
+			var AIProxyLibraryResponse LibraryStreamResponse
 			err := json.Unmarshal([]byte(data), &AIProxyLibraryResponse)
 			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
+				logger.SysError("error unmarshalling stream response: " + err.Error())
 				return true
 			}
 			if len(AIProxyLibraryResponse.Documents) != 0 {
@@ -160,7 +134,7 @@ func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIEr
 			response := streamResponseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
@@ -169,7 +143,7 @@ func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIEr
 			response := documentsAIProxyLibrary(documents)
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
@@ -179,28 +153,28 @@ func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIEr
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, &usage
 }

-func aiProxyLibraryHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var AIProxyLibraryResponse AIProxyLibraryResponse
+func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var AIProxyLibraryResponse LibraryResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &AIProxyLibraryResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if AIProxyLibraryResponse.ErrCode != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: AIProxyLibraryResponse.Message,
 				Type:    strconv.Itoa(AIProxyLibraryResponse.ErrCode),
 				Code:    AIProxyLibraryResponse.ErrCode,
@@ -211,10 +185,13 @@ func aiProxyLibraryHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWit
 	fullTextResponse := responseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
 	_, err = c.Writer.Write(jsonResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "write_response_body_failed", http.StatusInternalServerError), nil
+	}
 	return nil, &fullTextResponse.Usage
 }
--- a/relay/channel/aiproxy/model.go
+++ b/relay/channel/aiproxy/model.go
@@ -0,0 +1,32 @@
+package aiproxy
+
+type LibraryRequest struct {
+	Model     string `json:"model"`
+	Query     string `json:"query"`
+	LibraryId string `json:"libraryId"`
+	Stream    bool   `json:"stream"`
+}
+
+type LibraryError struct {
+	ErrCode int    `json:"errCode"`
+	Message string `json:"message"`
+}
+
+type LibraryDocument struct {
+	Title string `json:"title"`
+	URL   string `json:"url"`
+}
+
+type LibraryResponse struct {
+	Success   bool              `json:"success"`
+	Answer    string            `json:"answer"`
+	Documents []LibraryDocument `json:"documents"`
+	LibraryError
+}
+
+type LibraryStreamResponse struct {
+	Content   string            `json:"content"`
+	Finish    bool              `json:"finish"`
+	Model     string            `json:"model"`
+	Documents []LibraryDocument `json:"documents"`
+}
--- a/relay/channel/ali/adaptor.go
+++ b/relay/channel/ali/adaptor.go
@@ -0,0 +1,83 @@
+package ali
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+// https://help.aliyun.com/zh/dashscope/developer-reference/api-details
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	fullRequestURL := fmt.Sprintf("%s/api/v1/services/aigc/text-generation/generation", meta.BaseURL)
+	if meta.Mode == constant.RelayModeEmbeddings {
+		fullRequestURL = fmt.Sprintf("%s/api/v1/services/embeddings/text-embedding/text-embedding", meta.BaseURL)
+	}
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("Authorization", "Bearer "+meta.APIKey)
+	if meta.IsStream {
+		req.Header.Set("X-DashScope-SSE", "enable")
+	}
+	if c.GetString(common.ConfigKeyPlugin) != "" {
+		req.Header.Set("X-DashScope-Plugin", c.GetString(common.ConfigKeyPlugin))
+	}
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch relayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := ConvertEmbeddingRequest(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		baiduRequest := ConvertRequest(*request)
+		return baiduRequest, nil
+	}
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		err, usage = StreamHandler(c, resp)
+	} else {
+		switch meta.Mode {
+		case constant.RelayModeEmbeddings:
+			err, usage = EmbeddingHandler(c, resp)
+		default:
+			err, usage = Handler(c, resp)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "ali"
+}
--- a/relay/channel/ali/constants.go
+++ b/relay/channel/ali/constants.go
@@ -0,0 +1,6 @@
+package ali
+
+var ModelList = []string{
+	"qwen-turbo", "qwen-plus", "qwen-max", "qwen-max-longcontext",
+	"text-embedding-v1",
+}
--- a/relay/channel/ali/main.go
+++ b/relay/channel/ali/main.go
@@ -1,118 +1,53 @@
-package controller
+package ali

 import (
 	"bufio"
 	"encoding/json"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
 	"strings"
 )

 // https://help.aliyun.com/document_detail/613695.html?spm=a2c4g.2399480.0.0.1adb778fAdzP9w#341800c0f8w0r

-type AliMessage struct {
-	Content string `json:"content"`
-	Role    string `json:"role"`
-}
+const EnableSearchModelSuffix = "-internet"

-type AliInput struct {
-	//Prompt   string       `json:"prompt"`
-	Messages []AliMessage `json:"messages"`
-}
-
-type AliParameters struct {
-	TopP              float64 `json:"top_p,omitempty"`
-	TopK              int     `json:"top_k,omitempty"`
-	Seed              uint64  `json:"seed,omitempty"`
-	EnableSearch      bool    `json:"enable_search,omitempty"`
-	IncrementalOutput bool    `json:"incremental_output,omitempty"`
-}
-
-type AliChatRequest struct {
-	Model      string        `json:"model"`
-	Input      AliInput      `json:"input"`
-	Parameters AliParameters `json:"parameters,omitempty"`
-}
-
-type AliEmbeddingRequest struct {
-	Model string `json:"model"`
-	Input struct {
-		Texts []string `json:"texts"`
-	} `json:"input"`
-	Parameters *struct {
-		TextType string `json:"text_type,omitempty"`
-	} `json:"parameters,omitempty"`
-}
-
-type AliEmbedding struct {
-	Embedding []float64 `json:"embedding"`
-	TextIndex int       `json:"text_index"`
-}
-
-type AliEmbeddingResponse struct {
-	Output struct {
-		Embeddings []AliEmbedding `json:"embeddings"`
-	} `json:"output"`
-	Usage AliUsage `json:"usage"`
-	AliError
-}
-
-type AliError struct {
-	Code      string `json:"code"`
-	Message   string `json:"message"`
-	RequestId string `json:"request_id"`
-}
-
-type AliUsage struct {
-	InputTokens  int `json:"input_tokens"`
-	OutputTokens int `json:"output_tokens"`
-	TotalTokens  int `json:"total_tokens"`
-}
-
-type AliOutput struct {
-	Text         string `json:"text"`
-	FinishReason string `json:"finish_reason"`
-}
-
-type AliChatResponse struct {
-	Output AliOutput `json:"output"`
-	Usage  AliUsage  `json:"usage"`
-	AliError
-}
-
-const AliEnableSearchModelSuffix = "-internet"
-
-func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
-	messages := make([]AliMessage, 0, len(request.Messages))
+func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
+	messages := make([]Message, 0, len(request.Messages))
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
-		messages = append(messages, AliMessage{
+		messages = append(messages, Message{
 			Content: message.StringContent(),
 			Role:    strings.ToLower(message.Role),
 		})
 	}
 	enableSearch := false
 	aliModel := request.Model
-	if strings.HasSuffix(aliModel, AliEnableSearchModelSuffix) {
+	if strings.HasSuffix(aliModel, EnableSearchModelSuffix) {
 		enableSearch = true
-		aliModel = strings.TrimSuffix(aliModel, AliEnableSearchModelSuffix)
+		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
 	}
-	return &AliChatRequest{
+	return &ChatRequest{
 		Model: aliModel,
-		Input: AliInput{
+		Input: Input{
 			Messages: messages,
 		},
-		Parameters: AliParameters{
+		Parameters: Parameters{
 			EnableSearch:      enableSearch,
 			IncrementalOutput: request.Stream,
+			Seed:              uint64(request.Seed),
 		},
 	}
 }

-func embeddingRequestOpenAI2Ali(request GeneralOpenAIRequest) *AliEmbeddingRequest {
-	return &AliEmbeddingRequest{
+func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *EmbeddingRequest {
+	return &EmbeddingRequest{
 		Model: "text-embedding-v1",
 		Input: struct {
 			Texts []string `json:"texts"`
@@ -122,21 +57,21 @@ func embeddingRequestOpenAI2Ali(request GeneralOpenAIRequest) *AliEmbeddingReque
 	}
 }

-func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var aliResponse AliEmbeddingResponse
+func EmbeddingHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var aliResponse EmbeddingResponse
 	err := json.NewDecoder(resp.Body).Decode(&aliResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}

 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}

 	if aliResponse.Code != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: aliResponse.Message,
 				Type:    aliResponse.Code,
 				Param:   aliResponse.RequestId,
@@ -149,7 +84,7 @@ func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 	fullTextResponse := embeddingResponseAli2OpenAI(&aliResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -157,16 +92,16 @@ func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 	return nil, &fullTextResponse.Usage
 }

-func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *OpenAIEmbeddingResponse {
-	openAIEmbeddingResponse := OpenAIEmbeddingResponse{
+func embeddingResponseAli2OpenAI(response *EmbeddingResponse) *openai.EmbeddingResponse {
+	openAIEmbeddingResponse := openai.EmbeddingResponse{
 		Object: "list",
-		Data:   make([]OpenAIEmbeddingResponseItem, 0, len(response.Output.Embeddings)),
+		Data:   make([]openai.EmbeddingResponseItem, 0, len(response.Output.Embeddings)),
 		Model:  "text-embedding-v1",
-		Usage:  Usage{TotalTokens: response.Usage.TotalTokens},
+		Usage:  model.Usage{TotalTokens: response.Usage.TotalTokens},
 	}

 	for _, item := range response.Output.Embeddings {
-		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
 			Object:    `embedding`,
 			Index:     item.TextIndex,
 			Embedding: item.Embedding,
@@ -175,21 +110,21 @@ func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *OpenAIEmbeddin
 	return &openAIEmbeddingResponse
 }

-func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
-	choice := OpenAITextResponseChoice{
+func responseAli2OpenAI(response *ChatResponse) *openai.TextResponse {
+	choice := openai.TextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: model.Message{
 			Role:    "assistant",
 			Content: response.Output.Text,
 		},
 		FinishReason: response.Output.FinishReason,
 	}
-	fullTextResponse := OpenAITextResponse{
+	fullTextResponse := openai.TextResponse{
 		Id:      response.RequestId,
 		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
-		Usage: Usage{
+		Created: helper.GetTimestamp(),
+		Choices: []openai.TextResponseChoice{choice},
+		Usage: model.Usage{
 			PromptTokens:     response.Usage.InputTokens,
 			CompletionTokens: response.Usage.OutputTokens,
 			TotalTokens:      response.Usage.InputTokens + response.Usage.OutputTokens,
@@ -198,25 +133,25 @@ func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

-func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseAli2OpenAI(aliResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = aliResponse.Output.Text
 	if aliResponse.Output.FinishReason != "null" {
 		finishReason := aliResponse.Output.FinishReason
 		choice.FinishReason = &finishReason
 	}
-	response := ChatCompletionsStreamResponse{
+	response := openai.ChatCompletionsStreamResponse{
 		Id:      aliResponse.RequestId,
 		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
+		Created: helper.GetTimestamp(),
 		Model:   "qwen",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []openai.ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response
 }

-func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var usage model.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -246,15 +181,15 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	//lastResponseText := ""
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
-			var aliResponse AliChatResponse
+			var aliResponse ChatResponse
 			err := json.Unmarshal([]byte(data), &aliResponse)
 			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
+				logger.SysError("error unmarshalling stream response: " + err.Error())
 				return true
 			}
 			if aliResponse.Usage.OutputTokens != 0 {
@@ -267,7 +202,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 			//lastResponseText = aliResponse.Output.Text
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
@@ -279,28 +214,28 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, &usage
 }

-func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var aliResponse AliChatResponse
+func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var aliResponse ChatResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &aliResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if aliResponse.Code != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: aliResponse.Message,
 				Type:    aliResponse.Code,
 				Param:   aliResponse.RequestId,
@@ -313,7 +248,7 @@ func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode
 	fullTextResponse.Model = "qwen"
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/ali/model.go
+++ b/relay/channel/ali/model.go
@@ -0,0 +1,71 @@
+package ali
+
+type Message struct {
+	Content string `json:"content"`
+	Role    string `json:"role"`
+}
+
+type Input struct {
+	//Prompt   string       `json:"prompt"`
+	Messages []Message `json:"messages"`
+}
+
+type Parameters struct {
+	TopP              float64 `json:"top_p,omitempty"`
+	TopK              int     `json:"top_k,omitempty"`
+	Seed              uint64  `json:"seed,omitempty"`
+	EnableSearch      bool    `json:"enable_search,omitempty"`
+	IncrementalOutput bool    `json:"incremental_output,omitempty"`
+}
+
+type ChatRequest struct {
+	Model      string     `json:"model"`
+	Input      Input      `json:"input"`
+	Parameters Parameters `json:"parameters,omitempty"`
+}
+
+type EmbeddingRequest struct {
+	Model string `json:"model"`
+	Input struct {
+		Texts []string `json:"texts"`
+	} `json:"input"`
+	Parameters *struct {
+		TextType string `json:"text_type,omitempty"`
+	} `json:"parameters,omitempty"`
+}
+
+type Embedding struct {
+	Embedding []float64 `json:"embedding"`
+	TextIndex int       `json:"text_index"`
+}
+
+type EmbeddingResponse struct {
+	Output struct {
+		Embeddings []Embedding `json:"embeddings"`
+	} `json:"output"`
+	Usage Usage `json:"usage"`
+	Error
+}
+
+type Error struct {
+	Code      string `json:"code"`
+	Message   string `json:"message"`
+	RequestId string `json:"request_id"`
+}
+
+type Usage struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+	TotalTokens  int `json:"total_tokens"`
+}
+
+type Output struct {
+	Text         string `json:"text"`
+	FinishReason string `json:"finish_reason"`
+}
+
+type ChatResponse struct {
+	Output Output `json:"output"`
+	Usage  Usage  `json:"usage"`
+	Error
+}
--- a/relay/channel/anthropic/adaptor.go
+++ b/relay/channel/anthropic/adaptor.go
@@ -0,0 +1,65 @@
+package anthropic
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	return fmt.Sprintf("%s/v1/complete", meta.BaseURL), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("x-api-key", meta.APIKey)
+	anthropicVersion := c.Request.Header.Get("anthropic-version")
+	if anthropicVersion == "" {
+		anthropicVersion = "2023-06-01"
+	}
+	req.Header.Set("anthropic-version", anthropicVersion)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return ConvertRequest(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = StreamHandler(c, resp)
+		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "authropic"
+}
--- a/relay/channel/anthropic/constants.go
+++ b/relay/channel/anthropic/constants.go
@@ -0,0 +1,5 @@
+package anthropic
+
+var ModelList = []string{
+	"claude-instant-1", "claude-2", "claude-2.0", "claude-2.1",
+}
--- a/relay/channel/anthropic/main.go
+++ b/relay/channel/anthropic/main.go
@@ -1,44 +1,20 @@
-package controller
+package anthropic

 import (
 	"bufio"
 	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
 	"strings"
 )

-type ClaudeMetadata struct {
-	UserId string `json:"user_id"`
-}
-
-type ClaudeRequest struct {
-	Model             string   `json:"model"`
-	Prompt            string   `json:"prompt"`
-	MaxTokensToSample int      `json:"max_tokens_to_sample"`
-	StopSequences     []string `json:"stop_sequences,omitempty"`
-	Temperature       float64  `json:"temperature,omitempty"`
-	TopP              float64  `json:"top_p,omitempty"`
-	TopK              int      `json:"top_k,omitempty"`
-	//ClaudeMetadata    `json:"metadata,omitempty"`
-	Stream bool `json:"stream,omitempty"`
-}
-
-type ClaudeError struct {
-	Type    string `json:"type"`
-	Message string `json:"message"`
-}
-
-type ClaudeResponse struct {
-	Completion string      `json:"completion"`
-	StopReason string      `json:"stop_reason"`
-	Model      string      `json:"model"`
-	Error      ClaudeError `json:"error"`
-}
-
 func stopReasonClaude2OpenAI(reason string) string {
 	switch reason {
 	case "stop_sequence":
@@ -50,8 +26,8 @@ func stopReasonClaude2OpenAI(reason string) string {
 	}
 }

-func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
-	claudeRequest := ClaudeRequest{
+func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
+	claudeRequest := Request{
 		Model:             textRequest.Model,
 		Prompt:            "",
 		MaxTokensToSample: textRequest.MaxTokens,
@@ -80,43 +56,43 @@ func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
 	return &claudeRequest
 }

-func streamResponseClaude2OpenAI(claudeResponse *ClaudeResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseClaude2OpenAI(claudeResponse *Response) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = claudeResponse.Completion
 	finishReason := stopReasonClaude2OpenAI(claudeResponse.StopReason)
 	if finishReason != "null" {
 		choice.FinishReason = &finishReason
 	}
-	var response ChatCompletionsStreamResponse
+	var response openai.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = claudeResponse.Model
-	response.Choices = []ChatCompletionsStreamResponseChoice{choice}
+	response.Choices = []openai.ChatCompletionsStreamResponseChoice{choice}
 	return &response
 }

-func responseClaude2OpenAI(claudeResponse *ClaudeResponse) *OpenAITextResponse {
-	choice := OpenAITextResponseChoice{
+func responseClaude2OpenAI(claudeResponse *Response) *openai.TextResponse {
+	choice := openai.TextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: model.Message{
 			Role:    "assistant",
 			Content: strings.TrimPrefix(claudeResponse.Completion, " "),
 			Name:    nil,
 		},
 		FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
 	}
-	fullTextResponse := OpenAITextResponse{
-		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+	fullTextResponse := openai.TextResponse{
+		Id:      fmt.Sprintf("chatcmpl-%s", helper.GetUUID()),
 		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
+		Created: helper.GetTimestamp(),
+		Choices: []openai.TextResponseChoice{choice},
 	}
 	return &fullTextResponse
 }

-func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
 	responseText := ""
-	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
-	createdTime := common.GetTimestamp()
+	responseId := fmt.Sprintf("chatcmpl-%s", helper.GetUUID())
+	createdTime := helper.GetTimestamp()
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -143,16 +119,16 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
 			// some implementations may add \r at the end of data
 			data = strings.TrimSuffix(data, "\r")
-			var claudeResponse ClaudeResponse
+			var claudeResponse Response
 			err := json.Unmarshal([]byte(data), &claudeResponse)
 			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
+				logger.SysError("error unmarshalling stream response: " + err.Error())
 				return true
 			}
 			responseText += claudeResponse.Completion
@@ -161,7 +137,7 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 			response.Created = createdTime
 			jsonStr, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
@@ -173,28 +149,28 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	return nil, responseText
 }

-func claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName string) (*model.ErrorWithStatusCode, *model.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	var claudeResponse ClaudeResponse
+	var claudeResponse Response
 	err = json.Unmarshal(responseBody, &claudeResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if claudeResponse.Error.Type != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: claudeResponse.Error.Message,
 				Type:    claudeResponse.Error.Type,
 				Param:   "",
@@ -204,9 +180,9 @@ func claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 		}, nil
 	}
 	fullTextResponse := responseClaude2OpenAI(&claudeResponse)
-	fullTextResponse.Model = model
-	completionTokens := countTokenText(claudeResponse.Completion, model)
-	usage := Usage{
+	fullTextResponse.Model = modelName
+	completionTokens := openai.CountTokenText(claudeResponse.Completion, modelName)
+	usage := model.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -214,7 +190,7 @@ func claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	fullTextResponse.Usage = usage
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/anthropic/model.go
+++ b/relay/channel/anthropic/model.go
@@ -0,0 +1,29 @@
+package anthropic
+
+type Metadata struct {
+	UserId string `json:"user_id"`
+}
+
+type Request struct {
+	Model             string   `json:"model"`
+	Prompt            string   `json:"prompt"`
+	MaxTokensToSample int      `json:"max_tokens_to_sample"`
+	StopSequences     []string `json:"stop_sequences,omitempty"`
+	Temperature       float64  `json:"temperature,omitempty"`
+	TopP              float64  `json:"top_p,omitempty"`
+	TopK              int      `json:"top_k,omitempty"`
+	//Metadata    `json:"metadata,omitempty"`
+	Stream bool `json:"stream,omitempty"`
+}
+
+type Error struct {
+	Type    string `json:"type"`
+	Message string `json:"message"`
+}
+
+type Response struct {
+	Completion string `json:"completion"`
+	StopReason string `json:"stop_reason"`
+	Model      string `json:"model"`
+	Error      Error  `json:"error"`
+}
--- a/relay/channel/baidu/adaptor.go
+++ b/relay/channel/baidu/adaptor.go
@@ -0,0 +1,93 @@
+package baidu
+
+import (
+	"errors"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	var fullRequestURL string
+	switch meta.ActualModelName {
+	case "ERNIE-Bot-4":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
+	case "ERNIE-Bot-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_bot_8k"
+	case "ERNIE-Bot":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
+	case "ERNIE-Speed":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
+	case "ERNIE-Bot-turbo":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
+	case "BLOOMZ-7B":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
+	case "Embedding-V1":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
+	}
+	var accessToken string
+	var err error
+	if accessToken, err = GetAccessToken(meta.APIKey); err != nil {
+		return "", err
+	}
+	fullRequestURL += "?access_token=" + accessToken
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("Authorization", "Bearer "+meta.APIKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch relayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := ConvertEmbeddingRequest(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		baiduRequest := ConvertRequest(*request)
+		return baiduRequest, nil
+	}
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		err, usage = StreamHandler(c, resp)
+	} else {
+		switch meta.Mode {
+		case constant.RelayModeEmbeddings:
+			err, usage = EmbeddingHandler(c, resp)
+		default:
+			err, usage = Handler(c, resp)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "baidu"
+}
--- a/relay/channel/baidu/constants.go
+++ b/relay/channel/baidu/constants.go
@@ -0,0 +1,10 @@
+package baidu
+
+var ModelList = []string{
+	"ERNIE-Bot-4",
+	"ERNIE-Bot-8K",
+	"ERNIE-Bot",
+	"ERNIE-Speed",
+	"ERNIE-Bot-turbo",
+	"Embedding-V1",
+}
--- a/relay/channel/baidu/main.go
+++ b/relay/channel/baidu/main.go
@@ -1,4 +1,4 @@
-package controller
+package baidu

 import (
 	"bufio"
@@ -6,9 +6,14 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
 	"io"
 	"net/http"
-	"one-api/common"
 	"strings"
 	"sync"
 	"time"
@@ -16,148 +21,104 @@ import (

 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/flfmc9do2

-type BaiduTokenResponse struct {
+type TokenResponse struct {
 	ExpiresIn   int    `json:"expires_in"`
 	AccessToken string `json:"access_token"`
 }

-type BaiduMessage struct {
+type Message struct {
 	Role    string `json:"role"`
 	Content string `json:"content"`
 }

-type BaiduChatRequest struct {
-	Messages []BaiduMessage `json:"messages"`
-	Stream   bool           `json:"stream"`
-	UserId   string         `json:"user_id,omitempty"`
+type ChatRequest struct {
+	Messages []Message `json:"messages"`
+	Stream   bool      `json:"stream"`
+	UserId   string    `json:"user_id,omitempty"`
 }

-type BaiduError struct {
+type Error struct {
 	ErrorCode int    `json:"error_code"`
 	ErrorMsg  string `json:"error_msg"`
 }

-type BaiduChatResponse struct {
-	Id               string `json:"id"`
-	Object           string `json:"object"`
-	Created          int64  `json:"created"`
-	Result           string `json:"result"`
-	IsTruncated      bool   `json:"is_truncated"`
-	NeedClearHistory bool   `json:"need_clear_history"`
-	Usage            Usage  `json:"usage"`
-	BaiduError
-}
-
-type BaiduChatStreamResponse struct {
-	BaiduChatResponse
-	SentenceId int  `json:"sentence_id"`
-	IsEnd      bool `json:"is_end"`
-}
-
-type BaiduEmbeddingRequest struct {
-	Input []string `json:"input"`
-}
-
-type BaiduEmbeddingData struct {
-	Object    string    `json:"object"`
-	Embedding []float64 `json:"embedding"`
-	Index     int       `json:"index"`
-}
-
-type BaiduEmbeddingResponse struct {
-	Id      string               `json:"id"`
-	Object  string               `json:"object"`
-	Created int64                `json:"created"`
-	Data    []BaiduEmbeddingData `json:"data"`
-	Usage   Usage                `json:"usage"`
-	BaiduError
-}
-
-type BaiduAccessToken struct {
-	AccessToken      string    `json:"access_token"`
-	Error            string    `json:"error,omitempty"`
-	ErrorDescription string    `json:"error_description,omitempty"`
-	ExpiresIn        int64     `json:"expires_in,omitempty"`
-	ExpiresAt        time.Time `json:"-"`
-}
-
 var baiduTokenStore sync.Map

-func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
-	messages := make([]BaiduMessage, 0, len(request.Messages))
+func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
+	messages := make([]Message, 0, len(request.Messages))
 	for _, message := range request.Messages {
 		if message.Role == "system" {
-			messages = append(messages, BaiduMessage{
+			messages = append(messages, Message{
 				Role:    "user",
 				Content: message.StringContent(),
 			})
-			messages = append(messages, BaiduMessage{
+			messages = append(messages, Message{
 				Role:    "assistant",
 				Content: "Okay",
 			})
 		} else {
-			messages = append(messages, BaiduMessage{
+			messages = append(messages, Message{
 				Role:    message.Role,
 				Content: message.StringContent(),
 			})
 		}
 	}
-	return &BaiduChatRequest{
+	return &ChatRequest{
 		Messages: messages,
 		Stream:   request.Stream,
 	}
 }

-func responseBaidu2OpenAI(response *BaiduChatResponse) *OpenAITextResponse {
-	choice := OpenAITextResponseChoice{
+func responseBaidu2OpenAI(response *ChatResponse) *openai.TextResponse {
+	choice := openai.TextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: model.Message{
 			Role:    "assistant",
 			Content: response.Result,
 		},
 		FinishReason: "stop",
 	}
-	fullTextResponse := OpenAITextResponse{
+	fullTextResponse := openai.TextResponse{
 		Id:      response.Id,
 		Object:  "chat.completion",
 		Created: response.Created,
-		Choices: []OpenAITextResponseChoice{choice},
+		Choices: []openai.TextResponseChoice{choice},
 		Usage:   response.Usage,
 	}
 	return &fullTextResponse
 }

-func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseBaidu2OpenAI(baiduResponse *ChatStreamResponse) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = baiduResponse.Result
 	if baiduResponse.IsEnd {
-		choice.FinishReason = &stopFinishReason
+		choice.FinishReason = &constant.StopFinishReason
 	}
-	response := ChatCompletionsStreamResponse{
+	response := openai.ChatCompletionsStreamResponse{
 		Id:      baiduResponse.Id,
 		Object:  "chat.completion.chunk",
 		Created: baiduResponse.Created,
 		Model:   "ernie-bot",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []openai.ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response
 }

-func embeddingRequestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduEmbeddingRequest {
-	return &BaiduEmbeddingRequest{
+func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *EmbeddingRequest {
+	return &EmbeddingRequest{
 		Input: request.ParseInput(),
 	}
 }

-func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbeddingResponse {
-	openAIEmbeddingResponse := OpenAIEmbeddingResponse{
+func embeddingResponseBaidu2OpenAI(response *EmbeddingResponse) *openai.EmbeddingResponse {
+	openAIEmbeddingResponse := openai.EmbeddingResponse{
 		Object: "list",
-		Data:   make([]OpenAIEmbeddingResponseItem, 0, len(response.Data)),
+		Data:   make([]openai.EmbeddingResponseItem, 0, len(response.Data)),
 		Model:  "baidu-embedding",
 		Usage:  response.Usage,
 	}
 	for _, item := range response.Data {
-		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
 			Object:    item.Object,
 			Index:     item.Index,
 			Embedding: item.Embedding,
@@ -166,8 +127,8 @@ func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbe
 	return &openAIEmbeddingResponse
 }

-func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var usage model.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -194,14 +155,14 @@ func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
-			var baiduResponse BaiduChatStreamResponse
+			var baiduResponse ChatStreamResponse
 			err := json.Unmarshal([]byte(data), &baiduResponse)
 			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
+				logger.SysError("error unmarshalling stream response: " + err.Error())
 				return true
 			}
 			if baiduResponse.Usage.TotalTokens != 0 {
@@ -212,7 +173,7 @@ func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
 			response := streamResponseBaidu2OpenAI(&baiduResponse)
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
@@ -224,28 +185,28 @@ func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, &usage
 }

-func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var baiduResponse BaiduChatResponse
+func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var baiduResponse ChatResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &baiduResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: baiduResponse.ErrorMsg,
 				Type:    "baidu_error",
 				Param:   "",
@@ -258,7 +219,7 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	fullTextResponse.Model = "ernie-bot"
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -266,23 +227,23 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	return nil, &fullTextResponse.Usage
 }

-func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var baiduResponse BaiduEmbeddingResponse
+func EmbeddingHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var baiduResponse EmbeddingResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &baiduResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: baiduResponse.ErrorMsg,
 				Type:    "baidu_error",
 				Param:   "",
@@ -294,7 +255,7 @@ func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWit
 	fullTextResponse := embeddingResponseBaidu2OpenAI(&baiduResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -302,10 +263,10 @@ func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWit
 	return nil, &fullTextResponse.Usage
 }

-func getBaiduAccessToken(apiKey string) (string, error) {
+func GetAccessToken(apiKey string) (string, error) {
 	if val, ok := baiduTokenStore.Load(apiKey); ok {
-		var accessToken BaiduAccessToken
-		if accessToken, ok = val.(BaiduAccessToken); ok {
+		var accessToken AccessToken
+		if accessToken, ok = val.(AccessToken); ok {
 			// soon this will expire
 			if time.Now().Add(time.Hour).After(accessToken.ExpiresAt) {
 				go func() {
@@ -320,12 +281,12 @@ func getBaiduAccessToken(apiKey string) (string, error) {
 		return "", err
 	}
 	if accessToken == nil {
-		return "", errors.New("getBaiduAccessToken return a nil token")
+		return "", errors.New("GetAccessToken return a nil token")
 	}
 	return (*accessToken).AccessToken, nil
 }

-func getBaiduAccessTokenHelper(apiKey string) (*BaiduAccessToken, error) {
+func getBaiduAccessTokenHelper(apiKey string) (*AccessToken, error) {
 	parts := strings.Split(apiKey, "|")
 	if len(parts) != 2 {
 		return nil, errors.New("invalid baidu apikey")
@@ -337,13 +298,13 @@ func getBaiduAccessTokenHelper(apiKey string) (*BaiduAccessToken, error) {
 	}
 	req.Header.Add("Content-Type", "application/json")
 	req.Header.Add("Accept", "application/json")
-	res, err := impatientHTTPClient.Do(req)
+	res, err := util.ImpatientHTTPClient.Do(req)
 	if err != nil {
 		return nil, err
 	}
 	defer res.Body.Close()

-	var accessToken BaiduAccessToken
+	var accessToken AccessToken
 	err = json.NewDecoder(res.Body).Decode(&accessToken)
 	if err != nil {
 		return nil, err
--- a/relay/channel/baidu/model.go
+++ b/relay/channel/baidu/model.go
@@ -0,0 +1,50 @@
+package baidu
+
+import (
+	"github.com/songquanpeng/one-api/relay/model"
+	"time"
+)
+
+type ChatResponse struct {
+	Id               string      `json:"id"`
+	Object           string      `json:"object"`
+	Created          int64       `json:"created"`
+	Result           string      `json:"result"`
+	IsTruncated      bool        `json:"is_truncated"`
+	NeedClearHistory bool        `json:"need_clear_history"`
+	Usage            model.Usage `json:"usage"`
+	Error
+}
+
+type ChatStreamResponse struct {
+	ChatResponse
+	SentenceId int  `json:"sentence_id"`
+	IsEnd      bool `json:"is_end"`
+}
+
+type EmbeddingRequest struct {
+	Input []string `json:"input"`
+}
+
+type EmbeddingData struct {
+	Object    string    `json:"object"`
+	Embedding []float64 `json:"embedding"`
+	Index     int       `json:"index"`
+}
+
+type EmbeddingResponse struct {
+	Id      string          `json:"id"`
+	Object  string          `json:"object"`
+	Created int64           `json:"created"`
+	Data    []EmbeddingData `json:"data"`
+	Usage   model.Usage     `json:"usage"`
+	Error
+}
+
+type AccessToken struct {
+	AccessToken      string    `json:"access_token"`
+	Error            string    `json:"error,omitempty"`
+	ErrorDescription string    `json:"error_description,omitempty"`
+	ExpiresIn        int64     `json:"expires_in,omitempty"`
+	ExpiresAt        time.Time `json:"-"`
+}
--- a/relay/channel/common.go
+++ b/relay/channel/common.go
@@ -0,0 +1,51 @@
+package channel
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+func SetupCommonRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) {
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+	if meta.IsStream && c.Request.Header.Get("Accept") == "" {
+		req.Header.Set("Accept", "text/event-stream")
+	}
+}
+
+func DoRequestHelper(a Adaptor, c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.GetRequestURL(meta)
+	if err != nil {
+		return nil, fmt.Errorf("get request url failed: %w", err)
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	err = a.SetupRequestHeader(c, req, meta)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := DoRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, nil
+}
+
+func DoRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
+	resp, err := util.HTTPClient.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	if resp == nil {
+		return nil, errors.New("resp is nil")
+	}
+	_ = req.Body.Close()
+	_ = c.Request.Body.Close()
+	return resp, nil
+}
--- a/relay/channel/gemini/adaptor.go
+++ b/relay/channel/gemini/adaptor.go
@@ -0,0 +1,66 @@
+package gemini
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/helper"
+	channelhelper "github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	version := helper.AssignOrDefault(meta.APIVersion, "v1")
+	action := "generateContent"
+	if meta.IsStream {
+		action = "streamGenerateContent"
+	}
+	return fmt.Sprintf("%s/%s/models/%s:%s", meta.BaseURL, version, meta.ActualModelName, action), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channelhelper.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("x-goog-api-key", meta.APIKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return ConvertRequest(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channelhelper.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = StreamHandler(c, resp)
+		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "google gemini"
+}
--- a/relay/channel/gemini/constants.go
+++ b/relay/channel/gemini/constants.go
@@ -0,0 +1,6 @@
+package gemini
+
+var ModelList = []string{
+	"gemini-pro",
+	"gemini-pro-vision",
+}
--- a/relay/channel/gemini/main.go
+++ b/relay/channel/gemini/main.go
@@ -1,13 +1,19 @@
-package controller
+package gemini

 import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/image"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/common/image"
 	"strings"

 	"github.com/gin-gonic/gin"
@@ -16,79 +22,39 @@ import (
 // https://ai.google.dev/docs/gemini_api_overview?hl=zh-cn

 const (
-	GeminiVisionMaxImageNum = 16
+	VisionMaxImageNum = 16
 )

-type GeminiChatRequest struct {
-	Contents         []GeminiChatContent        `json:"contents"`
-	SafetySettings   []GeminiChatSafetySettings `json:"safety_settings,omitempty"`
-	GenerationConfig GeminiChatGenerationConfig `json:"generation_config,omitempty"`
-	Tools            []GeminiChatTools          `json:"tools,omitempty"`
-}
-
-type GeminiInlineData struct {
-	MimeType string `json:"mimeType"`
-	Data     string `json:"data"`
-}
-
-type GeminiPart struct {
-	Text       string            `json:"text,omitempty"`
-	InlineData *GeminiInlineData `json:"inlineData,omitempty"`
-}
-
-type GeminiChatContent struct {
-	Role  string       `json:"role,omitempty"`
-	Parts []GeminiPart `json:"parts"`
-}
-
-type GeminiChatSafetySettings struct {
-	Category  string `json:"category"`
-	Threshold string `json:"threshold"`
-}
-
-type GeminiChatTools struct {
-	FunctionDeclarations any `json:"functionDeclarations,omitempty"`
-}
-
-type GeminiChatGenerationConfig struct {
-	Temperature     float64  `json:"temperature,omitempty"`
-	TopP            float64  `json:"topP,omitempty"`
-	TopK            float64  `json:"topK,omitempty"`
-	MaxOutputTokens int      `json:"maxOutputTokens,omitempty"`
-	CandidateCount  int      `json:"candidateCount,omitempty"`
-	StopSequences   []string `json:"stopSequences,omitempty"`
-}
-
 // Setting safety to the lowest possible values since Gemini is already powerless enough
-func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
-	geminiRequest := GeminiChatRequest{
-		Contents: make([]GeminiChatContent, 0, len(textRequest.Messages)),
-		SafetySettings: []GeminiChatSafetySettings{
+func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
+	geminiRequest := ChatRequest{
+		Contents: make([]ChatContent, 0, len(textRequest.Messages)),
+		SafetySettings: []ChatSafetySettings{
 			{
 				Category:  "HARM_CATEGORY_HARASSMENT",
-				Threshold: common.GeminiSafetySetting,
+				Threshold: config.GeminiSafetySetting,
 			},
 			{
 				Category:  "HARM_CATEGORY_HATE_SPEECH",
-				Threshold: common.GeminiSafetySetting,
+				Threshold: config.GeminiSafetySetting,
 			},
 			{
 				Category:  "HARM_CATEGORY_SEXUALLY_EXPLICIT",
-				Threshold: common.GeminiSafetySetting,
+				Threshold: config.GeminiSafetySetting,
 			},
 			{
 				Category:  "HARM_CATEGORY_DANGEROUS_CONTENT",
-				Threshold: common.GeminiSafetySetting,
+				Threshold: config.GeminiSafetySetting,
 			},
 		},
-		GenerationConfig: GeminiChatGenerationConfig{
+		GenerationConfig: ChatGenerationConfig{
 			Temperature:     textRequest.Temperature,
 			TopP:            textRequest.TopP,
 			MaxOutputTokens: textRequest.MaxTokens,
 		},
 	}
 	if textRequest.Functions != nil {
-		geminiRequest.Tools = []GeminiChatTools{
+		geminiRequest.Tools = []ChatTools{
 			{
 				FunctionDeclarations: textRequest.Functions,
 			},
@@ -96,30 +62,30 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
 	}
 	shouldAddDummyModelMessage := false
 	for _, message := range textRequest.Messages {
-		content := GeminiChatContent{
+		content := ChatContent{
 			Role: message.Role,
-			Parts: []GeminiPart{
+			Parts: []Part{
 				{
 					Text: message.StringContent(),
 				},
 			},
 		}
 		openaiContent := message.ParseContent()
-		var parts []GeminiPart
+		var parts []Part
 		imageNum := 0
 		for _, part := range openaiContent {
-			if part.Type == ContentTypeText {
-				parts = append(parts, GeminiPart{
+			if part.Type == model.ContentTypeText {
+				parts = append(parts, Part{
 					Text: part.Text,
 				})
-			} else if part.Type == ContentTypeImageURL {
+			} else if part.Type == model.ContentTypeImageURL {
 				imageNum += 1
-				if imageNum > GeminiVisionMaxImageNum {
+				if imageNum > VisionMaxImageNum {
 					continue
 				}
 				mimeType, data, _ := image.GetImageFromUrl(part.ImageURL.Url)
-				parts = append(parts, GeminiPart{
-					InlineData: &GeminiInlineData{
+				parts = append(parts, Part{
+					InlineData: &InlineData{
 						MimeType: mimeType,
 						Data:     data,
 					},
@@ -141,9 +107,9 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {

 		// If a system message is the last message, we need to add a dummy model message to make gemini happy
 		if shouldAddDummyModelMessage {
-			geminiRequest.Contents = append(geminiRequest.Contents, GeminiChatContent{
+			geminiRequest.Contents = append(geminiRequest.Contents, ChatContent{
 				Role: "model",
-				Parts: []GeminiPart{
+				Parts: []Part{
 					{
 						Text: "Okay",
 					},
@@ -156,12 +122,12 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
 	return &geminiRequest
 }

-type GeminiChatResponse struct {
-	Candidates     []GeminiChatCandidate    `json:"candidates"`
-	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
+type ChatResponse struct {
+	Candidates     []ChatCandidate    `json:"candidates"`
+	PromptFeedback ChatPromptFeedback `json:"promptFeedback"`
 }

-func (g *GeminiChatResponse) GetResponseText() string {
+func (g *ChatResponse) GetResponseText() string {
 	if g == nil {
 		return ""
 	}
@@ -171,37 +137,37 @@ func (g *GeminiChatResponse) GetResponseText() string {
 	return ""
 }

-type GeminiChatCandidate struct {
-	Content       GeminiChatContent        `json:"content"`
-	FinishReason  string                   `json:"finishReason"`
-	Index         int64                    `json:"index"`
-	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+type ChatCandidate struct {
+	Content       ChatContent        `json:"content"`
+	FinishReason  string             `json:"finishReason"`
+	Index         int64              `json:"index"`
+	SafetyRatings []ChatSafetyRating `json:"safetyRatings"`
 }

-type GeminiChatSafetyRating struct {
+type ChatSafetyRating struct {
 	Category    string `json:"category"`
 	Probability string `json:"probability"`
 }

-type GeminiChatPromptFeedback struct {
-	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+type ChatPromptFeedback struct {
+	SafetyRatings []ChatSafetyRating `json:"safetyRatings"`
 }

-func responseGeminiChat2OpenAI(response *GeminiChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
-		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+func responseGeminiChat2OpenAI(response *ChatResponse) *openai.TextResponse {
+	fullTextResponse := openai.TextResponse{
+		Id:      fmt.Sprintf("chatcmpl-%s", helper.GetUUID()),
 		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Choices: make([]OpenAITextResponseChoice, 0, len(response.Candidates)),
+		Created: helper.GetTimestamp(),
+		Choices: make([]openai.TextResponseChoice, 0, len(response.Candidates)),
 	}
 	for i, candidate := range response.Candidates {
-		choice := OpenAITextResponseChoice{
+		choice := openai.TextResponseChoice{
 			Index: i,
-			Message: Message{
+			Message: model.Message{
 				Role:    "assistant",
 				Content: "",
 			},
-			FinishReason: stopFinishReason,
+			FinishReason: constant.StopFinishReason,
 		}
 		if len(candidate.Content.Parts) > 0 {
 			choice.Message.Content = candidate.Content.Parts[0].Text
@@ -211,18 +177,18 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *OpenAITextResponse
 	return &fullTextResponse
 }

-func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseGeminiChat2OpenAI(geminiResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = geminiResponse.GetResponseText()
-	choice.FinishReason = &stopFinishReason
-	var response ChatCompletionsStreamResponse
+	choice.FinishReason = &constant.StopFinishReason
+	var response openai.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = "gemini"
-	response.Choices = []ChatCompletionsStreamResponseChoice{choice}
+	response.Choices = []openai.ChatCompletionsStreamResponseChoice{choice}
 	return &response
 }

-func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
 	responseText := ""
 	dataChan := make(chan string)
 	stopChan := make(chan bool)
@@ -252,7 +218,7 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorW
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -264,18 +230,18 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorW
 			var dummy dummyStruct
 			err := json.Unmarshal([]byte(data), &dummy)
 			responseText += dummy.Content
-			var choice ChatCompletionsStreamResponseChoice
+			var choice openai.ChatCompletionsStreamResponseChoice
 			choice.Delta.Content = dummy.Content
-			response := ChatCompletionsStreamResponse{
-				Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+			response := openai.ChatCompletionsStreamResponse{
+				Id:      fmt.Sprintf("chatcmpl-%s", helper.GetUUID()),
 				Object:  "chat.completion.chunk",
-				Created: common.GetTimestamp(),
+				Created: helper.GetTimestamp(),
 				Model:   "gemini-pro",
-				Choices: []ChatCompletionsStreamResponseChoice{choice},
+				Choices: []openai.ChatCompletionsStreamResponseChoice{choice},
 			}
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
+				logger.SysError("error marshalling stream response: " + err.Error())
 				return true
 			}
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
@@ -287,28 +253,28 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorW
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	return nil, responseText
 }

-func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName string) (*model.ErrorWithStatusCode, *model.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	var geminiResponse GeminiChatResponse
+	var geminiResponse ChatResponse
 	err = json.Unmarshal(responseBody, &geminiResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if len(geminiResponse.Candidates) == 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: "No candidates returned",
 				Type:    "server_error",
 				Param:   "",
@@ -318,9 +284,9 @@ func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, mo
 		}, nil
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
-	fullTextResponse.Model = model
-	completionTokens := countTokenText(geminiResponse.GetResponseText(), model)
-	usage := Usage{
+	fullTextResponse.Model = modelName
+	completionTokens := openai.CountTokenText(geminiResponse.GetResponseText(), modelName)
+	usage := model.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -328,7 +294,7 @@ func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, mo
 	fullTextResponse.Usage = usage
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/gemini/model.go
+++ b/relay/channel/gemini/model.go
@@ -0,0 +1,41 @@
+package gemini
+
+type ChatRequest struct {
+	Contents         []ChatContent        `json:"contents"`
+	SafetySettings   []ChatSafetySettings `json:"safety_settings,omitempty"`
+	GenerationConfig ChatGenerationConfig `json:"generation_config,omitempty"`
+	Tools            []ChatTools          `json:"tools,omitempty"`
+}
+
+type InlineData struct {
+	MimeType string `json:"mimeType"`
+	Data     string `json:"data"`
+}
+
+type Part struct {
+	Text       string      `json:"text,omitempty"`
+	InlineData *InlineData `json:"inlineData,omitempty"`
+}
+
+type ChatContent struct {
+	Role  string `json:"role,omitempty"`
+	Parts []Part `json:"parts"`
+}
+
+type ChatSafetySettings struct {
+	Category  string `json:"category"`
+	Threshold string `json:"threshold"`
+}
+
+type ChatTools struct {
+	FunctionDeclarations any `json:"functionDeclarations,omitempty"`
+}
+
+type ChatGenerationConfig struct {
+	Temperature     float64  `json:"temperature,omitempty"`
+	TopP            float64  `json:"topP,omitempty"`
+	TopK            float64  `json:"topK,omitempty"`
+	MaxOutputTokens int      `json:"maxOutputTokens,omitempty"`
+	CandidateCount  int      `json:"candidateCount,omitempty"`
+	StopSequences   []string `json:"stopSequences,omitempty"`
+}
--- a/relay/channel/interface.go
+++ b/relay/channel/interface.go
@@ -0,0 +1,20 @@
+package channel
+
+import (
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor interface {
+	Init(meta *util.RelayMeta)
+	GetRequestURL(meta *util.RelayMeta) (string, error)
+	SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error
+	ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error)
+	DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error)
+	DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode)
+	GetModelList() []string
+	GetChannelName() string
+}
--- a/relay/channel/moonshot/constants.go
+++ b/relay/channel/moonshot/constants.go
@@ -0,0 +1,7 @@
+package moonshot
+
+var ModelList = []string{
+	"moonshot-v1-8k",
+	"moonshot-v1-32k",
+	"moonshot-v1-128k",
+}
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -0,0 +1,103 @@
+package openai
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/channel/ai360"
+	"github.com/songquanpeng/one-api/relay/channel/moonshot"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+	"strings"
+)
+
+type Adaptor struct {
+	ChannelType int
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+	a.ChannelType = meta.ChannelType
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	if meta.ChannelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
+		requestURL := strings.Split(meta.RequestURLPath, "?")[0]
+		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, meta.APIVersion)
+		task := strings.TrimPrefix(requestURL, "/v1/")
+		model_ := meta.ActualModelName
+		model_ = strings.Replace(model_, ".", "", -1)
+		// https://github.com/songquanpeng/one-api/issues/67
+		model_ = strings.TrimSuffix(model_, "-0301")
+		model_ = strings.TrimSuffix(model_, "-0314")
+		model_ = strings.TrimSuffix(model_, "-0613")
+
+		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
+		return util.GetFullRequestURL(meta.BaseURL, requestURL, meta.ChannelType), nil
+	}
+	return util.GetFullRequestURL(meta.BaseURL, meta.RequestURLPath, meta.ChannelType), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	if meta.ChannelType == common.ChannelTypeAzure {
+		req.Header.Set("api-key", meta.APIKey)
+		return nil
+	}
+	req.Header.Set("Authorization", "Bearer "+meta.APIKey)
+	if meta.ChannelType == common.ChannelTypeOpenRouter {
+		req.Header.Set("HTTP-Referer", "https://github.com/songquanpeng/one-api")
+		req.Header.Set("X-Title", "One API")
+	}
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = StreamHandler(c, resp, meta.Mode)
+		usage = ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	switch a.ChannelType {
+	case common.ChannelType360:
+		return ai360.ModelList
+	case common.ChannelTypeMoonshot:
+		return moonshot.ModelList
+	default:
+		return ModelList
+	}
+}
+
+func (a *Adaptor) GetChannelName() string {
+	switch a.ChannelType {
+	case common.ChannelTypeAzure:
+		return "azure"
+	case common.ChannelType360:
+		return "360"
+	case common.ChannelTypeMoonshot:
+		return "moonshot"
+	default:
+		return "openai"
+	}
+}
--- a/relay/channel/openai/constants.go
+++ b/relay/channel/openai/constants.go
@@ -0,0 +1,19 @@
+package openai
+
+var ModelList = []string{
+	"gpt-3.5-turbo", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125",
+	"gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613",
+	"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-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",
+	"text-moderation-latest", "text-moderation-stable",
+	"text-davinci-edit-001",
+	"davinci-002", "babbage-002",
+	"dall-e-2", "dall-e-3",
+	"whisper-1",
+	"tts-1", "tts-1-1106", "tts-1-hd", "tts-1-hd-1106",
+}
--- a/relay/channel/openai/helper.go
+++ b/relay/channel/openai/helper.go
@@ -0,0 +1,11 @@
+package openai
+
+import "github.com/songquanpeng/one-api/relay/model"
+
+func ResponseText2Usage(responseText string, modeName string, promptTokens int) *model.Usage {
+	usage := &model.Usage{}
+	usage.PromptTokens = promptTokens
+	usage.CompletionTokens = CountTokenText(responseText, modeName)
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	return usage
+}
--- a/relay/channel/openai/main.go
+++ b/relay/channel/openai/main.go
@@ -1,17 +1,20 @@
-package controller
+package openai

 import (
 	"bufio"
 	"bytes"
 	"encoding/json"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
 	"strings"
 )

-func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*OpenAIErrorWithStatusCode, string) {
+func StreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*model.ErrorWithStatusCode, string) {
 	responseText := ""
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
@@ -41,21 +44,21 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
 				switch relayMode {
-				case RelayModeChatCompletions:
+				case constant.RelayModeChatCompletions:
 					var streamResponse ChatCompletionsStreamResponse
 					err := json.Unmarshal([]byte(data), &streamResponse)
 					if err != nil {
-						common.SysError("error unmarshalling stream response: " + err.Error())
+						logger.SysError("error unmarshalling stream response: " + err.Error())
 						continue // just ignore the error
 					}
 					for _, choice := range streamResponse.Choices {
 						responseText += choice.Delta.Content
 					}
-				case RelayModeCompletions:
+				case constant.RelayModeCompletions:
 					var streamResponse CompletionsStreamResponse
 					err := json.Unmarshal([]byte(data), &streamResponse)
 					if err != nil {
-						common.SysError("error unmarshalling stream response: " + err.Error())
+						logger.SysError("error unmarshalling stream response: " + err.Error())
 						continue
 					}
 					for _, choice := range streamResponse.Choices {
@@ -66,7 +69,7 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -83,29 +86,29 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	return nil, responseText
 }

-func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
-	var textResponse TextResponse
+func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName string) (*model.ErrorWithStatusCode, *model.Usage) {
+	var textResponse SlimTextResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &textResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if textResponse.Error.Type != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: textResponse.Error,
-			StatusCode:  resp.StatusCode,
+		return &model.ErrorWithStatusCode{
+			Error:      textResponse.Error,
+			StatusCode: resp.StatusCode,
 		}, nil
 	}
 	// Reset response body
@@ -113,7 +116,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model

 	// We shouldn't set the header before we parse the response body, because the parse part may fail.
 	// And then we will have to send an error response, but in this case, the header has already been set.
-	// So the httpClient will be confused by the response.
+	// So the HTTPClient will be confused by the response.
 	// For example, Postman will report error, and we cannot check the response at all.
 	for k, v := range resp.Header {
 		c.Writer.Header().Set(k, v[0])
@@ -121,19 +124,19 @@ func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	c.Writer.WriteHeader(resp.StatusCode)
 	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
-		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
+		return ErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}

 	if textResponse.Usage.TotalTokens == 0 {
 		completionTokens := 0
 		for _, choice := range textResponse.Choices {
-			completionTokens += countTokenText(choice.Message.StringContent(), model)
+			completionTokens += CountTokenText(choice.Message.StringContent(), modelName)
 		}
-		textResponse.Usage = Usage{
+		textResponse.Usage = model.Usage{
 			PromptTokens:     promptTokens,
 			CompletionTokens: completionTokens,
 			TotalTokens:      promptTokens + completionTokens,
--- a/relay/channel/openai/model.go
+++ b/relay/channel/openai/model.go
@@ -0,0 +1,140 @@
+package openai
+
+import "github.com/songquanpeng/one-api/relay/model"
+
+type TextContent struct {
+	Type string `json:"type,omitempty"`
+	Text string `json:"text,omitempty"`
+}
+
+type ImageContent struct {
+	Type     string          `json:"type,omitempty"`
+	ImageURL *model.ImageURL `json:"image_url,omitempty"`
+}
+
+type ChatRequest struct {
+	Model     string          `json:"model"`
+	Messages  []model.Message `json:"messages"`
+	MaxTokens int             `json:"max_tokens"`
+}
+
+type TextRequest struct {
+	Model     string          `json:"model"`
+	Messages  []model.Message `json:"messages"`
+	Prompt    string          `json:"prompt"`
+	MaxTokens int             `json:"max_tokens"`
+	//Stream   bool      `json:"stream"`
+}
+
+// ImageRequest docs: https://platform.openai.com/docs/api-reference/images/create
+type ImageRequest struct {
+	Model          string `json:"model"`
+	Prompt         string `json:"prompt" binding:"required"`
+	N              int    `json:"n,omitempty"`
+	Size           string `json:"size,omitempty"`
+	Quality        string `json:"quality,omitempty"`
+	ResponseFormat string `json:"response_format,omitempty"`
+	Style          string `json:"style,omitempty"`
+	User           string `json:"user,omitempty"`
+}
+
+type WhisperJSONResponse struct {
+	Text string `json:"text,omitempty"`
+}
+
+type WhisperVerboseJSONResponse struct {
+	Task     string    `json:"task,omitempty"`
+	Language string    `json:"language,omitempty"`
+	Duration float64   `json:"duration,omitempty"`
+	Text     string    `json:"text,omitempty"`
+	Segments []Segment `json:"segments,omitempty"`
+}
+
+type Segment struct {
+	Id               int     `json:"id"`
+	Seek             int     `json:"seek"`
+	Start            float64 `json:"start"`
+	End              float64 `json:"end"`
+	Text             string  `json:"text"`
+	Tokens           []int   `json:"tokens"`
+	Temperature      float64 `json:"temperature"`
+	AvgLogprob       float64 `json:"avg_logprob"`
+	CompressionRatio float64 `json:"compression_ratio"`
+	NoSpeechProb     float64 `json:"no_speech_prob"`
+}
+
+type TextToSpeechRequest struct {
+	Model          string  `json:"model" binding:"required"`
+	Input          string  `json:"input" binding:"required"`
+	Voice          string  `json:"voice" binding:"required"`
+	Speed          float64 `json:"speed"`
+	ResponseFormat string  `json:"response_format"`
+}
+
+type UsageOrResponseText struct {
+	*model.Usage
+	ResponseText string
+}
+
+type SlimTextResponse struct {
+	Choices     []TextResponseChoice `json:"choices"`
+	model.Usage `json:"usage"`
+	Error       model.Error `json:"error"`
+}
+
+type TextResponseChoice struct {
+	Index         int `json:"index"`
+	model.Message `json:"message"`
+	FinishReason  string `json:"finish_reason"`
+}
+
+type TextResponse struct {
+	Id          string               `json:"id"`
+	Model       string               `json:"model,omitempty"`
+	Object      string               `json:"object"`
+	Created     int64                `json:"created"`
+	Choices     []TextResponseChoice `json:"choices"`
+	model.Usage `json:"usage"`
+}
+
+type EmbeddingResponseItem struct {
+	Object    string    `json:"object"`
+	Index     int       `json:"index"`
+	Embedding []float64 `json:"embedding"`
+}
+
+type EmbeddingResponse struct {
+	Object      string                  `json:"object"`
+	Data        []EmbeddingResponseItem `json:"data"`
+	Model       string                  `json:"model"`
+	model.Usage `json:"usage"`
+}
+
+type ImageResponse struct {
+	Created int `json:"created"`
+	Data    []struct {
+		Url string `json:"url"`
+	}
+}
+
+type ChatCompletionsStreamResponseChoice struct {
+	Delta struct {
+		Content string `json:"content"`
+	} `json:"delta"`
+	FinishReason *string `json:"finish_reason,omitempty"`
+}
+
+type ChatCompletionsStreamResponse struct {
+	Id      string                                `json:"id"`
+	Object  string                                `json:"object"`
+	Created int64                                 `json:"created"`
+	Model   string                                `json:"model"`
+	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+}
+
+type CompletionsStreamResponse struct {
+	Choices []struct {
+		Text         string `json:"text"`
+		FinishReason string `json:"finish_reason"`
+	} `json:"choices"`
+}
--- a/relay/channel/openai/token.go
+++ b/relay/channel/openai/token.go
@@ -1,41 +1,34 @@
-package controller
+package openai

 import (
-	"context"
-	"encoding/json"
 	"errors"
 	"fmt"
-	"io"
-	"math"
-	"net/http"
-	"one-api/common"
-	"one-api/common/image"
-	"one-api/model"
-	"strconv"
-	"strings"
-
-	"github.com/gin-gonic/gin"
 	"github.com/pkoukk/tiktoken-go"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/image"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/model"
+	"math"
+	"strings"
 )

-var stopFinishReason = "stop"
-
 // tokenEncoderMap won't grow after initialization
 var tokenEncoderMap = map[string]*tiktoken.Tiktoken{}
 var defaultTokenEncoder *tiktoken.Tiktoken

 func InitTokenEncoders() {
-	common.SysLog("initializing token encoders")
+	logger.SysLog("initializing token encoders")
 	gpt35TokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
 	if err != nil {
-		common.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
+		logger.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
 	}
 	defaultTokenEncoder = gpt35TokenEncoder
 	gpt4TokenEncoder, err := tiktoken.EncodingForModel("gpt-4")
 	if err != nil {
-		common.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
+		logger.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
 	}
-	for model, _ := range common.ModelRatio {
+	for model := range common.ModelRatio {
 		if strings.HasPrefix(model, "gpt-3.5") {
 			tokenEncoderMap[model] = gpt35TokenEncoder
 		} else if strings.HasPrefix(model, "gpt-4") {
@@ -44,7 +37,7 @@ func InitTokenEncoders() {
 			tokenEncoderMap[model] = nil
 		}
 	}
-	common.SysLog("token encoders initialized")
+	logger.SysLog("token encoders initialized")
 }

 func getTokenEncoder(model string) *tiktoken.Tiktoken {
@@ -55,7 +48,7 @@ func getTokenEncoder(model string) *tiktoken.Tiktoken {
 	if ok {
 		tokenEncoder, err := tiktoken.EncodingForModel(model)
 		if err != nil {
-			common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
+			logger.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
 			tokenEncoder = defaultTokenEncoder
 		}
 		tokenEncoderMap[model] = tokenEncoder
@@ -65,13 +58,13 @@ func getTokenEncoder(model string) *tiktoken.Tiktoken {
 }

 func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
-	if common.ApproximateTokenEnabled {
+	if config.ApproximateTokenEnabled {
 		return int(float64(len(text)) * 0.38)
 	}
 	return len(tokenEncoder.Encode(text, nil, nil))
 }

-func countTokenMessages(messages []Message, model string) int {
+func CountTokenMessages(messages []model.Message, model string) int {
 	tokenEncoder := getTokenEncoder(model)
 	// Reference:
 	// https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
@@ -109,7 +102,7 @@ func countTokenMessages(messages []Message, model string) int {
 						}
 						imageTokens, err := countImageTokens(url, detail)
 						if err != nil {
-							common.SysError("error counting image tokens: " + err.Error())
+							logger.SysError("error counting image tokens: " + err.Error())
 						} else {
 							tokenNum += imageTokens
 						}
@@ -195,191 +188,21 @@ func countImageTokens(url string, detail string) (_ int, err error) {
 	}
 }

-func countTokenInput(input any, model string) int {
+func CountTokenInput(input any, model string) int {
 	switch v := input.(type) {
 	case string:
-		return countTokenText(v, model)
+		return CountTokenText(v, model)
 	case []string:
 		text := ""
 		for _, s := range v {
 			text += s
 		}
-		return countTokenText(text, model)
+		return CountTokenText(text, model)
 	}
 	return 0
 }

-func countTokenText(text string, model string) int {
+func CountTokenText(text string, model string) int {
 	tokenEncoder := getTokenEncoder(model)
 	return getTokenNum(tokenEncoder, text)
 }
-
-func errorWrapper(err error, code string, statusCode int) *OpenAIErrorWithStatusCode {
-	openAIError := OpenAIError{
-		Message: err.Error(),
-		Type:    "one_api_error",
-		Code:    code,
-	}
-	return &OpenAIErrorWithStatusCode{
-		OpenAIError: openAIError,
-		StatusCode:  statusCode,
-	}
-}
-
-func shouldDisableChannel(err *OpenAIError, statusCode int) bool {
-	if !common.AutomaticDisableChannelEnabled {
-		return false
-	}
-	if err == nil {
-		return false
-	}
-	if statusCode == http.StatusUnauthorized {
-		return true
-	}
-	if err.Type == "insufficient_quota" || err.Code == "invalid_api_key" || err.Code == "account_deactivated" {
-		return true
-	}
-	return false
-}
-
-func shouldEnableChannel(err error, openAIErr *OpenAIError) bool {
-	if !common.AutomaticEnableChannelEnabled {
-		return false
-	}
-	if err != nil {
-		return false
-	}
-	if openAIErr != nil {
-		return false
-	}
-	return true
-}
-
-func setEventStreamHeaders(c *gin.Context) {
-	c.Writer.Header().Set("Content-Type", "text/event-stream")
-	c.Writer.Header().Set("Cache-Control", "no-cache")
-	c.Writer.Header().Set("Connection", "keep-alive")
-	c.Writer.Header().Set("Transfer-Encoding", "chunked")
-	c.Writer.Header().Set("X-Accel-Buffering", "no")
-}
-
-type GeneralErrorResponse struct {
-	Error    OpenAIError `json:"error"`
-	Message  string      `json:"message"`
-	Msg      string      `json:"msg"`
-	Err      string      `json:"err"`
-	ErrorMsg string      `json:"error_msg"`
-	Header   struct {
-		Message string `json:"message"`
-	} `json:"header"`
-	Response struct {
-		Error struct {
-			Message string `json:"message"`
-		} `json:"error"`
-	} `json:"response"`
-}
-
-func (e GeneralErrorResponse) ToMessage() string {
-	if e.Error.Message != "" {
-		return e.Error.Message
-	}
-	if e.Message != "" {
-		return e.Message
-	}
-	if e.Msg != "" {
-		return e.Msg
-	}
-	if e.Err != "" {
-		return e.Err
-	}
-	if e.ErrorMsg != "" {
-		return e.ErrorMsg
-	}
-	if e.Header.Message != "" {
-		return e.Header.Message
-	}
-	if e.Response.Error.Message != "" {
-		return e.Response.Error.Message
-	}
-	return ""
-}
-
-func relayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *OpenAIErrorWithStatusCode) {
-	openAIErrorWithStatusCode = &OpenAIErrorWithStatusCode{
-		StatusCode: resp.StatusCode,
-		OpenAIError: OpenAIError{
-			Message: "",
-			Type:    "upstream_error",
-			Code:    "bad_response_status_code",
-			Param:   strconv.Itoa(resp.StatusCode),
-		},
-	}
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return
-	}
-	var errResponse GeneralErrorResponse
-	err = json.Unmarshal(responseBody, &errResponse)
-	if err != nil {
-		return
-	}
-	if errResponse.Error.Message != "" {
-		// OpenAI format error, so we override the default one
-		openAIErrorWithStatusCode.OpenAIError = errResponse.Error
-	} else {
-		openAIErrorWithStatusCode.OpenAIError.Message = errResponse.ToMessage()
-	}
-	if openAIErrorWithStatusCode.OpenAIError.Message == "" {
-		openAIErrorWithStatusCode.OpenAIError.Message = fmt.Sprintf("bad response status code %d", resp.StatusCode)
-	}
-	return
-}
-
-func getFullRequestURL(baseURL string, requestURL string, channelType int) string {
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
-
-	if strings.HasPrefix(baseURL, "https://gateway.ai.cloudflare.com") {
-		switch channelType {
-		case common.ChannelTypeOpenAI:
-			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/v1"))
-		case common.ChannelTypeAzure:
-			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/openai/deployments"))
-		}
-	}
-	return fullRequestURL
-}
-
-func postConsumeQuota(ctx context.Context, tokenId int, quotaDelta int, totalQuota int, userId int, channelId int, modelRatio float64, groupRatio float64, modelName string, tokenName string) {
-	// quotaDelta is remaining quota to be consumed
-	err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
-	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())
-	}
-	// totalQuota is total quota consumed
-	if totalQuota != 0 {
-		logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-		model.RecordConsumeLog(ctx, userId, channelId, totalQuota, 0, modelName, tokenName, totalQuota, logContent)
-		model.UpdateUserUsedQuotaAndRequestCount(userId, totalQuota)
-		model.UpdateChannelUsedQuota(channelId, totalQuota)
-	}
-	if totalQuota <= 0 {
-		common.LogError(ctx, fmt.Sprintf("totalQuota consumed is %d, something is wrong", totalQuota))
-	}
-}
-
-func GetAPIVersion(c *gin.Context) string {
-	query := c.Request.URL.Query()
-	apiVersion := query.Get("api-version")
-	if apiVersion == "" {
-		apiVersion = c.GetString("api_version")
-	}
-	return apiVersion
-}
--- a/relay/channel/openai/util.go
+++ b/relay/channel/openai/util.go
@@ -0,0 +1,15 @@
+package openai
+
+import "github.com/songquanpeng/one-api/relay/model"
+
+func ErrorWrapper(err error, code string, statusCode int) *model.ErrorWithStatusCode {
+	Error := model.Error{
+		Message: err.Error(),
+		Type:    "one_api_error",
+		Code:    code,
+	}
+	return &model.ErrorWithStatusCode{
+		Error:      Error,
+		StatusCode: statusCode,
+	}
+}
--- a/relay/channel/palm/adaptor.go
+++ b/relay/channel/palm/adaptor.go
@@ -0,0 +1,60 @@
+package palm
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	return fmt.Sprintf("%s/v1beta2/models/chat-bison-001:generateMessage", meta.BaseURL), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("x-goog-api-key", meta.APIKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return ConvertRequest(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = StreamHandler(c, resp)
+		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "google palm"
+}
--- a/relay/channel/palm/constants.go
+++ b/relay/channel/palm/constants.go
@@ -0,0 +1,5 @@
+package palm
+
+var ModelList = []string{
+	"PaLM-2",
+}
--- a/relay/channel/palm/model.go
+++ b/relay/channel/palm/model.go
@@ -0,0 +1,40 @@
+package palm
+
+import (
+	"github.com/songquanpeng/one-api/relay/model"
+)
+
+type ChatMessage struct {
+	Author  string `json:"author"`
+	Content string `json:"content"`
+}
+
+type Filter struct {
+	Reason  string `json:"reason"`
+	Message string `json:"message"`
+}
+
+type Prompt struct {
+	Messages []ChatMessage `json:"messages"`
+}
+
+type ChatRequest struct {
+	Prompt         Prompt  `json:"prompt"`
+	Temperature    float64 `json:"temperature,omitempty"`
+	CandidateCount int     `json:"candidateCount,omitempty"`
+	TopP           float64 `json:"topP,omitempty"`
+	TopK           int     `json:"topK,omitempty"`
+}
+
+type Error struct {
+	Code    int    `json:"code"`
+	Message string `json:"message"`
+	Status  string `json:"status"`
+}
+
+type ChatResponse struct {
+	Candidates []ChatMessage   `json:"candidates"`
+	Messages   []model.Message `json:"messages"`
+	Filters    []Filter        `json:"filters"`
+	Error      Error           `json:"error"`
+}
--- a/relay/channel/palm/palm.go
+++ b/relay/channel/palm/palm.go
@@ -1,56 +1,26 @@
-package controller
+package palm

 import (
 	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
-	"one-api/common"
 )

 // https://developers.generativeai.google/api/rest/generativelanguage/models/generateMessage#request-body
 // https://developers.generativeai.google/api/rest/generativelanguage/models/generateMessage#response-body

-type PaLMChatMessage struct {
-	Author  string `json:"author"`
-	Content string `json:"content"`
-}
-
-type PaLMFilter struct {
-	Reason  string `json:"reason"`
-	Message string `json:"message"`
-}
-
-type PaLMPrompt struct {
-	Messages []PaLMChatMessage `json:"messages"`
-}
-
-type PaLMChatRequest struct {
-	Prompt         PaLMPrompt `json:"prompt"`
-	Temperature    float64    `json:"temperature,omitempty"`
-	CandidateCount int        `json:"candidateCount,omitempty"`
-	TopP           float64    `json:"topP,omitempty"`
-	TopK           int        `json:"topK,omitempty"`
-}
-
-type PaLMError struct {
-	Code    int    `json:"code"`
-	Message string `json:"message"`
-	Status  string `json:"status"`
-}
-
-type PaLMChatResponse struct {
-	Candidates []PaLMChatMessage `json:"candidates"`
-	Messages   []Message         `json:"messages"`
-	Filters    []PaLMFilter      `json:"filters"`
-	Error      PaLMError         `json:"error"`
-}
-
-func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
-	palmRequest := PaLMChatRequest{
-		Prompt: PaLMPrompt{
-			Messages: make([]PaLMChatMessage, 0, len(textRequest.Messages)),
+func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
+	palmRequest := ChatRequest{
+		Prompt: Prompt{
+			Messages: make([]ChatMessage, 0, len(textRequest.Messages)),
 		},
 		Temperature:    textRequest.Temperature,
 		CandidateCount: textRequest.N,
@@ -58,7 +28,7 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 		TopK:           textRequest.MaxTokens,
 	}
 	for _, message := range textRequest.Messages {
-		palmMessage := PaLMChatMessage{
+		palmMessage := ChatMessage{
 			Content: message.StringContent(),
 		}
 		if message.Role == "user" {
@@ -71,14 +41,14 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 	return &palmRequest
 }

-func responsePaLM2OpenAI(response *PaLMChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
-		Choices: make([]OpenAITextResponseChoice, 0, len(response.Candidates)),
+func responsePaLM2OpenAI(response *ChatResponse) *openai.TextResponse {
+	fullTextResponse := openai.TextResponse{
+		Choices: make([]openai.TextResponseChoice, 0, len(response.Candidates)),
 	}
 	for i, candidate := range response.Candidates {
-		choice := OpenAITextResponseChoice{
+		choice := openai.TextResponseChoice{
 			Index: i,
-			Message: Message{
+			Message: model.Message{
 				Role:    "assistant",
 				Content: candidate.Content,
 			},
@@ -89,42 +59,42 @@ func responsePaLM2OpenAI(response *PaLMChatResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

-func streamResponsePaLM2OpenAI(palmResponse *PaLMChatResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponsePaLM2OpenAI(palmResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
+	var choice openai.ChatCompletionsStreamResponseChoice
 	if len(palmResponse.Candidates) > 0 {
 		choice.Delta.Content = palmResponse.Candidates[0].Content
 	}
-	choice.FinishReason = &stopFinishReason
-	var response ChatCompletionsStreamResponse
+	choice.FinishReason = &constant.StopFinishReason
+	var response openai.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = "palm2"
-	response.Choices = []ChatCompletionsStreamResponseChoice{choice}
+	response.Choices = []openai.ChatCompletionsStreamResponseChoice{choice}
 	return &response
 }

-func palmStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
 	responseText := ""
-	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
-	createdTime := common.GetTimestamp()
+	responseId := fmt.Sprintf("chatcmpl-%s", helper.GetUUID())
+	createdTime := helper.GetTimestamp()
 	dataChan := make(chan string)
 	stopChan := make(chan bool)
 	go func() {
 		responseBody, err := io.ReadAll(resp.Body)
 		if err != nil {
-			common.SysError("error reading stream response: " + err.Error())
+			logger.SysError("error reading stream response: " + err.Error())
 			stopChan <- true
 			return
 		}
 		err = resp.Body.Close()
 		if err != nil {
-			common.SysError("error closing stream response: " + err.Error())
+			logger.SysError("error closing stream response: " + err.Error())
 			stopChan <- true
 			return
 		}
-		var palmResponse PaLMChatResponse
+		var palmResponse ChatResponse
 		err = json.Unmarshal(responseBody, &palmResponse)
 		if err != nil {
-			common.SysError("error unmarshalling stream response: " + err.Error())
+			logger.SysError("error unmarshalling stream response: " + err.Error())
 			stopChan <- true
 			return
 		}
@@ -136,14 +106,14 @@ func palmStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSta
 		}
 		jsonResponse, err := json.Marshal(fullTextResponse)
 		if err != nil {
-			common.SysError("error marshalling stream response: " + err.Error())
+			logger.SysError("error marshalling stream response: " + err.Error())
 			stopChan <- true
 			return
 		}
 		dataChan <- string(jsonResponse)
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	common.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -156,28 +126,28 @@ func palmStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSta
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	return nil, responseText
 }

-func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName string) (*model.ErrorWithStatusCode, *model.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	var palmResponse PaLMChatResponse
+	var palmResponse ChatResponse
 	err = json.Unmarshal(responseBody, &palmResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if palmResponse.Error.Code != 0 || len(palmResponse.Candidates) == 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
 				Message: palmResponse.Error.Message,
 				Type:    palmResponse.Error.Status,
 				Param:   "",
@@ -187,9 +157,9 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	fullTextResponse.Model = model
-	completionTokens := countTokenText(palmResponse.Candidates[0].Content, model)
-	usage := Usage{
+	fullTextResponse.Model = modelName
+	completionTokens := openai.CountTokenText(palmResponse.Candidates[0].Content, modelName)
+	usage := model.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -197,7 +167,7 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 	fullTextResponse.Usage = usage
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/tencent/adaptor.go
+++ b/relay/channel/tencent/adaptor.go
@@ -0,0 +1,76 @@
+package tencent
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/channel"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/util"
+	"io"
+	"net/http"
+	"strings"
+)
+
+// https://cloud.tencent.com/document/api/1729/101837
+
+type Adaptor struct {
+	Sign string
+}
+
+func (a *Adaptor) Init(meta *util.RelayMeta) {
+
+}
+
+func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) {
+	return fmt.Sprintf("%s/hyllm/v1/chat/completions", meta.BaseURL), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *util.RelayMeta) error {
+	channel.SetupCommonRequestHeader(c, req, meta)
+	req.Header.Set("Authorization", a.Sign)
+	req.Header.Set("X-TC-Action", meta.ActualModelName)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	apiKey := c.Request.Header.Get("Authorization")
+	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+	appId, secretId, secretKey, err := ParseConfig(apiKey)
+	if err != nil {
+		return nil, err
+	}
+	tencentRequest := ConvertRequest(*request)
+	tencentRequest.AppId = appId
+	tencentRequest.SecretId = secretId
+	// we have to calculate the sign here
+	a.Sign = GetSign(*tencentRequest, secretKey)
+	return tencentRequest, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *util.RelayMeta, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoRequestHelper(a, c, meta, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.RelayMeta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = StreamHandler(c, resp)
+		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		err, usage = Handler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return "tencent"
+}
--- a/relay/channel/tencent/constants.go
+++ b/relay/channel/tencent/constants.go
@@ -0,0 +1,7 @@
+package tencent
+
+var ModelList = []string{
+	"ChatPro",
+	"ChatStd",
+	"hunyuan",
+}
--- a/relay/channel/tencent/main.go
+++ b/relay/channel/tencent/main.go
@@ -0,0 +1,238 @@
+package tencent
+
+import (
+	"bufio"
+	"crypto/hmac"
+	"crypto/sha1"
+	"encoding/base64"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/channel/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
+	"io"
+	"net/http"
+	"sort"
+	"strconv"
+	"strings"
+)
+
+// https://cloud.tencent.com/document/product/1729/97732
+
+func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
+	messages := make([]Message, 0, len(request.Messages))
+	for i := 0; i < len(request.Messages); i++ {
+		message := request.Messages[i]
+		if message.Role == "system" {
+			messages = append(messages, Message{
+				Role:    "user",
+				Content: message.StringContent(),
+			})
+			messages = append(messages, Message{
+				Role:    "assistant",
+				Content: "Okay",
+			})
+			continue
+		}
+		messages = append(messages, Message{
+			Content: message.StringContent(),
+			Role:    message.Role,
+		})
+	}
+	stream := 0
+	if request.Stream {
+		stream = 1
+	}
+	return &ChatRequest{
+		Timestamp:   helper.GetTimestamp(),
+		Expired:     helper.GetTimestamp() + 24*60*60,
+		QueryID:     helper.GetUUID(),
+		Temperature: request.Temperature,
+		TopP:        request.TopP,
+		Stream:      stream,
+		Messages:    messages,
+	}
+}
+
+func responseTencent2OpenAI(response *ChatResponse) *openai.TextResponse {
+	fullTextResponse := openai.TextResponse{
+		Object:  "chat.completion",
+		Created: helper.GetTimestamp(),
+		Usage:   response.Usage,
+	}
+	if len(response.Choices) > 0 {
+		choice := openai.TextResponseChoice{
+			Index: 0,
+			Message: model.Message{
+				Role:    "assistant",
+				Content: response.Choices[0].Messages.Content,
+			},
+			FinishReason: response.Choices[0].FinishReason,
+		}
+		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	}
+	return &fullTextResponse
+}
+
+func streamResponseTencent2OpenAI(TencentResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
+	response := openai.ChatCompletionsStreamResponse{
+		Object:  "chat.completion.chunk",
+		Created: helper.GetTimestamp(),
+		Model:   "tencent-hunyuan",
+	}
+	if len(TencentResponse.Choices) > 0 {
+		var choice openai.ChatCompletionsStreamResponseChoice
+		choice.Delta.Content = TencentResponse.Choices[0].Delta.Content
+		if TencentResponse.Choices[0].FinishReason == "stop" {
+			choice.FinishReason = &constant.StopFinishReason
+		}
+		response.Choices = append(response.Choices, choice)
+	}
+	return &response
+}
+
+func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
+	var responseText string
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
+		if atEOF && len(data) == 0 {
+			return 0, nil, nil
+		}
+		if i := strings.Index(string(data), "\n"); i >= 0 {
+			return i + 1, data[0:i], nil
+		}
+		if atEOF {
+			return len(data), data, nil
+		}
+		return 0, nil, nil
+	})
+	dataChan := make(chan string)
+	stopChan := make(chan bool)
+	go func() {
+		for scanner.Scan() {
+			data := scanner.Text()
+			if len(data) < 5 { // ignore blank line or wrong format
+				continue
+			}
+			if data[:5] != "data:" {
+				continue
+			}
+			data = data[5:]
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	common.SetEventStreamHeaders(c)
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			var TencentResponse ChatResponse
+			err := json.Unmarshal([]byte(data), &TencentResponse)
+			if err != nil {
+				logger.SysError("error unmarshalling stream response: " + err.Error())
+				return true
+			}
+			response := streamResponseTencent2OpenAI(&TencentResponse)
+			if len(response.Choices) != 0 {
+				responseText += response.Choices[0].Delta.Content
+			}
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				logger.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	err := resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+	}
+	return nil, responseText
+}
+
+func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var TencentResponse ChatResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &TencentResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if TencentResponse.Error.Code != 0 {
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
+				Message: TencentResponse.Error.Message,
+				Code:    TencentResponse.Error.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := responseTencent2OpenAI(&TencentResponse)
+	fullTextResponse.Model = "hunyuan"
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "write_response_body_failed", http.StatusInternalServerError), nil
+	}
+	return nil, &fullTextResponse.Usage
+}
+
+func ParseConfig(config string) (appId int64, secretId string, secretKey string, err error) {
+	parts := strings.Split(config, "|")
+	if len(parts) != 3 {
+		err = errors.New("invalid tencent config")
+		return
+	}
+	appId, err = strconv.ParseInt(parts[0], 10, 64)
+	secretId = parts[1]
+	secretKey = parts[2]
+	return
+}
+
+func GetSign(req ChatRequest, secretKey string) string {
+	params := make([]string, 0)
+	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
+	params = append(params, "secret_id="+req.SecretId)
+	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
+	params = append(params, "query_id="+req.QueryID)
+	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
+	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
+	params = append(params, "stream="+strconv.Itoa(req.Stream))
+	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
+
+	var messageStr string
+	for _, msg := range req.Messages {
+		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
+	}
+	messageStr = strings.TrimSuffix(messageStr, ",")
+	params = append(params, "messages=["+messageStr+"]")
+
+	sort.Strings(params)
+	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
+	mac := hmac.New(sha1.New, []byte(secretKey))
+	signURL := url
+	mac.Write([]byte(signURL))
+	sign := mac.Sum([]byte(nil))
+	return base64.StdEncoding.EncodeToString(sign)
+}
--- a/relay/channel/tencent/model.go
+++ b/relay/channel/tencent/model.go
@@ -0,0 +1,63 @@
+package tencent
+
+import (
+	"github.com/songquanpeng/one-api/relay/model"
+)
+
+type Message struct {
+	Role    string `json:"role"`
+	Content string `json:"content"`
+}
+
+type ChatRequest struct {
+	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
+	SecretId string `json:"secret_id"` // 官网 SecretId
+	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
+	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
+	Timestamp int64 `json:"timestamp"`
+	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
+	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
+	Expired int64  `json:"expired"`
+	QueryID string `json:"query_id"` //请求 Id，用于问题排查
+	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
+	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
+	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
+	Temperature float64 `json:"temperature"`
+	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
+	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
+	// 建议该参数和 temperature 只设置1个，不要同时更改
+	TopP float64 `json:"top_p"`
+	// Stream 0：同步，1：流式 （默认，协议：SSE)
+	// 同步请求超时：60s，如果内容较长建议使用流式
+	Stream int `json:"stream"`
+	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
+	// 输入 content 总数最大支持 3000 token。
+	Messages []Message `json:"messages"`
+}
+
+type Error struct {
+	Code    int    `json:"code"`
+	Message string `json:"message"`
+}
+
+type Usage struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+	TotalTokens  int `json:"total_tokens"`
+}
+
+type ResponseChoices struct {
+	FinishReason string  `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     Message `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        Message `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+}
+
+type ChatResponse struct {
+	Choices []ResponseChoices `json:"choices,omitempty"` // 结果
+	Created string            `json:"created,omitempty"` // unix 时间戳的字符串
+	Id      string            `json:"id,omitempty"`      // 会话 id
+	Usage   model.Usage       `json:"usage,omitempty"`   // token 数量
+	Error   Error             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string            `json:"note,omitempty"`    // 注释
+	ReqID   string            `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+}
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
JustSong	565ea58e68	feat: built in retry supported (close #1036 , close #770 )	2024-02-25 19:01:49 +08:00
JustSong	f141a37a9e	fix: fix "error update user quota cache: Error 1040: Too many connections"	2024-02-25 16:58:14 +08:00
JustSong	5b78886ad3	fix: fix i18n	2024-02-25 16:53:46 +08:00
JustSong	87c7c4f0e6	fix: rm history build before building	2024-02-25 02:07:34 +08:00
JustSong	4c4a873890	fix: add an ending line for THEMES	2024-02-25 01:59:40 +08:00
JustSong	0664bdfda1	fix: fix build.sh (close #1026 )	2024-02-25 01:53:27 +08:00
JustSong	32387d9c20	fix: fix version is blank	2024-02-21 22:21:01 +08:00
JustSong	bd888f2eb7	fix: fix prompt token is zero (close #1023 )	2024-02-21 22:19:42 +08:00
JustSong	cece77e533	fix: fix model list	2024-02-19 22:20:18 +08:00
JustSong	2a5468e23c	refactor: remove useless button (close #1014 )	2024-02-18 22:21:37 +08:00
JustSong	d0e415893b	fix: fix SparkDesk model name	2024-02-18 17:16:11 +08:00
JustSong	6cf5ce9a7a	fix: fix SparkDesk model name	2024-02-18 17:11:16 +08:00
JustSong	f598b9df87	feat: add new SparkDesk models	2024-02-18 17:02:36 +08:00
JustSong	532c50d212	fix: fix channel table page copy	2024-02-18 16:19:14 +08:00
JustSong	2acc2f5017	feat: support moonshot now (close #804 )	2024-02-18 16:17:19 +08:00
JustSong	604ac56305	fix: set seed parameter for qwen (close #1005 )	2024-02-18 15:01:09 +08:00
JustSong	9383b638a6	feat: add ChatPro & ChatStd for tencent (#1010 )	2024-02-18 14:40:01 +08:00
JustSong	28d512a675	refactor: delete useless code	2024-02-18 02:23:31 +08:00
JustSong	de9a58ca0b	refactor: use config field to save config	2024-02-18 02:22:50 +08:00
JustSong	1aa374ccfb	refactor: use adaptor to do relay & test	2024-02-18 00:15:31 +08:00
Laisky.Cai	d548a01c59	feat: Handle errors, validate model names, and calculate quota usage (#978 ) - Improved error handling in various modules for better stability and responsiveness. - Optimized code in several files for improved efficiency and readability. - Enhanced user experience by providing more detailed error responses in the controller. - Strengthened security by ignoring sensitive files in `.gitignore`.	2024-02-12 21:35:40 +08:00
JustSong	2cd1a78203	chore: update module name	2024-01-28 19:38:58 +08:00
JustSong	b9d3cb0c45	refactor: split RelayTextHelper function	2024-01-28 19:14:46 +08:00
JustSong	ea407f0054	feat: able to set completion ration now (close #968 )	2024-01-28 16:45:54 +08:00
Benny	26e2e646cb	feat: sync models with OpenAI (#971 ) * add new 0125 chat models and embedding-3 models * refine the step of manually deploying * add gpt-4-turbo-preview	2024-01-28 16:09:21 +08:00
yongman	4f214c48c6	fix: fix primary chat button (#951 ) Signed-off-by: yongman <yming0221@gmail.com>	2024-01-21 23:27:34 +08:00
JustSong	2d760d4a01	refactor: refactor relay part (#957 ) * refactor: refactor relay part * refactor: refactor config part	2024-01-21 23:21:42 +08:00
Buer	e2ed0399f0	fix: fix aff not effective (#937 )	2024-01-20 12:38:06 +08:00
JustSong	eed9f5fdf0	refactor: refactor relay part (#935 )	2024-01-14 19:21:03 +08:00
JustSong	f2c51a494c	feat: able to login via email (close #921 )	2024-01-14 14:08:39 +08:00
Calcium-Ion	8a4d6f3327	fix: remove useless wrong index (#916 ) * add sqlite busy_timeout=3000 * chore: update impl * fix: fix JSON tag in Log struct * fix: 修复高并发下，高额度用户使用低额度令牌没有预扣费而导致令牌大额欠费 * Revert "fix: 修复高并发下，高额度用户使用低额度令牌没有预扣费而导致令牌大额欠费" This reverts commit `f0ffe14437`. * fix: remove wrong index --------- Co-authored-by: JustSong <songquanpeng@foxmail.com>	2024-01-14 13:48:16 +08:00
Buer	cf4e33cb12	fix: fix bugs with theme berry (#931 ) * fix: home page & logo style issue * improve: Enhanced user experience by improving the channel selection box * fix: key cannot be activated after expiration	2024-01-14 13:22:31 +08:00
JustSong	5d60305570	docs: update readme (close #930 )	2024-01-14 13:00:59 +08:00