feat: 记录请求的token用量

feat: 解决渠道密钥长度限制问题
fix: 修复保存telegram设置后会将telegram登陆禁用的问题
2026-03-31 18:49:50 +00:00 · 2024-03-04 14:58:30 +08:00 · 2024-03-04 14:55:26 +08:00 · 2024-03-03 23:41:00 +08:00 · 2024-03-03 22:28:07 +08:00 · 2024-03-03 22:08:03 +08:00
133 changed files with 5225 additions and 3660 deletions
--- a/.github/workflows/docker-image-amd64-en.yml
+++ b/.github/workflows/docker-image-amd64-en.yml
@@ -1,9 +1,10 @@
-name: Publish Docker image (amd64, English)
+name: Publish Docker image (amd64)

 on:
  push:
    tags:
      - '*'
+      - '!*-alpha*'
  workflow_dispatch:
    inputs:
      name:
@@ -24,21 +25,26 @@ jobs:
        run: |
          git describe --tags > VERSION 

-      - name: Translate
-        run: |
-          python ./i18n/translate.py --repository_path . --json_file_path ./i18n/en.json
      - name: Log in to Docker Hub
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

+      - name: Log in to the Container registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
      - name: Extract metadata (tags, labels) for Docker
        id: meta
        uses: docker/metadata-action@v4
        with:
          images: |
-            justsong/one-api-en
+            calciumion/new-api
+            ghcr.io/${{ github.repository }}

      - name: Build and push Docker images
        uses: docker/build-push-action@v3
--- a/.github/workflows/docker-image-arm64.yml
+++ b/.github/workflows/docker-image-arm64.yml
@@ -49,7 +49,7 @@ jobs:
        uses: docker/metadata-action@v4
        with:
          images: |
-            justsong/one-api
+            calciumion/new-api
            ghcr.io/${{ github.repository }}

      - name: Build and push Docker images
--- a/Midjourney.md
+++ b/Midjourney.md
@@ -1,254 +1,291 @@
 # Midjourney Proxy API文档

-
 **简介**:Midjourney Proxy API文档

+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）

-**HOST**:https://api.nekoedu.com  
+```json
+{
+  "gpt-4-gizmo-*": 0.1,
+  "mj_imagine": 0.1,
+  "mj_variation": 0.1,
+  "mj_reroll": 0.1,
+  "mj_blend": 0.1,
+  "mj_describe": 0.05,
+  "mj_upscale": 0.05
+}
+```

+## 渠道设置

-**Version**:v2.3.5
+### 对接 midjourney-proxy
+1. 部署Midjourney-Proxy，并配置好midjourney账号等（强烈建议设置密钥），[项目地址](https://github.com/novicezk/midjourney-proxy)
+2. 在渠道管理中添加渠道，渠道类型选择Midjourney Proxy，模型选择midjourney
+3. 地址填写midjourney-proxy部署的地址，例如：http://localhost:8080
+4. 密钥填写midjourney-proxy的密钥，如果没有设置密钥，可以随便填

+### 对接上游new api
+1. 在渠道管理中添加渠道，渠道类型选择Midjourney Proxy，模型选择midjourney
+2. 地址填写上游new api的地址，例如：http://localhost:8080
+3. 密钥填写上游new api的密钥

-[TOC]
-
-
-
-
-
-
-# 任务提交
-
-
-## 绘图变化
+## 任务提交

+### 绘图变化

 **接口地址**:`/mj/submit/change`

-
 **请求方式**:`POST`

-
 **请求数据类型**:`application/json`

-
 **响应数据类型**:`*/*`

-
 **接口描述**:

-
 **请求示例**:

-
 ```javascript
 {
-  "action": "UPSCALE",
-  "index": 1,
-  "notifyHook": "",
-  "state": "",
-  "taskId": "1320098173412546"
+    "action"
+:
+    "UPSCALE",
+        "index"
+:
+    1,
+        "notifyHook"
+:
+    "",
+        "state"
+:
+    "",
+        "taskId"
+:
+    "1320098173412546"
 }
 ```

-
 **请求参数**:

-
-| 参数名称 | 参数说明 | 请求类型    | 是否必须 | 数据类型 | schema |
-| -------- | -------- | ----- | -------- | -------- | ------ |
-|changeDTO|changeDTO|body|true|变化任务提交参数|变化任务提交参数|
-|&emsp;&emsp;action|UPSCALE(放大); VARIATION(变换); REROLL(重新生成),可用值:UPSCALE,VARIATION,REROLL||true|string||
-|&emsp;&emsp;index|序号(1~4), action为UPSCALE,VARIATION时必传||false|integer(int32)||
-|&emsp;&emsp;notifyHook|回调地址, 为空时使用全局notifyHook||false|string||
-|&emsp;&emsp;state|自定义参数||false|string||
-|&emsp;&emsp;taskId|任务ID||true|string||
-
+| 参数名称                   | 参数说明                                                                  | 请求类型 | 是否必须  | 数据类型           | schema   |
+|------------------------|-----------------------------------------------------------------------|------|-------|----------------|----------|
+| changeDTO              | changeDTO                                                             | body | true  | 变化任务提交参数       | 变化任务提交参数 |
+| &emsp;&emsp;action     | UPSCALE(放大); VARIATION(变换); REROLL(重新生成),可用值:UPSCALE,VARIATION,REROLL |      | true  | string         |          |
+| &emsp;&emsp;index      | 序号(1~4), action为UPSCALE,VARIATION时必传                                  |      | false | integer(int32) |          |
+| &emsp;&emsp;notifyHook | 回调地址, 为空时使用全局notifyHook                                               |      | false | string         |          |
+| &emsp;&emsp;state      | 自定义参数                                                                 |      | false | string         |          |
+| &emsp;&emsp;taskId     | 任务ID                                                                  |      | true  | string         |          |

 **响应状态**:

-
-| 状态码 | 说明 | schema |
-| -------- | -------- | ----- | 
-|200|OK|提交结果|
-|201|Created||
-|401|Unauthorized||
-|403|Forbidden||
-|404|Not Found||
-
+| 状态码 | 说明           | schema |
+|-----|--------------|--------| 
+| 200 | OK           | 提交结果   |
+| 201 | Created      |        |
+| 401 | Unauthorized |        |
+| 403 | Forbidden    |        |
+| 404 | Not Found    |        |

 **响应参数**:

-
-| 参数名称 | 参数说明 | 类型 | schema |
-| -------- | -------- | ----- |----- | 
-|code|状态码: 1(提交成功), 21(已存在), 22(排队中), other(错误)|integer(int32)|integer(int32)|
-|description|描述|string||
-|properties|扩展字段|object||
-|result|任务ID|string||
-
+| 参数名称        | 参数说明                                      | 类型             | schema         |
+|-------------|-------------------------------------------|----------------|----------------| 
+| code        | 状态码: 1(提交成功), 21(已存在), 22(排队中), other(错误) | integer(int32) | integer(int32) |
+| description | 描述                                        | string         |                |
+| properties  | 扩展字段                                      | object         |                |
+| result      | 任务ID                                      | string         |                |

 **响应示例**:
+
 ```javascript
 {
-	"code": 1,
-	"description": "提交成功",
-	"properties": {},
-	"result": 1320098173412546
+    "code"
+:
+    1,
+        "description"
+:
+    "提交成功",
+        "properties"
+:
+    {
+    }
+,
+    "result"
+:
+    1320098173412546
 }
 ```

-## 提交Imagine任务
-
+### 提交Imagine任务

 **接口地址**:`/mj/submit/imagine`

-
 **请求方式**:`POST`

-
 **请求数据类型**:`application/json`

-
 **响应数据类型**:`*/*`

-
 **接口描述**:

-
 **请求示例**:

-
 ```javascript
 {
-  "base64": "",
-  "notifyHook": "",
-  "prompt": "Cat",
-  "state": ""
+    "base64"
+:
+    "",
+        "notifyHook"
+:
+    "",
+        "prompt"
+:
+    "Cat",
+        "state"
+:
+    ""
 }
 ```

-
 **请求参数**:

-
-| 参数名称 | 参数说明 | 请求类型    | 是否必须 | 数据类型 | schema |
-| -------- | -------- | ----- | -------- | -------- | ------ |
-|imagineDTO|imagineDTO|body|true|Imagine提交参数|Imagine提交参数|
-|&emsp;&emsp;base64|垫图base64||false|string||
-|&emsp;&emsp;notifyHook|回调地址, 为空时使用全局notifyHook||false|string||
-|&emsp;&emsp;prompt|提示词||true|string||
-|&emsp;&emsp;state|自定义参数||false|string||
-
+| 参数名称                   | 参数说明                    | 请求类型 | 是否必须  | 数据类型        | schema      |
+|------------------------|-------------------------|------|-------|-------------|-------------|
+| imagineDTO             | imagineDTO              | body | true  | Imagine提交参数 | Imagine提交参数 |
+| &emsp;&emsp;base64     | 垫图base64                |      | false | string      |             |
+| &emsp;&emsp;notifyHook | 回调地址, 为空时使用全局notifyHook |      | false | string      |             |
+| &emsp;&emsp;prompt     | 提示词                     |      | true  | string      |             |
+| &emsp;&emsp;state      | 自定义参数                   |      | false | string      |             |

 **响应状态**:

-
-| 状态码 | 说明 | schema |
-| -------- | -------- | ----- | 
-|200|OK|提交结果|
-|201|Created||
-|401|Unauthorized||
-|403|Forbidden||
-|404|Not Found||
-
+| 状态码 | 说明           | schema |
+|-----|--------------|--------| 
+| 200 | OK           | 提交结果   |
+| 201 | Created      |        |
+| 401 | Unauthorized |        |
+| 403 | Forbidden    |        |
+| 404 | Not Found    |        |

 **响应参数**:

-
-| 参数名称 | 参数说明 | 类型 | schema |
-| -------- | -------- | ----- |----- | 
-|code|状态码: 1(提交成功), 21(已存在), 22(排队中), other(错误)|integer(int32)|integer(int32)|
-|description|描述|string||
-|properties|扩展字段|object||
-|result|任务ID|string||
-
+| 参数名称        | 参数说明                                      | 类型             | schema         |
+|-------------|-------------------------------------------|----------------|----------------| 
+| code        | 状态码: 1(提交成功), 21(已存在), 22(排队中), other(错误) | integer(int32) | integer(int32) |
+| description | 描述                                        | string         |                |
+| properties  | 扩展字段                                      | object         |                |
+| result      | 任务ID                                      | string         |                |

 **响应示例**:
+
 ```javascript
 {
-	"code": 1,
-	"description": "提交成功",
-	"properties": {},
-	"result": 1320098173412546
+    "code"
+:
+    1,
+        "description"
+:
+    "提交成功",
+        "properties"
+:
+    {
+    }
+,
+    "result"
+:
+    1320098173412546
 }
 ```

+## 任务查询

-# 任务查询
-
-## 指定ID获取任务
-
+### 指定ID获取任务

 **接口地址**:`/mj/task/{id}/fetch`

-
 **请求方式**:`GET`

-
 **请求数据类型**:`application/x-www-form-urlencoded`

-
 **响应数据类型**:`*/*`

-
 **接口描述**:

-
 **请求参数**:

-
-| 参数名称 | 参数说明 | 请求类型    | 是否必须 | 数据类型 | schema |
-| -------- | -------- | ----- | -------- | -------- | ------ |
-|id|任务ID|path|false|string||
-
+| 参数名称 | 参数说明 | 请求类型 | 是否必须  | 数据类型   | schema |
+|------|------|------|-------|--------|--------|
+| id   | 任务ID | path | false | string |        |

 **响应状态**:

-
-| 状态码 | 说明 | schema |
-| -------- | -------- | ----- | 
-|200|OK|任务|
-|401|Unauthorized||
-|403|Forbidden||
-|404|Not Found||
-
+| 状态码 | 说明           | schema |
+|-----|--------------|--------| 
+| 200 | OK           | 任务     |
+| 401 | Unauthorized |        |
+| 403 | Forbidden    |        |
+| 404 | Not Found    |        |

 **响应参数**:

-
-| 参数名称 | 参数说明 | 类型 | schema |
-| -------- | -------- | ----- |----- | 
-|action|可用值:IMAGINE,UPSCALE,VARIATION,REROLL,DESCRIBE,BLEND|string||
-|description|任务描述|string||
-|failReason|失败原因|string||
-|finishTime|结束时间|integer(int64)|integer(int64)|
-|id|任务ID|string||
-|imageUrl|图片url|string||
-|progress|任务进度|string||
-|prompt|提示词|string||
-|promptEn|提示词-英文|string||
-|startTime|开始执行时间|integer(int64)|integer(int64)|
-|state|自定义参数|string||
-|status|任务状态,可用值:NOT_START,SUBMITTED,IN_PROGRESS,FAILURE,SUCCESS|string||
-|submitTime|提交时间|integer(int64)|integer(int64)|
-
+| 参数名称        | 参数说明                                                     | 类型             | schema         |
+|-------------|----------------------------------------------------------|----------------|----------------| 
+| action      | 可用值:IMAGINE,UPSCALE,VARIATION,REROLL,DESCRIBE,BLEND      | string         |                |
+| description | 任务描述                                                     | string         |                |
+| failReason  | 失败原因                                                     | string         |                |
+| finishTime  | 结束时间                                                     | integer(int64) | integer(int64) |
+| id          | 任务ID                                                     | string         |                |
+| imageUrl    | 图片url                                                    | string         |                |
+| progress    | 任务进度                                                     | string         |                |
+| prompt      | 提示词                                                      | string         |                |
+| promptEn    | 提示词-英文                                                   | string         |                |
+| startTime   | 开始执行时间                                                   | integer(int64) | integer(int64) |
+| state       | 自定义参数                                                    | string         |                |
+| status      | 任务状态,可用值:NOT_START,SUBMITTED,IN_PROGRESS,FAILURE,SUCCESS | string         |                |
+| submitTime  | 提交时间                                                     | integer(int64) | integer(int64) |

 **响应示例**:
+
 ```javascript
 {
-	"action": "",
-	"description": "",
-	"failReason": "",
-	"finishTime": 0,
-	"id": "",
-	"imageUrl": "",
-	"progress": "",
-	"prompt": "",
-	"promptEn": "",
-	"startTime": 0,
-	"state": "",
-	"status": "",
-	"submitTime": 0
+    "action"
+:
+    "",
+        "description"
+:
+    "",
+        "failReason"
+:
+    "",
+        "finishTime"
+:
+    0,
+        "id"
+:
+    "",
+        "imageUrl"
+:
+    "",
+        "progress"
+:
+    "",
+        "prompt"
+:
+    "",
+        "promptEn"
+:
+    "",
+        "startTime"
+:
+    0,
+        "state"
+:
+    "",
+        "status"
+:
+    "",
+        "submitTime"
+:
+    0
 }
 ```
--- a/README.md
+++ b/README.md
@@ -14,29 +14,37 @@
 > 最新版Docker镜像 calciumion/new-api:latest  
 > 更新指令 docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR

-## 此分叉版本的主要变更
+## 主要变更
+此分叉版本的主要变更如下：
+
 1. 全新的UI界面（部分界面还待更新）
-2. 添加[Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)接口的支持：
-    + [x] /mj/submit/imagine
-    + [x] /mj/submit/change
-    + [x] /mj/submit/blend
-    + [x] /mj/submit/describe
-    + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
-    + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
+2. 添加[Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)接口的支持
+   + [x] /mj/submit/imagine
+   + [x] /mj/submit/change
+   + [x] /mj/submit/blend
+   + [x] /mj/submit/describe
+   + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
+   + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
+   + [x] /task/list-by-condition
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
-    + [x] 易支付
+   + [x] 易支付
 4. 支持用key查询使用额度:
-    + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用情况，方便二次分销
+   + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用
 5. 渠道显示已使用额度，支持指定组织访问
 6. 分页支持选择每页显示数量
-7. 支持 gpt-4-1106-vision-preview，dall-e-3，tts-1
-8. 支持第三方模型 **gps** （gpt-4-gizmo-*），在渠道中添加自定义模型gpt-4-gizmo-*即可
-9. 兼容原版One API的数据库，可直接使用原版数据库（one-api.db）
-10. 支持模型按次数收费，可在 系统设置-运营设置 中设置
-11. 支持gemini-pro，gemini-pro-vision模型
-12. 支持渠道**加权随机**
-13. 数据看板
-14. 可设置令牌能调用的模型
+7. 兼容原版One API的数据库，可直接使用原版数据库（one-api.db）
+8. 支持模型按次数收费，可在 系统设置-运营设置 中设置
+9. 支持渠道**加权随机**
+10. 数据看板
+11. 可设置令牌能调用的模型
+12. 支持Telegram授权登录
+
+## 模型支持
+此版本额外支持以下模型：
+1. 第三方模型 **gps** （gpt-4-gizmo-*）
+2. 智谱glm-4v，glm-4v识图
+
+您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。

 ## 部署
 ### 基于 Docker 进行部署
@@ -47,6 +55,18 @@ docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -
 # 例如：
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
 ```
+### 使用宝塔面板Docker功能部署
+```shell
+# 使用 SQLite 的部署命令：
+docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
+# 使用 MySQL 的部署命令，在上面的基础上添加 `-e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"`，请自行修改数据库连接参数。
+# 例如：
+# 注意：数据库要开启远程访问，并且只允许服务器IP访问
+docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(宝塔的服务器地址:宝塔数据库端口)/宝塔数据库名称" -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
+# 注意：数据库要开启远程访问，并且只允许服务器IP访问
+```
+## Midjourney接口设置文档
+[对接文档](Midjourney.md)

 ## 交流群
 <img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="300">
--- a/common/constants.go
+++ b/common/constants.go
@@ -9,24 +9,32 @@ import (
 	"github.com/google/uuid"
 )

+// Pay Settings
+
+var PayAddress = ""
+var CustomCallbackAddress = ""
+var EpayId = ""
+var EpayKey = ""
+var Price = 7.3
+var MinTopUp = 1
+
 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 = "New API"
 var ServerAddress = "http://localhost:3000"
-var PayAddress = ""
-var EpayId = ""
-var EpayKey = ""
-var Price = 7.3
 var Footer = ""
 var Logo = ""
 var TopUpLink = ""
 var ChatLink = ""
+var ChatLink2 = ""
 var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 var DrawingEnabled = true
 var DataExportEnabled = true
-var DataExportInterval = 5 // unit: minute
+var DataExportInterval = 5         // unit: minute
+var DataExportDefaultTime = "hour" // unit: minute
+var DefaultCollapseSidebar = false // default value of collapse sidebar

 // Any options with "Secret", "Token" in its key won't be return by GetOptions

@@ -43,6 +51,7 @@ var PasswordRegisterEnabled = true
 var EmailVerificationEnabled = false
 var GitHubOAuthEnabled = false
 var WeChatAuthEnabled = false
+var TelegramOAuthEnabled = false
 var TurnstileCheckEnabled = false
 var RegisterEnabled = true

@@ -80,11 +89,15 @@ var WeChatAccountQRCodeImageURL = ""
 var TurnstileSiteKey = ""
 var TurnstileSecretKey = ""

+var TelegramBotToken = ""
+var TelegramBotName = ""
+
 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

@@ -104,6 +117,8 @@ var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)

 var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second

+var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )
@@ -194,6 +209,8 @@ const (
 	ChannelTypeFastGPT        = 22
 	ChannelTypeTencent        = 23
 	ChannelTypeGemini         = 24
+	ChannelTypeMoonshot       = 25
+	ChannelTypeZhipu_v4       = 26
 )

 var ChannelBaseURLs = []string{
@@ -222,4 +239,6 @@ var ChannelBaseURLs = []string{
 	"https://fastgpt.run/api/openapi",   // 22
 	"https://hunyuan.cloud.tencent.com", //23
 	"",                                  //24
+	"https://api.moonshot.cn",           //25
+	"https://open.bigmodel.cn",          //26
 }
--- a/common/go-channel.go
+++ b/common/go-channel.go
@@ -0,0 +1,32 @@
+package common
+
+import (
+	"fmt"
+	"runtime/debug"
+)
+
+func SafeGoroutine(f func()) {
+	go func() {
+		defer func() {
+			if r := recover(); r != nil {
+				SysError(fmt.Sprintf("child goroutine panic occured: error: %v, stack: %s", r, string(debug.Stack())))
+			}
+		}()
+		f()
+	}()
+}
+
+func SafeSend(ch chan bool, value bool) (closed bool) {
+	defer func() {
+		// Recover from panic if one occured. A panic would mean the channel was closed.
+		if recover() != nil {
+			closed = true
+		}
+	}()
+
+	// This will panic if the channel is closed.
+	ch <- value
+
+	// If the code reaches here, then the channel was not closed.
+	return false
+}
--- a/common/image.go
+++ b/common/image.go
@@ -68,17 +68,29 @@ func DecodeUrlImageData(imageUrl string) (image.Config, string, error) {
 		SysLog(fmt.Sprintf("fail to get image from url: %s", err.Error()))
 		return image.Config{}, "", err
 	}
+	defer response.Body.Close()

-	// 限制读取的字节数，防止下载整个图片
-	limitReader := io.LimitReader(response.Body, 1024*20)
-	//data, err := io.ReadAll(limitReader)
-	//if err != nil {
-	//	log.Fatal(err)
-	//}
-	//log.Printf("%x", data)
-	config, format, err := getImageConfig(limitReader)
-	response.Body.Close()
-	return config, format, err
+	var readData []byte
+	for _, limit := range []int64{1024 * 8, 1024 * 24, 1024 * 64} {
+		SysLog(fmt.Sprintf("try to decode image config with limit: %d", limit))
+
+		// 从response.Body读取更多的数据直到达到当前的限制
+		additionalData := make([]byte, limit-int64(len(readData)))
+		n, _ := io.ReadFull(response.Body, additionalData)
+		readData = append(readData, additionalData[:n]...)
+
+		// 使用io.MultiReader组合已经读取的数据和response.Body
+		limitReader := io.MultiReader(bytes.NewReader(readData), response.Body)
+
+		var config image.Config
+		var format string
+		config, format, err = getImageConfig(limitReader)
+		if err == nil {
+			return config, format, nil
+		}
+	}
+
+	return image.Config{}, "", err // 返回最后一个错误
 }

 func getImageConfig(reader io.Reader) (image.Config, string, error) {
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -23,6 +23,8 @@ var ModelRatio = map[string]float64{
 	"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-4-1106-vision-preview": 5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":             0.75, // $0.0015 / 1K tokens
@@ -32,8 +34,9 @@ var ModelRatio = map[string]float64{
 	"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
-	"babbage-002":               0.2,  // $0.0004 / 1K tokens
-	"davinci-002":               1,    // $0.002 / 1K tokens
+	"gpt-3.5-turbo-0125":        0.25,
+	"babbage-002":               0.2, // $0.0004 / 1K tokens
+	"davinci-002":               1,   // $0.002 / 1K tokens
 	"text-ada-001":              0.2,
 	"text-babbage-001":          0.25,
 	"text-curie-001":            1,
@@ -50,6 +53,8 @@ var ModelRatio = map[string]float64{
 	"curie":                     10,
 	"babbage":                   10,
 	"ada":                       10,
+	"text-embedding-3-small":    0.01,
+	"text-embedding-3-large":    0.065,
 	"text-embedding-ada-002":    0.05,
 	"text-search-ada-doc-001":   10,
 	"text-moderation-stable":    0.1,
@@ -69,10 +74,16 @@ var ModelRatio = map[string]float64{
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
+	"glm-4":                     7.143,  // ￥0.1 / 1k tokens
+	"glm-4v":                    7.143,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":               0.3572,
 	"qwen-turbo":                0.8572, // ￥0.012 / 1k tokens
 	"qwen-plus":                 10,     // ￥0.14 / 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
@@ -103,13 +114,15 @@ func UpdateModelPriceByJSONString(jsonStr string) error {
 	return json.Unmarshal([]byte(jsonStr), &ModelPrice)
 }

-func GetModelPrice(name string) float64 {
+func GetModelPrice(name string, printErr bool) float64 {
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
 	price, ok := ModelPrice[name]
 	if !ok {
-		SysError("model price not found: " + name)
+		if printErr {
+			SysError("model price not found: " + name)
+		}
 		return -1
 	}
 	return price
@@ -142,6 +155,9 @@ func GetModelRatio(name string) float64 {

 func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-3.5") {
+		if strings.HasSuffix(name, "0125") {
+			return 3
+		}
 		if strings.HasSuffix(name, "1106") {
 			return 2
 		}
--- a/common/redis.go
+++ b/common/redis.go
@@ -57,12 +57,51 @@ func RedisGet(key string) (string, error) {
 	return RDB.Get(ctx, key).Result()
 }

+func RedisExpire(key string, expiration time.Duration) error {
+	ctx := context.Background()
+	return RDB.Expire(ctx, key, expiration).Err()
+}
+
+func RedisGetEx(key string, expiration time.Duration) (string, error) {
+	ctx := context.Background()
+	return RDB.GetSet(ctx, key, expiration).Result()
+}
+
 func RedisDel(key string) error {
 	ctx := context.Background()
 	return RDB.Del(ctx, key).Err()
 }

 func RedisDecrease(key string, value int64) error {
-	ctx := context.Background()
-	return RDB.DecrBy(ctx, key, value).Err()
+
+	// 检查键的剩余生存时间
+	ttlCmd := RDB.TTL(context.Background(), key)
+	ttl, err := ttlCmd.Result()
+	if err != nil {
+		// 失败则尝试直接减少
+		return RDB.DecrBy(context.Background(), key, value).Err()
+	}
+
+	// 如果剩余生存时间大于0，则进行减少操作
+	if ttl > 0 {
+		ctx := context.Background()
+		// 开始一个Redis事务
+		txn := RDB.TxPipeline()
+
+		// 减少余额
+		decrCmd := txn.DecrBy(ctx, key, value)
+		if err := decrCmd.Err(); err != nil {
+			return err // 如果减少失败，则直接返回错误
+		}
+
+		// 重新设置过期时间，使用原来的过期时间
+		txn.Expire(ctx, key, ttl)
+
+		// 执行事务
+		_, err = txn.Exec(ctx)
+		return err
+	} else {
+		_ = RedisDel(key)
+	}
+	return nil
 }
--- a/common/utils.go
+++ b/common/utils.go
@@ -202,6 +202,13 @@ func GetOrDefault(env string, defaultValue int) int {
 	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)
 }
@@ -223,7 +230,7 @@ func StringsContains(strs []string, str string) bool {
 	return false
 }

-// []byte only read, panic on append
+// StringToByteSlice []byte only read, panic on append
 func StringToByteSlice(s string) []byte {
 	tmp1 := (*[2]uintptr)(unsafe.Pointer(&s))
 	tmp2 := [3]uintptr{tmp1[0], tmp1[1], tmp1[1]}
--- a/controller/billing.go
+++ b/controller/billing.go
@@ -3,6 +3,7 @@ package controller
 import (
 	"github.com/gin-gonic/gin"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/model"
 )

@@ -27,7 +28,7 @@ func GetSubscription(c *gin.Context) {
 		expiredTime = 0
 	}
 	if err != nil {
-		openAIError := OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: err.Error(),
 			Type:    "upstream_error",
 		}
@@ -69,7 +70,7 @@ func GetUsage(c *gin.Context) {
 		quota, err = model.GetUserUsedQuota(userId)
 	}
 	if err != nil {
-		openAIError := OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: err.Error(),
 			Type:    "new_api_error",
 		}
--- a/controller/channel-billing.go
+++ b/controller/channel-billing.go
@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"one-api/service"
 	"strconv"
 	"time"

@@ -92,7 +93,7 @@ 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 := service.GetHttpClient().Do(req)
 	if err != nil {
 		return nil, err
 	}
@@ -310,7 +311,7 @@ func updateAllChannelsBalance() error {
 		} else {
 			// err is nil & balance <= 0 means quota is used up
 			if balance <= 0 {
-				disableChannel(channel.Id, channel.Name, "余额不足")
+				service.DisableChannel(channel.Id, channel.Name, "余额不足")
 			}
 		}
 		time.Sleep(common.RequestInterval)
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -5,9 +5,17 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"io"
 	"net/http"
+	"net/http/httptest"
+	"net/url"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/model"
+	"one-api/relay"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+	"one-api/service"
 	"strconv"
 	"sync"
 	"time"
@@ -15,81 +23,77 @@ 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.ChannelTypeAnthropic:
-		fallthrough
-	case common.ChannelTypeBaidu:
-		fallthrough
-	case common.ChannelTypeZhipu:
-		fallthrough
-	case common.ChannelTypeAli:
-		fallthrough
-	case common.ChannelType360:
-		fallthrough
-	case common.ChannelTypeGemini:
-		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"
+func testChannel(channel *model.Channel, testModel string) (err error, openaiErr *dto.OpenAIError) {
+	common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
+	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),
 	}
-	requestURL := common.ChannelBaseURLs[channel.Type]
-	if channel.Type == common.ChannelTypeAzure {
-		requestURL = fmt.Sprintf("%s/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", channel.GetBaseURL(), request.Model)
-	} else {
-		if channel.GetBaseURL() != "" {
-			requestURL = channel.GetBaseURL()
-		}
-		requestURL += "/v1/chat/completions"
+	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 := relaycommon.GenRelayInfo(c)
+	apiType := constant.ChannelType2APIType(channel.Type)
+	adaptor := relay.GetAdaptor(apiType)
+	if adaptor == nil {
+		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
 	}
+	if testModel == "" {
+		testModel = adaptor.GetModelList()[0]
+	}
+	request := buildTestRequest()

-	jsonData, err := json.Marshal(request)
+	adaptor.Init(meta, *request)
+
+	request.Model = testModel
+	meta.UpstreamModelName = testModel
+	convertedRequest, err := adaptor.ConvertRequest(c, constant.RelayModeChatCompletions, request)
 	if err != nil {
 		return err, nil
 	}
-	req, err := http.NewRequest("POST", requestURL, bytes.NewBuffer(jsonData))
+	jsonData, err := json.Marshal(convertedRequest)
 	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)
+	requestBody := bytes.NewBuffer(jsonData)
+	c.Request.Body = io.NopCloser(requestBody)
+	resp, err := adaptor.DoRequest(c, meta, requestBody)
 	if err != nil {
 		return err, nil
 	}
-	defer resp.Body.Close()
-	var response TextResponse
-	err = json.NewDecoder(resp.Body).Decode(&response)
+	if resp.StatusCode != http.StatusOK {
+		err := relaycommon.RelayErrorHandler(resp)
+		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.OpenAIError.Message), &err.OpenAIError
+	}
+	usage, respErr := adaptor.DoResponse(c, resp, meta)
+	if respErr != nil {
+		return fmt.Errorf("%s", respErr.OpenAIError.Message), &respErr.OpenAIError
+	}
+	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
 	}
-	if response.Usage.CompletionTokens == 0 {
-		return errors.New(fmt.Sprintf("type %s, code %v, message %s", response.Error.Type, response.Error.Code, response.Error.Message)), &response.Error
-	}
+	common.SysLog(fmt.Sprintf("testing channel #%d, response: \n%s", channel.Id, string(respBody)))
 	return nil, nil
 }

-func buildTestRequest() *ChatRequest {
-	testRequest := &ChatRequest{
+func buildTestRequest() *dto.GeneralOpenAIRequest {
+	testRequest := &dto.GeneralOpenAIRequest{
 		Model:     "", // this will be set later
 		MaxTokens: 1,
 	}
 	content, _ := json.Marshal("hi")
-	testMessage := Message{
+	testMessage := dto.Message{
 		Role:    "user",
 		Content: content,
 	}
@@ -114,9 +118,9 @@ func TestChannel(c *gin.Context) {
 		})
 		return
 	}
-	testRequest := buildTestRequest()
+	testModel := c.Query("model")
 	tik := time.Now()
-	err, _ = testChannel(channel, *testRequest)
+	err, _ = testChannel(channel, testModel)
 	tok := time.Now()
 	milliseconds := tok.Sub(tik).Milliseconds()
 	go channel.UpdateResponseTime(milliseconds)
@@ -140,20 +144,6 @@ func TestChannel(c *gin.Context) {
 var testAllChannelsLock sync.Mutex
 var testAllChannelsRunning bool = false

-// disable & notify
-func disableChannel(channelId int, channelName string, reason string) {
-	if common.RootUserEmail == "" {
-		common.RootUserEmail = model.GetRootUserEmail()
-	}
-	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled)
-	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
-	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
-	err := common.SendEmail(subject, common.RootUserEmail, content)
-	if err != nil {
-		common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
-	}
-}
-
 func testAllChannels(notify bool) error {
 	if common.RootUserEmail == "" {
 		common.RootUserEmail = model.GetRootUserEmail()
@@ -169,18 +159,15 @@ func testAllChannels(notify bool) error {
 	if err != nil {
 		return err
 	}
-	testRequest := buildTestRequest()
 	var disableThreshold = int64(common.ChannelDisableThreshold * 1000)
 	if disableThreshold == 0 {
 		disableThreshold = 10000000 // a impossible value
 	}
 	go func() {
 		for _, channel := range channels {
-			if channel.Status != common.ChannelStatusEnabled {
-				continue
-			}
+			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()

@@ -197,8 +184,11 @@ func testAllChannels(notify bool) error {
 			if channel.AutoBan != nil && *channel.AutoBan == 0 {
 				ban = false
 			}
-			if shouldDisableChannel(openaiErr, -1) && ban {
-				disableChannel(channel.Id, channel.Name, err.Error())
+			if isChannelEnabled && service.ShouldDisableChannel(openaiErr, -1) && ban {
+				service.DisableChannel(channel.Id, channel.Name, err.Error())
+			}
+			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr) {
+				service.EnableChannel(channel.Id, channel.Name)
 			}
 			channel.UpdateResponseTime(milliseconds)
 			time.Sleep(common.RequestInterval)
--- a/controller/channel.go
+++ b/controller/channel.go
@@ -35,11 +35,28 @@ func GetAllChannels(c *gin.Context) {
 	return
 }

+func FixChannelsAbilities(c *gin.Context) {
+	count, err := model.FixAbility()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    count,
+	})
+}
+
 func SearchChannels(c *gin.Context) {
 	keyword := c.Query("keyword")
 	group := c.Query("group")
+	modelKeyword := c.Query("model")
 	//idSort, _ := strconv.ParseBool(c.Query("id_sort"))
-	channels, err := model.SearchChannels(keyword, group)
+	channels, err := model.SearchChannels(keyword, group, modelKeyword)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
--- a/controller/midjourney.go
+++ b/controller/midjourney.go
@@ -11,6 +11,8 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	relay2 "one-api/relay"
+	"one-api/service"
 	"strconv"
 	"strings"
 	"time"
@@ -63,7 +65,7 @@ import (
 				req = req.WithContext(ctx)

 				req.Header.Set("Content-Type", "application/json")
-				//req.Header.Set("Authorization", "Bearer midjourney-proxy")
+				//req.Header.Set("ApiKey", "Bearer midjourney-proxy")
 				req.Header.Set("mj-api-secret", midjourneyChannel.Key)
 				resp, err := httpClient.Do(req)
 				if err != nil {
@@ -148,13 +150,7 @@ import (
 */

 func UpdateMidjourneyTaskBulk() {
-	//revocer
-	defer func() {
-		if err := recover(); err != nil {
-			log.Printf("UpdateMidjourneyTask panic: %v", err)
-		}
-	}()
-	imageModel := "midjourney"
+	//imageModel := "midjourney"
 	ctx := context.TODO()
 	for {
 		time.Sleep(time.Duration(15) * time.Second)
@@ -167,13 +163,27 @@ func UpdateMidjourneyTaskBulk() {
 		common.LogInfo(ctx, fmt.Sprintf("检测到未完成的任务数有: %v", len(tasks)))
 		taskChannelM := make(map[int][]string)
 		taskM := make(map[string]*model.Midjourney)
+		nullTaskIds := make([]int, 0)
 		for _, task := range tasks {
 			if task.MjId == "" {
+				// 统计失败的未完成任务
+				nullTaskIds = append(nullTaskIds, task.Id)
 				continue
 			}
 			taskM[task.MjId] = task
 			taskChannelM[task.ChannelId] = append(taskChannelM[task.ChannelId], task.MjId)
 		}
+		if len(nullTaskIds) > 0 {
+			err := model.MjBulkUpdateByTaskIds(nullTaskIds, map[string]any{
+				"status":   "FAILURE",
+				"progress": "100%",
+			})
+			if err != nil {
+				common.LogError(ctx, fmt.Sprintf("Fix null mj_id task error: %v", err))
+			} else {
+				common.LogInfo(ctx, fmt.Sprintf("Fix null mj_id task success: %v", nullTaskIds))
+			}
+		}
 		if len(taskChannelM) == 0 {
 			continue
 		}
@@ -213,7 +223,7 @@ func UpdateMidjourneyTaskBulk() {
 			req = req.WithContext(ctx)
 			req.Header.Set("Content-Type", "application/json")
 			req.Header.Set("mj-api-secret", midjourneyChannel.Key)
-			resp, err := httpClient.Do(req)
+			resp, err := service.GetHttpClient().Do(req)
 			if err != nil {
 				common.LogError(ctx, fmt.Sprintf("Get Task Do req error: %v", err))
 				continue
@@ -223,10 +233,10 @@ func UpdateMidjourneyTaskBulk() {
 				common.LogError(ctx, fmt.Sprintf("Get Task parse body error: %v", err))
 				continue
 			}
-			var responseItems []Midjourney
+			var responseItems []relay2.Midjourney
 			err = json.Unmarshal(responseBody, &responseItems)
 			if err != nil {
-				common.LogError(ctx, fmt.Sprintf("Get Task parse body error2: %v", err))
+				common.LogError(ctx, fmt.Sprintf("Get Task parse body error2: %v, body: %s", err, string(responseBody)))
 				continue
 			}
 			resp.Body.Close()
@@ -256,10 +266,7 @@ func UpdateMidjourneyTaskBulk() {
 					if err != nil {
 						common.LogError(ctx, "error update user quota cache: "+err.Error())
 					} else {
-						modelRatio := common.GetModelRatio(imageModel)
-						groupRatio := common.GetGroupRatio("default")
-						ratio := modelRatio * groupRatio
-						quota := int(ratio * 1 * 1000)
+						quota := task.Quota
 						if quota != 0 {
 							err = model.IncreaseUserQuota(task.UserId, quota)
 							if err != nil {
@@ -279,7 +286,7 @@ func UpdateMidjourneyTaskBulk() {
 	}
 }

-func checkMjTaskNeedUpdate(oldTask *model.Midjourney, newTask Midjourney) bool {
+func checkMjTaskNeedUpdate(oldTask *model.Midjourney, newTask relay2.Midjourney) bool {
 	if oldTask.Code != 1 {
 		return true
 	}
--- a/controller/misc.go
+++ b/controller/misc.go
@@ -16,26 +16,33 @@ func GetStatus(c *gin.Context) {
 		"success": true,
 		"message": "",
 		"data": gin.H{
-			"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,
-			"price":               common.Price,
-			"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,
-			"enable_batch_update": common.BatchUpdateEnabled,
-			"enable_drawing":      common.DrawingEnabled,
-			"enable_data_export":  common.DataExportEnabled,
+			"start_time":               common.StartTime,
+			"email_verification":       common.EmailVerificationEnabled,
+			"github_oauth":             common.GitHubOAuthEnabled,
+			"github_client_id":         common.GitHubClientId,
+			"telegram_oauth":           common.TelegramOAuthEnabled,
+			"telegram_bot_name":        common.TelegramBotName,
+			"system_name":              common.SystemName,
+			"logo":                     common.Logo,
+			"footer_html":              common.Footer,
+			"wechat_qrcode":            common.WeChatAccountQRCodeImageURL,
+			"wechat_login":             common.WeChatAuthEnabled,
+			"server_address":           common.ServerAddress,
+			"price":                    common.Price,
+			"min_topup":                common.MinTopUp,
+			"turnstile_check":          common.TurnstileCheckEnabled,
+			"turnstile_site_key":       common.TurnstileSiteKey,
+			"top_up_link":              common.TopUpLink,
+			"chat_link":                common.ChatLink,
+			"chat_link2":               common.ChatLink2,
+			"quota_per_unit":           common.QuotaPerUnit,
+			"display_in_currency":      common.DisplayInCurrencyEnabled,
+			"enable_batch_update":      common.BatchUpdateEnabled,
+			"enable_drawing":           common.DrawingEnabled,
+			"enable_data_export":       common.DataExportEnabled,
+			"data_export_default_time": common.DataExportDefaultTime,
+			"default_collapse_sidebar": common.DefaultCollapseSidebar,
+			"enable_online_topup":      common.PayAddress != "" && common.EpayId != "" && common.EpayKey != "",
 		},
 	})
 	return
--- a/controller/model.go
+++ b/controller/model.go
@@ -2,8 +2,14 @@ package controller

 import (
 	"fmt"
-
 	"github.com/gin-gonic/gin"
+	"net/http"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay"
+	"one-api/relay/channel/ai360"
+	"one-api/relay/channel/moonshot"
+	"one-api/relay/constant"
 )

 // https://platform.openai.com/docs/api-reference/models/list
@@ -53,529 +59,46 @@ func init() {
 		IsBlocking:         false,
 	})
 	// https://platform.openai.com/docs/models/model-endpoint-compatibility
-	openAIModels = []OpenAIModels{
-		{
-			Id:         "midjourney",
+	for i := 0; i < constant.APITypeDummy; i++ {
+		if i == constant.APITypeAIProxyLibrary {
+			continue
+		}
+		adaptor := relay.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:    "Midjourney",
-			Permission: permission,
-			Root:       "midjourney",
-			Parent:     nil,
-		},
-		{
-			Id:         "dall-e-2",
-			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:         "gpt-4-1106-vision-preview",
-			Object:     "model",
-			Created:    1699593571,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "gpt-4-1106-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:         "babbage-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "babbage-002",
-			Parent:     nil,
-		},
-		{
-			Id:         "davinci-002",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "openai",
-			Permission: permission,
-			Root:       "davinci-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:         "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",
-			Permission: permission,
-			Root:       "PaLM-2",
-			Parent:     nil,
-		},
-		{
-			Id:         "gemini-pro",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "google",
-			Permission: permission,
-			Root:       "gemini-pro",
-			Parent:     nil,
-		},
-		{
-			Id:         "gemini-pro-vision",
-			Object:     "model",
-			Created:    1677649963,
-			OwnedBy:    "google",
-			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:         "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 {
@@ -584,6 +107,29 @@ func init() {
 }

 func ListModels(c *gin.Context) {
+	userId := c.GetInt("id")
+	user, err := model.GetUserById(userId, true)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	models := model.GetGroupModels(user.Group)
+	userOpenAiModels := make([]OpenAIModels, 0)
+	for _, s := range models {
+		if _, ok := openAIModelsMap[s]; ok {
+			userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+		}
+	}
+	c.JSON(200, gin.H{
+		"object": "list",
+		"data":   userOpenAiModels,
+	})
+}
+
+func ChannelListModels(c *gin.Context) {
 	c.JSON(200, gin.H{
 		"object": "list",
 		"data":   openAIModels,
@@ -595,7 +141,7 @@ func RetrieveModel(c *gin.Context) {
 	if model, ok := openAIModelsMap[modelId]; ok {
 		c.JSON(200, model)
 	} else {
-		openAIError := OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),
 			Type:    "invalid_request_error",
 			Param:   "model",
--- a/controller/relay-aiproxy.go
+++ b/controller/relay-aiproxy.go
@@ -1,220 +0,0 @@
-package controller
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"github.com/gin-gonic/gin"
-	"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 {
-	query := ""
-	if len(request.Messages) != 0 {
-		query = string(request.Messages[len(request.Messages)-1].Content)
-	}
-	return &AIProxyLibraryRequest{
-		Model:  request.Model,
-		Stream: request.Stream,
-		Query:  query,
-	}
-}
-
-func aiProxyDocuments2Markdown(documents []AIProxyLibraryDocument) string {
-	if len(documents) == 0 {
-		return ""
-	}
-	content := "\n\n参考文档：\n"
-	for i, document := range documents {
-		content += fmt.Sprintf("%d. [%s](%s)\n", i+1, document.Title, document.URL)
-	}
-	return content
-}
-
-func responseAIProxyLibrary2OpenAI(response *AIProxyLibraryResponse) *OpenAITextResponse {
-	content, _ := json.Marshal(response.Answer + aiProxyDocuments2Markdown(response.Documents))
-	choice := OpenAITextResponseChoice{
-		Index: 0,
-		Message: Message{
-			Role:    "assistant",
-			Content: content,
-		},
-		FinishReason: "stop",
-	}
-	fullTextResponse := OpenAITextResponse{
-		Id:      common.GetUUID(),
-		Object:  "chat.completion",
-		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
-	}
-	return &fullTextResponse
-}
-
-func documentsAIProxyLibrary(documents []AIProxyLibraryDocument) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
-	choice.Delta.Content = aiProxyDocuments2Markdown(documents)
-	choice.FinishReason = &stopFinishReason
-	return &ChatCompletionsStreamResponse{
-		Id:      common.GetUUID(),
-		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
-		Model:   "",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
-	}
-}
-
-func streamResponseAIProxyLibrary2OpenAI(response *AIProxyLibraryStreamResponse) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
-	choice.Delta.Content = response.Content
-	return &ChatCompletionsStreamResponse{
-		Id:      common.GetUUID(),
-		Object:  "chat.completion.chunk",
-		Created: common.GetTimestamp(),
-		Model:   response.Model,
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
-	}
-}
-
-func aiProxyLibraryStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
-	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)
-	var documents []AIProxyLibraryDocument
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var AIProxyLibraryResponse AIProxyLibraryStreamResponse
-			err := json.Unmarshal([]byte(data), &AIProxyLibraryResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			if len(AIProxyLibraryResponse.Documents) != 0 {
-				documents = AIProxyLibraryResponse.Documents
-			}
-			response := streamResponseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
-			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:
-			response := documentsAIProxyLibrary(documents)
-			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)})
-			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), nil
-	}
-	return nil, &usage
-}
-
-func aiProxyLibraryHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var AIProxyLibraryResponse AIProxyLibraryResponse
-	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, &AIProxyLibraryResponse)
-	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-	if AIProxyLibraryResponse.ErrCode != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
-				Message: AIProxyLibraryResponse.Message,
-				Type:    strconv.Itoa(AIProxyLibraryResponse.ErrCode),
-				Code:    AIProxyLibraryResponse.ErrCode,
-			},
-			StatusCode: resp.StatusCode,
-		}, nil
-	}
-	fullTextResponse := responseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
-	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
-}
--- a/controller/relay-text.go
+++ b/controller/relay-text.go
@@ -1,735 +0,0 @@
-package controller
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"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")
-	startTime := time.Now()
-	var textRequest GeneralOpenAIRequest
-
-	err := common.UnmarshalBodyReusable(c, &textRequest)
-	if err != nil {
-		return errorWrapper(err, "bind_request_body_failed", 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
-			query := c.Request.URL.Query()
-			apiVersion := query.Get("api-version")
-			if apiVersion == "" {
-				apiVersion = c.GetString("api_version")
-			}
-			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")
-			fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/%s", baseURL, model_, task)
-		}
-	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)
-		}
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		fullRequestURL += "?key=" + apiKey
-	case APITypeGemini:
-		requestBaseURL := "https://generativelanguage.googleapis.com"
-		if baseURL != "" {
-			requestBaseURL = baseURL
-		}
-		version := "v1beta"
-		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)
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		fullRequestURL += "?key=" + apiKey
-		//log.Println(fullRequestURL)
-
-	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, err = countTokenMessages(textRequest.Messages, textRequest.Model)
-		if err != nil {
-			return errorWrapper(err, "count_token_messages_failed", http.StatusInternalServerError)
-		}
-	case RelayModeCompletions:
-		promptTokens = countTokenInput(textRequest.Prompt, textRequest.Model)
-	case RelayModeModerations:
-		promptTokens = countTokenInput(textRequest.Input, textRequest.Model)
-	}
-	modelPrice := common.GetModelPrice(textRequest.Model)
-	groupRatio := common.GetGroupRatio(group)
-
-	var preConsumedQuota int
-	var ratio float64
-	var modelRatio float64
-	if modelPrice == -1 {
-		preConsumedTokens := common.PreConsumedQuota
-		if textRequest.MaxTokens != 0 {
-			preConsumedTokens = promptTokens + int(textRequest.MaxTokens)
-		}
-		modelRatio = common.GetModelRatio(textRequest.Model)
-		ratio = modelRatio * groupRatio
-		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
-	} else {
-		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
-	}
-
-	userQuota, err := model.CacheGetUserQuota(userId)
-	if err != nil {
-		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
-	}
-	if userQuota < 0 || 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 {
-		userQuota, 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)
-		// 设置GetBody函数，该函数返回一个新的io.ReadCloser，该io.ReadCloser返回与原始请求体相同的数据
-		req.GetBody = func() (io.ReadCloser, error) {
-			return io.NopCloser(requestBody), nil
-		}
-		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 c.Request.Header.Get("OpenAI-Organization") != "" {
-					req.Header.Set("OpenAI-Organization", c.Request.Header.Get("OpenAI-Organization"))
-				}
-				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")
-			}
-		case APITypeTencent:
-			req.Header.Set("Authorization", apiKey)
-		case APITypeGemini:
-			req.Header.Set("Content-Type", "application/json")
-		default:
-			req.Header.Set("Authorization", "Bearer "+apiKey)
-		}
-		if apiType != APITypeGemini {
-			// 设置公共头部...
-			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.HeaderBar.Set("Connection", c.Request.HeaderBar.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, userQuota, -preConsumedQuota, 0, false)
-					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() {
-			promptTokens = textResponse.Usage.PromptTokens
-			completionTokens = textResponse.Usage.CompletionTokens
-
-			quota := 0
-			if modelPrice == -1 {
-				completionRatio := common.GetCompletionRatio(textRequest.Model)
-				quota = promptTokens + int(float64(completionTokens)*completionRatio)
-				quota = int(float64(quota) * ratio)
-				if ratio != 0 && quota <= 0 {
-					quota = 1
-				}
-			} else {
-				quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
-			}
-			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, userQuota, quotaDelta, preConsumedQuota, true)
-			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())
-			}
-
-			// record all the consume log even if quota is 0
-			useTimeSeconds := time.Now().Unix() - startTime.Unix()
-			var logContent string
-			if modelPrice == -1 {
-				logContent = fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，用时 %d秒", modelRatio, groupRatio, useTimeSeconds)
-			} else {
-				logContent = fmt.Sprintf("模型价格 %.2f，分组倍率 %.2f，用时 %d秒", modelPrice, groupRatio, useTimeSeconds)
-			}
-			logModel := textRequest.Model
-			if strings.HasPrefix(logModel, "gpt-4-gizmo") {
-				logModel = "gpt-4-gizmo-*"
-				logContent += fmt.Sprintf("，模型 %s", textRequest.Model)
-			}
-
-			model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, logModel, tokenName, quota, logContent, tokenId, userQuota)
-			model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-			model.UpdateChannelUsedQuota(channelId, quota)
-			//if quota != 0 {
-			//
-			//}
-		}()
-	}(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
@@ -1,307 +1,34 @@
 package controller

 import (
-	"encoding/json"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"log"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	"one-api/relay"
+	"one-api/relay/constant"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
 	"strconv"
 	"strings"
-
-	"github.com/gin-gonic/gin"
 )

-type Message struct {
-	Role    string          `json:"role"`
-	Content json.RawMessage `json:"content"`
-	Name    *string         `json:"name,omitempty"`
-}
-
-type MediaMessage struct {
-	Type     string `json:"type"`
-	Text     string `json:"text"`
-	ImageUrl any    `json:"image_url,omitempty"`
-}
-
-type MessageImageUrl struct {
-	Url    string `json:"url"`
-	Detail string `json:"detail"`
-}
-
-const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
-)
-
-func (m Message) ParseContent() []MediaMessage {
-	var contentList []MediaMessage
-	var stringContent string
-	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
-		contentList = append(contentList, MediaMessage{
-			Type: ContentTypeText,
-			Text: stringContent,
-		})
-		return contentList
-	}
-	var arrayContent []json.RawMessage
-	if err := json.Unmarshal(m.Content, &arrayContent); err == nil {
-		for _, contentItem := range arrayContent {
-			var contentMap map[string]any
-			if err := json.Unmarshal(contentItem, &contentMap); err != nil {
-				continue
-			}
-			switch contentMap["type"] {
-			case ContentTypeText:
-				if subStr, ok := contentMap["text"].(string); ok {
-					contentList = append(contentList, MediaMessage{
-						Type: ContentTypeText,
-						Text: subStr,
-					})
-				}
-			case ContentTypeImageURL:
-				if subObj, ok := contentMap["image_url"].(map[string]any); ok {
-					detail, ok := subObj["detail"]
-					if ok {
-						subObj["detail"] = detail.(string)
-					} else {
-						subObj["detail"] = "auto"
-					}
-					contentList = append(contentList, MediaMessage{
-						Type: ContentTypeImageURL,
-						ImageUrl: MessageImageUrl{
-							Url:    subObj["url"].(string),
-							Detail: subObj["detail"].(string),
-						},
-					})
-				}
-			}
-		}
-		return contentList
-	}
-
-	return nil
-}
-
-const (
-	RelayModeUnknown = iota
-	RelayModeChatCompletions
-	RelayModeCompletions
-	RelayModeEmbeddings
-	RelayModeModerations
-	RelayModeImagesGenerations
-	RelayModeEdits
-	RelayModeMidjourneyImagine
-	RelayModeMidjourneyDescribe
-	RelayModeMidjourneyBlend
-	RelayModeMidjourneyChange
-	RelayModeMidjourneySimpleChange
-	RelayModeMidjourneyNotify
-	RelayModeMidjourneyTaskFetch
-	RelayModeMidjourneyTaskFetchByCondition
-	RelayModeAudio
-)
-
-// https://platform.openai.com/docs/api-reference/chat
-
-type GeneralOpenAIRequest struct {
-	Model       string    `json:"model,omitempty"`
-	Messages    []Message `json:"messages,omitempty"`
-	Prompt      any       `json:"prompt,omitempty"`
-	Stream      bool      `json:"stream,omitempty"`
-	MaxTokens   uint      `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"`
-}
-
-func (r GeneralOpenAIRequest) ParseInput() []string {
-	if r.Input == nil {
-		return nil
-	}
-	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 AudioRequest struct {
-	Model string `json:"model"`
-	Voice string `json:"voice"`
-	Input string `json:"input"`
-}
-
-type ChatRequest struct {
-	Model     string    `json:"model"`
-	Messages  []Message `json:"messages"`
-	MaxTokens uint      `json:"max_tokens"`
-}
-
-type TextRequest struct {
-	Model     string    `json:"model"`
-	Messages  []Message `json:"messages"`
-	Prompt    string    `json:"prompt"`
-	MaxTokens uint      `json:"max_tokens"`
-	//Stream   bool      `json:"stream"`
-}
-
-type ImageRequest struct {
-	Model          string `json:"model"`
-	Prompt         string `json:"prompt"`
-	N              int    `json:"n"`
-	Size           string `json:"size"`
-	Quality        string `json:"quality,omitempty"`
-	ResponseFormat string `json:"response_format,omitempty"`
-	Style          string `json:"style,omitempty"`
-}
-
-type AudioResponse struct {
-	Text string `json:"text,omitempty"`
-}
-
-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"`
-	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"`
-		B64Json string `json:"b64_json"`
-	}
-}
-
-type ChatCompletionsStreamResponseChoice struct {
-	Delta struct {
-		Content string `json:"content"`
-	} `json:"delta"`
-	FinishReason *string `json:"finish_reason"`
-}
-
-type ChatCompletionsStreamResponse struct {
-	Id      string                                `json:"id"`
-	Object  string                                `json:"object"`
-	Created int64                                 `json:"created"`
-	Model   string                                `json:"model"`
-	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
-}
-
-type ChatCompletionsStreamResponseSimple struct {
-	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
-}
-
-type CompletionsStreamResponse struct {
-	Choices []struct {
-		Text         string `json:"text"`
-		FinishReason string `json:"finish_reason"`
-	} `json:"choices"`
-}
-
-type MidjourneyRequest struct {
-	Prompt      string   `json:"prompt"`
-	NotifyHook  string   `json:"notifyHook"`
-	Action      string   `json:"action"`
-	Index       int      `json:"index"`
-	State       string   `json:"state"`
-	TaskId      string   `json:"taskId"`
-	Base64Array []string `json:"base64Array"`
-	Content     string   `json:"content"`
-}
-
-type MidjourneyResponse struct {
-	Code        int         `json:"code"`
-	Description string      `json:"description"`
-	Properties  interface{} `json:"properties"`
-	Result      string      `json:"result"`
-}
-
 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") {
-		relayMode = RelayModeAudio
-	}
-	var err *OpenAIErrorWithStatusCode
+	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
+	var err *dto.OpenAIErrorWithStatusCode
 	switch relayMode {
-	case RelayModeImagesGenerations:
-		err = relayImageHelper(c, relayMode)
-	case RelayModeAudio:
-		err = relayAudioHelper(c, relayMode)
+	case relayconstant.RelayModeImagesGenerations:
+		err = relay.RelayImageHelper(c, relayMode)
+	case relayconstant.RelayModeAudioSpeech:
+		fallthrough
+	case relayconstant.RelayModeAudioTranslation:
+		fallthrough
+	case relayconstant.RelayModeAudioTranscription:
+		err = relay.AudioHelper(c, relayMode)
 	default:
-		err = relayTextHelper(c, relayMode)
+		err = relay.TextHelper(c)
 	}
 	if err != nil {
 		requestId := c.GetString(common.RequestIdKey)
@@ -311,7 +38,7 @@ func Relay(c *gin.Context) {
 			retryTimes = common.RetryTimes
 		}
 		if retryTimes > 0 {
-			c.Redirect(http.StatusTemporaryRedirect, fmt.Sprintf("%s?retry=%d", c.Request.URL.Path, retryTimes-1))
+			c.Redirect(http.StatusTemporaryRedirect, fmt.Sprintf("%s?retry=%d&error=%s", c.Request.URL.Path, retryTimes-1, err.Message))
 		} 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"
@@ -325,42 +52,42 @@ func Relay(c *gin.Context) {
 		autoBan := c.GetBool("auto_ban")
 		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) && autoBan {
+		if service.ShouldDisableChannel(&err.OpenAIError, err.StatusCode) && autoBan {
 			channelId := c.GetInt("channel_id")
 			channelName := c.GetString("channel_name")
-			disableChannel(channelId, channelName, err.Message)
+			service.DisableChannel(channelId, channelName, err.Message)
 		}
 	}
 }

 func RelayMidjourney(c *gin.Context) {
-	relayMode := RelayModeUnknown
+	relayMode := relayconstant.RelayModeUnknown
 	if strings.HasPrefix(c.Request.URL.Path, "/mj/submit/imagine") {
-		relayMode = RelayModeMidjourneyImagine
+		relayMode = relayconstant.RelayModeMidjourneyImagine
 	} else if strings.HasPrefix(c.Request.URL.Path, "/mj/submit/blend") {
-		relayMode = RelayModeMidjourneyBlend
+		relayMode = relayconstant.RelayModeMidjourneyBlend
 	} else if strings.HasPrefix(c.Request.URL.Path, "/mj/submit/describe") {
-		relayMode = RelayModeMidjourneyDescribe
+		relayMode = relayconstant.RelayModeMidjourneyDescribe
 	} else if strings.HasPrefix(c.Request.URL.Path, "/mj/notify") {
-		relayMode = RelayModeMidjourneyNotify
+		relayMode = relayconstant.RelayModeMidjourneyNotify
 	} else if strings.HasPrefix(c.Request.URL.Path, "/mj/submit/change") {
-		relayMode = RelayModeMidjourneyChange
+		relayMode = relayconstant.RelayModeMidjourneyChange
 	} else if strings.HasPrefix(c.Request.URL.Path, "/mj/submit/simple-change") {
-		relayMode = RelayModeMidjourneyChange
+		relayMode = relayconstant.RelayModeMidjourneyChange
 	} else if strings.HasSuffix(c.Request.URL.Path, "/fetch") {
-		relayMode = RelayModeMidjourneyTaskFetch
+		relayMode = relayconstant.RelayModeMidjourneyTaskFetch
 	} else if strings.HasSuffix(c.Request.URL.Path, "/list-by-condition") {
-		relayMode = RelayModeMidjourneyTaskFetchByCondition
+		relayMode = relayconstant.RelayModeMidjourneyTaskFetchByCondition
 	}

-	var err *MidjourneyResponse
+	var err *dto.MidjourneyResponse
 	switch relayMode {
-	case RelayModeMidjourneyNotify:
-		err = relayMidjourneyNotify(c)
-	case RelayModeMidjourneyTaskFetch, RelayModeMidjourneyTaskFetchByCondition:
-		err = relayMidjourneyTask(c, relayMode)
+	case relayconstant.RelayModeMidjourneyNotify:
+		err = relay.RelayMidjourneyNotify(c)
+	case relayconstant.RelayModeMidjourneyTaskFetch, relayconstant.RelayModeMidjourneyTaskFetchByCondition:
+		err = relay.RelayMidjourneyTask(c, relayMode)
 	default:
-		err = relayMidjourneySubmit(c, relayMode)
+		err = relay.RelayMidjourneySubmit(c, relayMode)
 	}
 	//err = relayMidjourneySubmit(c, relayMode)
 	log.Println(err)
@@ -376,12 +103,13 @@ func RelayMidjourney(c *gin.Context) {
 			if err.Code == 30 {
 				err.Result = "当前分组负载已饱和，请稍后再试，或升级账户以提升服务质量。"
 			}
-			c.JSON(400, gin.H{
-				"error": err.Description + " " + err.Result,
+			c.JSON(429, gin.H{
+				"error": fmt.Sprintf("%s %s", err.Description, err.Result),
+				"type":  "upstream_error",
 			})
 		}
 		channelId := c.GetInt("channel_id")
-		common.SysError(fmt.Sprintf("relay error (channel #%d): %s", channelId, err.Result))
+		common.SysError(fmt.Sprintf("relay error (channel #%d): %s", channelId, fmt.Sprintf("%s %s", err.Description, err.Result)))
 		//if shouldDisableChannel(&err.OpenAIError) {
 		//	channelId := c.GetInt("channel_id")
 		//	channelName := c.GetString("channel_name")
@@ -391,7 +119,7 @@ func RelayMidjourney(c *gin.Context) {
 }

 func RelayNotImplemented(c *gin.Context) {
-	err := OpenAIError{
+	err := dto.OpenAIError{
 		Message: "API not implemented",
 		Type:    "new_api_error",
 		Param:   "",
@@ -403,7 +131,7 @@ func RelayNotImplemented(c *gin.Context) {
 }

 func RelayNotFound(c *gin.Context) {
-	err := OpenAIError{
+	err := dto.OpenAIError{
 		Message: fmt.Sprintf("Invalid URL (%s %s)", c.Request.Method, c.Request.URL.Path),
 		Type:    "invalid_request_error",
 		Param:   "",
--- a/controller/telegram.go
+++ b/controller/telegram.go
@@ -0,0 +1,116 @@
+package controller
+
+import (
+	"crypto/hmac"
+	"crypto/sha256"
+	"encoding/hex"
+	"io"
+	"one-api/common"
+	"one-api/model"
+	"sort"
+
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+)
+
+func TelegramBind(c *gin.Context) {
+	if !common.TelegramOAuthEnabled {
+		c.JSON(200, gin.H{
+			"message": "管理员未开启通过 Telegram 登录以及注册",
+			"success": false,
+		})
+		return
+	}
+	params := c.Request.URL.Query()
+	if !checkTelegramAuthorization(params, common.TelegramBotToken) {
+		c.JSON(200, gin.H{
+			"message": "无效的请求",
+			"success": false,
+		})
+		return
+	}
+	telegramId := params["id"][0]
+	if model.IsTelegramIdAlreadyTaken(telegramId) {
+		c.JSON(200, gin.H{
+			"message": "该 Telegram 账户已被绑定",
+			"success": false,
+		})
+		return
+	}
+
+	session := sessions.Default(c)
+	id := session.Get("id")
+	user := model.User{Id: id.(int)}
+	if err := user.FillUserById(); err != nil {
+		c.JSON(200, gin.H{
+			"message": err.Error(),
+			"success": false,
+		})
+		return
+	}
+	user.TelegramId = telegramId
+	if err := user.Update(false); err != nil {
+		c.JSON(200, gin.H{
+			"message": err.Error(),
+			"success": false,
+		})
+		return
+	}
+
+	c.Redirect(302, "/setting")
+}
+
+func TelegramLogin(c *gin.Context) {
+	if !common.TelegramOAuthEnabled {
+		c.JSON(200, gin.H{
+			"message": "管理员未开启通过 Telegram 登录以及注册",
+			"success": false,
+		})
+		return
+	}
+	params := c.Request.URL.Query()
+	if !checkTelegramAuthorization(params, common.TelegramBotToken) {
+		c.JSON(200, gin.H{
+			"message": "无效的请求",
+			"success": false,
+		})
+		return
+	}
+
+	telegramId := params["id"][0]
+	user := model.User{TelegramId: telegramId}
+	if err := user.FillUserByTelegramId(); err != nil {
+		c.JSON(200, gin.H{
+			"message": err.Error(),
+			"success": false,
+		})
+		return
+	}
+	setupLogin(&user, c)
+}
+
+func checkTelegramAuthorization(params map[string][]string, token string) bool {
+	strs := []string{}
+	var hash = ""
+	for k, v := range params {
+		if k == "hash" {
+			hash = v[0]
+			continue
+		}
+		strs = append(strs, k+"="+v[0])
+	}
+	sort.Strings(strs)
+	var imploded = ""
+	for _, s := range strs {
+		if imploded != "" {
+			imploded += "\n"
+		}
+		imploded += s
+	}
+	sha256hash := sha256.New()
+	io.WriteString(sha256hash, token)
+	hmachash := hmac.New(sha256.New, sha256hash.Sum(nil))
+	io.WriteString(hmachash, imploded)
+	ss := hex.EncodeToString(hmachash.Sum(nil))
+	return hash == ss
+}
--- a/controller/token.go
+++ b/controller/token.go
@@ -124,14 +124,16 @@ func AddToken(c *gin.Context) {
 		return
 	}
 	cleanToken := model.Token{
-		UserId:         c.GetInt("id"),
-		Name:           token.Name,
-		Key:            common.GenerateKey(),
-		CreatedTime:    common.GetTimestamp(),
-		AccessedTime:   common.GetTimestamp(),
-		ExpiredTime:    token.ExpiredTime,
-		RemainQuota:    token.RemainQuota,
-		UnlimitedQuota: token.UnlimitedQuota,
+		UserId:             c.GetInt("id"),
+		Name:               token.Name,
+		Key:                common.GenerateKey(),
+		CreatedTime:        common.GetTimestamp(),
+		AccessedTime:       common.GetTimestamp(),
+		ExpiredTime:        token.ExpiredTime,
+		RemainQuota:        token.RemainQuota,
+		UnlimitedQuota:     token.UnlimitedQuota,
+		ModelLimitsEnabled: token.ModelLimitsEnabled,
+		ModelLimits:        token.ModelLimits,
 	}
 	err = cleanToken.Insert()
 	if err != nil {
--- a/controller/topup.go
+++ b/controller/topup.go
@@ -9,6 +9,7 @@ import (
 	"net/url"
 	"one-api/common"
 	"one-api/model"
+	"one-api/service"
 	"strconv"
 	"time"
 )
@@ -55,14 +56,14 @@ func RequestEpay(c *gin.Context) {
 		c.JSON(200, gin.H{"message": err.Error(), "data": 10})
 		return
 	}
-	if req.Amount < 1 {
-		c.JSON(200, gin.H{"message": "充值金额不能小于1", "data": 10})
+	if req.Amount < common.MinTopUp {
+		c.JSON(200, gin.H{"message": fmt.Sprintf("充值数量不能小于 %d", common.MinTopUp), "data": 10})
 		return
 	}

 	id := c.GetInt("id")
 	user, _ := model.GetUserById(id, false)
-	amount := GetAmount(float64(req.Amount), *user)
+	payMoney := GetAmount(float64(req.Amount), *user)

 	var payType epay.PurchaseType
 	if req.PaymentMethod == "zfb" {
@@ -72,11 +73,10 @@ func RequestEpay(c *gin.Context) {
 		req.PaymentMethod = "wxpay"
 		payType = epay.WechatPay
 	}
-
+	callBackAddress := service.GetCallbackAddress()
 	returnUrl, _ := url.Parse(common.ServerAddress + "/log")
-	notifyUrl, _ := url.Parse(common.ServerAddress + "/api/user/epay/notify")
+	notifyUrl, _ := url.Parse(callBackAddress + "/api/user/epay/notify")
 	tradeNo := strconv.FormatInt(time.Now().Unix(), 10)
-	payMoney := amount
 	client := GetEpayClient()
 	if client == nil {
 		c.JSON(200, gin.H{"message": "error", "data": "当前管理员未配置支付信息"})
@@ -169,8 +169,8 @@ func RequestAmount(c *gin.Context) {
 		c.JSON(200, gin.H{"message": "error", "data": "参数错误"})
 		return
 	}
-	if req.Amount < 1 {
-		c.JSON(200, gin.H{"message": "error", "data": "充值金额不能小于1"})
+	if req.Amount < common.MinTopUp {
+		c.JSON(200, gin.H{"message": "error", "data": fmt.Sprintf("充值数量不能小于 %d", common.MinTopUp)})
 		return
 	}
 	id := c.GetInt("id")
--- a/controller/usedata.go
+++ b/controller/usedata.go
@@ -31,6 +31,14 @@ func GetUserQuotaDates(c *gin.Context) {
 	userId := c.GetInt("id")
 	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+	// 判断时间跨度是否超过 1 个月
+	if endTimestamp-startTimestamp > 2592000 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "时间跨度不能超过 1 个月",
+		})
+		return
+	}
 	dates, err := model.GetQuotaDataByUserId(userId, startTimestamp, endTimestamp)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -3,6 +3,7 @@ version: '3.4'
 services:
  new-api:
    image: calciumion/new-api:latest
+    # build: .
    container_name: new-api
    restart: always
    command: --log-dir /app/logs
--- a/dto/audio.go
+++ b/dto/audio.go
@@ -0,0 +1,13 @@
+package dto
+
+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 AudioResponse struct {
+	Text string `json:"text"`
+}
--- a/dto/dalle.go
+++ b/dto/dalle.go
@@ -0,0 +1,20 @@
+package dto
+
+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 ImageResponse struct {
+	Created int `json:"created"`
+	Data    []struct {
+		Url     string `json:"url"`
+		B64Json string `json:"b64_json"`
+	}
+}
--- a/dto/error.go
+++ b/dto/error.go
@@ -0,0 +1,13 @@
+package dto
+
+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"`
+}
--- a/dto/midjourney.go
+++ b/dto/midjourney.go
@@ -0,0 +1,19 @@
+package dto
+
+type MidjourneyRequest struct {
+	Prompt      string   `json:"prompt"`
+	NotifyHook  string   `json:"notifyHook"`
+	Action      string   `json:"action"`
+	Index       int      `json:"index"`
+	State       string   `json:"state"`
+	TaskId      string   `json:"taskId"`
+	Base64Array []string `json:"base64Array"`
+	Content     string   `json:"content"`
+}
+
+type MidjourneyResponse struct {
+	Code        int         `json:"code"`
+	Description string      `json:"description"`
+	Properties  interface{} `json:"properties"`
+	Result      string      `json:"result"`
+}
--- a/dto/text_request.go
+++ b/dto/text_request.go
@@ -0,0 +1,138 @@
+package dto
+
+import "encoding/json"
+
+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        uint            `json:"max_tokens,omitempty"`
+	Temperature      float64         `json:"temperature,omitempty"`
+	TopP             float64         `json:"top_p,omitempty"`
+	Stop             any             `json:"stop,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"`
+	LogProbs         bool            `json:"logprobs,omitempty"`
+	TopLogProbs      int             `json:"top_logprobs,omitempty"`
+}
+
+func (r GeneralOpenAIRequest) ParseInput() []string {
+	if r.Input == nil {
+		return nil
+	}
+	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 Message struct {
+	Role       string          `json:"role"`
+	Content    json.RawMessage `json:"content"`
+	Name       *string         `json:"name,omitempty"`
+	ToolCalls  any             `json:"tool_calls,omitempty"`
+	ToolCallId string          `json:"tool_call_id,omitempty"`
+}
+
+type MediaMessage struct {
+	Type     string `json:"type"`
+	Text     string `json:"text"`
+	ImageUrl any    `json:"image_url,omitempty"`
+}
+
+type MessageImageUrl struct {
+	Url    string `json:"url"`
+	Detail string `json:"detail"`
+}
+
+const (
+	ContentTypeText     = "text"
+	ContentTypeImageURL = "image_url"
+)
+
+func (m Message) StringContent() string {
+	var stringContent string
+	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
+		return stringContent
+	}
+	return string(m.Content)
+}
+
+func (m Message) ParseContent() []MediaMessage {
+	var contentList []MediaMessage
+	var stringContent string
+	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
+		contentList = append(contentList, MediaMessage{
+			Type: ContentTypeText,
+			Text: stringContent,
+		})
+		return contentList
+	}
+	var arrayContent []json.RawMessage
+	if err := json.Unmarshal(m.Content, &arrayContent); err == nil {
+		for _, contentItem := range arrayContent {
+			var contentMap map[string]any
+			if err := json.Unmarshal(contentItem, &contentMap); err != nil {
+				continue
+			}
+			switch contentMap["type"] {
+			case ContentTypeText:
+				if subStr, ok := contentMap["text"].(string); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeText,
+						Text: subStr,
+					})
+				}
+			case ContentTypeImageURL:
+				if subObj, ok := contentMap["image_url"].(map[string]any); ok {
+					detail, ok := subObj["detail"]
+					if ok {
+						subObj["detail"] = detail.(string)
+					} else {
+						subObj["detail"] = "auto"
+					}
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeImageURL,
+						ImageUrl: MessageImageUrl{
+							Url:    subObj["url"].(string),
+							Detail: subObj["detail"].(string),
+						},
+					})
+				}
+			}
+		}
+		return contentList
+	}
+
+	return nil
+}
+
+type Usage struct {
+	PromptTokens     int `json:"prompt_tokens"`
+	CompletionTokens int `json:"completion_tokens"`
+	TotalTokens      int `json:"total_tokens"`
+}
--- a/dto/text_response.go
+++ b/dto/text_response.go
@@ -0,0 +1,63 @@
+package dto
+
+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"`
+	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 ChatCompletionsStreamResponseChoice struct {
+	Delta struct {
+		Content   string `json:"content"`
+		Role      string `json:"role,omitempty"`
+		ToolCalls any    `json:"tool_calls,omitempty"`
+	} `json:"delta"`
+	FinishReason *string `json:"finish_reason,omitempty"`
+	Index        int     `json:"index,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 ChatCompletionsStreamResponseSimple struct {
+	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+}
+
+type CompletionsStreamResponse struct {
+	Choices []struct {
+		Text         string `json:"text"`
+		FinishReason string `json:"finish_reason"`
+	} `json:"choices"`
+}
--- a/main.go
+++ b/main.go
@@ -13,6 +13,7 @@ import (
 	"one-api/middleware"
 	"one-api/model"
 	"one-api/router"
+	"one-api/service"
 	"os"
 	"strconv"

@@ -63,6 +64,9 @@ func main() {
 		common.SysError(fmt.Sprintf("sync frequency: %d seconds", common.SyncFrequency))
 		model.InitChannelCache()
 	}
+	if common.RedisEnabled {
+		go model.SyncTokenCache(common.SyncFrequency)
+	}
 	if common.MemoryCacheEnabled {
 		go model.SyncOptions(common.SyncFrequency)
 		go model.SyncChannelCache(common.SyncFrequency)
@@ -85,7 +89,9 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
-	go controller.UpdateMidjourneyTaskBulk()
+	common.SafeGoroutine(func() {
+		controller.UpdateMidjourneyTaskBulk()
+	})
 	if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
 		common.BatchUpdateEnabled = true
 		common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")
@@ -100,7 +106,7 @@ func main() {
 		common.SysLog("pprof enabled")
 	}

-	controller.InitTokenEncoders()
+	service.InitTokenEncoders()

 	// Initialize HTTP server
 	server := gin.New()
--- a/14
+++ b/14
@@ -0,0 +1,14 @@
+FRONTEND_DIR = ./web
+BACKEND_DIR = .
+
+.PHONY: all build-frontend start-backend
+
+all: build-frontend start-backend
+
+build-frontend:
+	@echo "Building frontend..."
+	@cd $(FRONTEND_DIR) && npm install && DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build npm run build
+
+start-backend:
+	@echo "Starting backend dev server..."
+	@cd $(BACKEND_DIR) && go run main.go &
--- a/middleware/auth.go
+++ b/middleware/auth.go
@@ -115,6 +115,10 @@ func TokenAuth() func(c *gin.Context) {
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
 		c.Set("token_name", token.Name)
+		c.Set("token_unlimited_quota", token.UnlimitedQuota)
+		if !token.UnlimitedQuota {
+			c.Set("token_quota", token.RemainQuota)
+		}
 		if token.ModelLimitsEnabled {
 			c.Set("token_model_limit_enabled", true)
 			c.Set("token_model_limit", token.GetModelLimitsMap())
--- a/middleware/distributor.go
+++ b/middleware/distributor.go
@@ -18,8 +18,6 @@ type ModelRequest struct {
 func Distribute() func(c *gin.Context) {
 	return func(c *gin.Context) {
 		userId := c.GetInt("id")
-		userGroup, _ := model.CacheGetUserGroup(userId)
-		c.Set("group", userGroup)
 		var channel *model.Channel
 		channelId, ok := c.Get("channelId")
 		if ok {
@@ -50,7 +48,7 @@ func Distribute() func(c *gin.Context) {
 				err = common.UnmarshalBodyReusable(c, &modelRequest)
 			}
 			if err != nil {
-				abortWithMessage(c, http.StatusBadRequest, "无效的请求: "+err.Error())
+				abortWithMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
 				return
 			}
 			if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
@@ -98,16 +96,26 @@ func Distribute() func(c *gin.Context) {
 					return
 				}
 			}
+
+			userGroup, _ := model.CacheGetUserGroup(userId)
+			c.Set("group", userGroup)
+
 			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)
+				// 如果错误，但是渠道不为空，说明是数据库一致性问题
 				if channel != nil {
 					common.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"
 				}
+				// 如果错误，而且渠道为空，说明是没有可用渠道
 				abortWithMessage(c, http.StatusServiceUnavailable, message)
 				return
 			}
+			if channel == nil {
+				abortWithMessage(c, http.StatusServiceUnavailable, fmt.Sprintf("当前分组 %s 下对于模型 %s 无可用渠道（数据库一致性已被破坏）", userGroup, modelRequest.Model))
+				return
+			}
 		}
 		c.Set("channel", channel.Type)
 		c.Set("channel_id", channel.Id)
@@ -121,15 +129,18 @@ func Distribute() func(c *gin.Context) {
 		c.Set("model_mapping", channel.GetModelMapping())
 		c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
 		c.Set("base_url", channel.GetBaseURL())
+		// TODO: api_version统一
 		switch channel.Type {
 		case common.ChannelTypeAzure:
 			c.Set("api_version", channel.Other)
 		case common.ChannelTypeXunfei:
 			c.Set("api_version", channel.Other)
-		case common.ChannelTypeAIProxyLibrary:
-			c.Set("library_id", channel.Other)
+		//case common.ChannelTypeAIProxyLibrary:
+		//	c.Set("library_id", channel.Other)
 		case common.ChannelTypeGemini:
 			c.Set("api_version", channel.Other)
+		case common.ChannelTypeAli:
+			c.Set("plugin", channel.Other)
 		}
 		c.Next()
 	}
--- a/model/ability.go
+++ b/model/ability.go
@@ -1,6 +1,8 @@
 package model

 import (
+	"errors"
+	"fmt"
 	"one-api/common"
 	"strings"
 )
@@ -68,7 +70,7 @@ func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 			}
 		}
 	} else {
-		return nil, nil
+		return nil, errors.New("channel not found")
 	}
 	err = DB.First(&channel, "id = ?", channel.Id).Error
 	return &channel, err
@@ -118,3 +120,46 @@ func (channel *Channel) UpdateAbilities() error {
 func UpdateAbilityStatus(channelId int, status bool) error {
 	return DB.Model(&Ability{}).Where("channel_id = ?", channelId).Select("enabled").Update("enabled", status).Error
 }
+
+func FixAbility() (int, error) {
+	var channelIds []int
+	count := 0
+	// Find all channel ids from channel table
+	err := DB.Model(&Channel{}).Pluck("id", &channelIds).Error
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get channel ids from channel table failed: %s", err.Error()))
+		return 0, err
+	}
+	// Delete abilities of channels that are not in channel table
+	err = DB.Where("channel_id NOT IN (?)", channelIds).Delete(&Ability{}).Error
+	if err != nil {
+		common.SysError(fmt.Sprintf("Delete abilities of channels that are not in channel table failed: %s", err.Error()))
+		return 0, err
+	}
+	common.SysLog(fmt.Sprintf("Delete abilities of channels that are not in channel table successfully, ids: %v", channelIds))
+	count += len(channelIds)
+
+	// Use channelIds to find channel not in abilities table
+	var abilityChannelIds []int
+	err = DB.Model(&Ability{}).Pluck("channel_id", &abilityChannelIds).Error
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get channel ids from abilities table failed: %s", err.Error()))
+		return 0, err
+	}
+	var channels []Channel
+	err = DB.Where("id NOT IN (?)", abilityChannelIds).Find(&channels).Error
+	if err != nil {
+		return 0, err
+	}
+	for _, channel := range channels {
+		err := channel.UpdateAbilities()
+		if err != nil {
+			common.SysError(fmt.Sprintf("Update abilities of channel %d failed: %s", channel.Id, err.Error()))
+		} else {
+			common.SysLog(fmt.Sprintf("Update abilities of channel %d successfully", channel.Id))
+			count++
+		}
+	}
+	InitChannelCache()
+	return count, nil
+}
--- a/model/cache.go
+++ b/model/cache.go
@@ -20,34 +20,88 @@ var (
 	UserId2StatusCacheSeconds = common.SyncFrequency
 )

-func CacheGetTokenByKey(key string) (*Token, error) {
-	keyCol := "`key`"
-	if common.UsingPostgreSQL {
-		keyCol = `"key"`
-	}
-	var token Token
+// 仅用于定时同步缓存
+var token2UserId = make(map[string]int)
+var token2UserIdLock sync.RWMutex
+
+func cacheSetToken(token *Token) error {
 	if !common.RedisEnabled {
-		err := DB.Where(keyCol+" = ?", key).First(&token).Error
-		return &token, err
+		return token.SelectUpdate()
 	}
+	jsonBytes, err := json.Marshal(token)
+	if err != nil {
+		return err
+	}
+	err = common.RedisSet(fmt.Sprintf("token:%s", token.Key), string(jsonBytes), time.Duration(TokenCacheSeconds)*time.Second)
+	if err != nil {
+		common.SysError(fmt.Sprintf("failed to set token %s to redis: %s", token.Key, err.Error()))
+		return err
+	}
+	token2UserIdLock.Lock()
+	defer token2UserIdLock.Unlock()
+	token2UserId[token.Key] = token.UserId
+	return nil
+}
+
+// CacheGetTokenByKey 从缓存中获取 token 并续期时间，如果缓存中不存在，则从数据库中获取
+func CacheGetTokenByKey(key string) (*Token, error) {
+	if !common.RedisEnabled {
+		return GetTokenByKey(key)
+	}
+	var token *Token
 	tokenObjectString, err := common.RedisGet(fmt.Sprintf("token:%s", key))
 	if err != nil {
-		err := DB.Where(keyCol+" = ?", key).First(&token).Error
+		// 如果缓存中不存在，则从数据库中获取
+		token, err = GetTokenByKey(key)
 		if err != nil {
 			return nil, err
 		}
-		jsonBytes, err := json.Marshal(token)
-		if err != nil {
-			return nil, err
-		}
-		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())
-		}
-		return &token, nil
+		err = cacheSetToken(token)
+		return token, nil
 	}
+	// 如果缓存中存在，则续期时间
+	err = common.RedisExpire(fmt.Sprintf("token:%s", key), time.Duration(TokenCacheSeconds)*time.Second)
 	err = json.Unmarshal([]byte(tokenObjectString), &token)
-	return &token, err
+	return token, err
+}
+
+func SyncTokenCache(frequency int) {
+	for {
+		time.Sleep(time.Duration(frequency) * time.Second)
+		common.SysLog("syncing tokens from database")
+		token2UserIdLock.Lock()
+		// 从token2UserId中获取所有的key
+		var copyToken2UserId = make(map[string]int)
+		for s, i := range token2UserId {
+			copyToken2UserId[s] = i
+		}
+		token2UserId = make(map[string]int)
+		token2UserIdLock.Unlock()
+
+		for key := range copyToken2UserId {
+			token, err := GetTokenByKey(key)
+			if err != nil {
+				// 如果数据库中不存在，则删除缓存
+				common.SysError(fmt.Sprintf("failed to get token %s from database: %s", key, err.Error()))
+				//delete redis
+				err := common.RedisDel(fmt.Sprintf("token:%s", key))
+				if err != nil {
+					common.SysError(fmt.Sprintf("failed to delete token %s from redis: %s", key, err.Error()))
+				}
+			} else {
+				// 如果数据库中存在，先检查redis
+				_, err := common.RedisGet(fmt.Sprintf("token:%s", key))
+				if err != nil {
+					// 如果redis中不存在，则跳过
+					continue
+				}
+				err = cacheSetToken(token)
+				if err != nil {
+					common.SysError(fmt.Sprintf("failed to update token %s to redis: %s", key, err.Error()))
+				}
+			}
+		}
+	}
 }

 func CacheGetUserGroup(id int) (group string, err error) {
@@ -68,6 +122,24 @@ func CacheGetUserGroup(id int) (group string, err error) {
 	return group, err
 }

+func CacheGetUsername(id int) (username string, err error) {
+	if !common.RedisEnabled {
+		return GetUsernameById(id)
+	}
+	username, err = common.RedisGet(fmt.Sprintf("user_name:%d", id))
+	if err != nil {
+		username, err = GetUsernameById(id)
+		if err != nil {
+			return "", err
+		}
+		err = common.RedisSet(fmt.Sprintf("user_name:%d", id), username, time.Duration(UserId2GroupCacheSeconds)*time.Second)
+		if err != nil {
+			common.SysError("Redis set user group error: " + err.Error())
+		}
+	}
+	return username, err
+}
+
 func CacheGetUserQuota(id int) (quota int, err error) {
 	if !common.RedisEnabled {
 		return GetUserQuota(id)
@@ -219,29 +291,32 @@ func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error
 			}
 		}
 	}
+
+	// 平滑系数
+	smoothingFactor := 10
 	// Calculate the total weight of all channels up to endIdx
 	totalWeight := 0
 	for _, channel := range channels[:endIdx] {
-		totalWeight += channel.GetWeight()
+		totalWeight += channel.GetWeight() + smoothingFactor
 	}

-	if totalWeight == 0 {
-		// If all weights are 0, select a channel randomly
-		return channels[rand.Intn(endIdx)], nil
-	}
+	//if totalWeight == 0 {
+	//	// If all weights are 0, select a channel randomly
+	//	return channels[rand.Intn(endIdx)], nil
+	//}

 	// Generate a random value in the range [0, totalWeight)
 	randomWeight := rand.Intn(totalWeight)

 	// Find a channel based on its weight
 	for _, channel := range channels[:endIdx] {
-		randomWeight -= channel.GetWeight()
-		if randomWeight <= 0 {
+		randomWeight -= channel.GetWeight() + smoothingFactor
+		if randomWeight < 0 {
 			return channel, nil
 		}
 	}
-	// return the last channel if no channel is found
-	return channels[endIdx-1], nil
+	// return null if no channel is not found
+	return nil, errors.New("channel not found")
 }

 func CacheGetChannel(id int) (*Channel, error) {
--- a/model/channel.go
+++ b/model/channel.go
@@ -8,7 +8,7 @@ import (
 type Channel struct {
 	Id                 int     `json:"id"`
 	Type               int     `json:"type" gorm:"default:0"`
-	Key                string  `json:"key" gorm:"not null;index"`
+	Key                string  `json:"key" gorm:"not null"`
 	OpenAIOrganization *string `json:"openai_organization"`
 	Status             int     `json:"status" gorm:"default:1"`
 	Name               string  `json:"name" gorm:"index"`
@@ -43,21 +43,39 @@ func GetAllChannels(startIdx int, num int, selectAll bool, idSort bool) ([]*Chan
 	return channels, err
 }

-func SearchChannels(keyword string, group string) (channels []*Channel, err error) {
+func SearchChannels(keyword string, group string, model string) ([]*Channel, error) {
+	var channels []*Channel
 	keyCol := "`key`"
+	groupCol := "`group`"
+	modelsCol := "`models`"
+
+	// 如果是 PostgreSQL，使用双引号
 	if common.UsingPostgreSQL {
 		keyCol = `"key"`
+		groupCol = `"group"`
+		modelsCol = `"models"`
 	}
+
+	// 构造基础查询
+	baseQuery := DB.Model(&Channel{}).Omit(keyCol)
+
+	// 构造WHERE子句
+	var whereClause string
+	var args []interface{}
 	if group != "" {
-		groupCol := "`group`"
-		if common.UsingPostgreSQL {
-			groupCol = `"group"`
-		}
-		err = DB.Omit("key").Where("(id = ? or name LIKE ? or "+keyCol+" = ?) and "+groupCol+" LIKE ?", common.String2Int(keyword), keyword+"%", keyword, "%"+group+"%").Find(&channels).Error
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " LIKE ? AND " + modelsCol + " LIKE ?"
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+group+"%", "%"+model+"%")
 	} else {
-		err = DB.Omit("key").Where("id = ? or name LIKE ? or "+keyCol+" = ?", common.String2Int(keyword), keyword+"%", keyword).Find(&channels).Error
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")
 	}
-	return channels, err
+
+	// 执行查询
+	err := baseQuery.Where(whereClause, args...).Find(&channels).Error
+	if err != nil {
+		return nil, err
+	}
+	return channels, nil
 }

 func GetChannelById(id int, selectAll bool) (*Channel, error) {
--- a/model/log.go
+++ b/model/log.go
@@ -20,6 +20,8 @@ type Log struct {
 	Quota            int    `json:"quota" gorm:"default:0"`
 	PromptTokens     int    `json:"prompt_tokens" gorm:"default:0"`
 	CompletionTokens int    `json:"completion_tokens" gorm:"default:0"`
+	UseTime          int    `json:"use_time" gorm:"default:0"`
+	IsStream         bool   `json:"is_stream" gorm:"default:false"`
 	ChannelId        int    `json:"channel" gorm:"index"`
 	TokenId          int    `json:"token_id" gorm:"default:0;index"`
 }
@@ -41,9 +43,10 @@ func RecordLog(userId int, logType int, content string) {
 	if logType == LogTypeConsume && !common.LogConsumeEnabled {
 		return
 	}
+	username, _ := CacheGetUsername(userId)
 	log := &Log{
 		UserId:    userId,
-		Username:  GetUsernameById(userId),
+		Username:  username,
 		CreatedAt: common.GetTimestamp(),
 		Type:      logType,
 		Content:   content,
@@ -54,12 +57,12 @@ func RecordLog(userId int, logType int, content string) {
 	}
 }

-func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int) {
+func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int, useTimeSeconds int, isStream bool) {
 	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, 用户调用前余额=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, userQuota, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
 	if !common.LogConsumeEnabled {
 		return
 	}
-	username := GetUsernameById(userId)
+	username, _ := CacheGetUsername(userId)
 	log := &Log{
 		UserId:           userId,
 		Username:         username,
@@ -73,13 +76,17 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		Quota:            quota,
 		ChannelId:        channelId,
 		TokenId:          tokenId,
+		UseTime:          useTimeSeconds,
+		IsStream:         isStream,
 	}
 	err := DB.Create(log).Error
 	if err != nil {
 		common.LogError(ctx, "failed to record log: "+err.Error())
 	}
 	if common.DataExportEnabled {
-		LogQuotaData(userId, username, modelName, quota, common.GetTimestamp())
+		common.SafeGoroutine(func() {
+			LogQuotaData(userId, username, modelName, quota, common.GetTimestamp(), promptTokens+completionTokens)
+		})
 	}
 }

--- a/model/midjourney.go
+++ b/model/midjourney.go
@@ -18,6 +18,7 @@ type Midjourney struct {
 	Progress    string `json:"progress"`
 	FailReason  string `json:"fail_reason"`
 	ChannelId   int    `json:"channel_id"`
+	Quota       int    `json:"quota"`
 }

 // TaskQueryParams 用于包含所有搜索条件的结构体，可以根据需求添加更多字段
@@ -152,8 +153,14 @@ func (midjourney *Midjourney) Update() error {
 	return err
 }

-func MjBulkUpdate(taskIDs []string, params map[string]any) error {
+func MjBulkUpdate(mjIds []string, params map[string]any) error {
 	return DB.Model(&Midjourney{}).
-		Where("mj_id in (?)", taskIDs).
+		Where("mj_id in (?)", mjIds).
+		Updates(params).Error
+}
+
+func MjBulkUpdateByTaskIds(taskIDs []int, params map[string]any) error {
+	return DB.Model(&Midjourney{}).
+		Where("id in (?)", taskIDs).
 		Updates(params).Error
 }
--- a/model/option.go
+++ b/model/option.go
@@ -30,10 +30,12 @@ func InitOptionMap() {
 	common.OptionMap["PasswordRegisterEnabled"] = strconv.FormatBool(common.PasswordRegisterEnabled)
 	common.OptionMap["EmailVerificationEnabled"] = strconv.FormatBool(common.EmailVerificationEnabled)
 	common.OptionMap["GitHubOAuthEnabled"] = strconv.FormatBool(common.GitHubOAuthEnabled)
+	common.OptionMap["TelegramOAuthEnabled"] = strconv.FormatBool(common.TelegramOAuthEnabled)
 	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["LogConsumeEnabled"] = strconv.FormatBool(common.LogConsumeEnabled)
 	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
 	common.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(common.DisplayTokenStatEnabled)
@@ -55,12 +57,16 @@ func InitOptionMap() {
 	common.OptionMap["Logo"] = common.Logo
 	common.OptionMap["ServerAddress"] = ""
 	common.OptionMap["PayAddress"] = ""
+	common.OptionMap["CustomCallbackAddress"] = ""
 	common.OptionMap["EpayId"] = ""
 	common.OptionMap["EpayKey"] = ""
 	common.OptionMap["Price"] = strconv.FormatFloat(common.Price, 'f', -1, 64)
+	common.OptionMap["MinTopUp"] = strconv.Itoa(common.MinTopUp)
 	common.OptionMap["TopupGroupRatio"] = common.TopupGroupRatio2JSONString()
 	common.OptionMap["GitHubClientId"] = ""
 	common.OptionMap["GitHubClientSecret"] = ""
+	common.OptionMap["TelegramBotToken"] = ""
+	common.OptionMap["TelegramBotName"] = ""
 	common.OptionMap["WeChatServerAddress"] = ""
 	common.OptionMap["WeChatServerToken"] = ""
 	common.OptionMap["WeChatAccountQRCodeImageURL"] = ""
@@ -76,9 +82,12 @@ func InitOptionMap() {
 	common.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
 	common.OptionMap["TopUpLink"] = common.TopUpLink
 	common.OptionMap["ChatLink"] = common.ChatLink
+	common.OptionMap["ChatLink2"] = common.ChatLink2
 	common.OptionMap["QuotaPerUnit"] = strconv.FormatFloat(common.QuotaPerUnit, 'f', -1, 64)
 	common.OptionMap["RetryTimes"] = strconv.Itoa(common.RetryTimes)
 	common.OptionMap["DataExportInterval"] = strconv.Itoa(common.DataExportInterval)
+	common.OptionMap["DataExportDefaultTime"] = common.DataExportDefaultTime
+	common.OptionMap["DefaultCollapseSidebar"] = strconv.FormatBool(common.DefaultCollapseSidebar)

 	common.OptionMapRWMutex.Unlock()
 	loadOptionsFromDatabase()
@@ -135,7 +144,7 @@ func updateOptionMap(key string, value string) (err error) {
 			common.ImageDownloadPermission = intValue
 		}
 	}
-	if strings.HasSuffix(key, "Enabled") {
+	if strings.HasSuffix(key, "Enabled") || key == "DefaultCollapseSidebar" {
 		boolValue := value == "true"
 		switch key {
 		case "PasswordRegisterEnabled":
@@ -148,6 +157,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.GitHubOAuthEnabled = boolValue
 		case "WeChatAuthEnabled":
 			common.WeChatAuthEnabled = boolValue
+		case "TelegramOAuthEnabled":
+			common.TelegramOAuthEnabled = boolValue
 		case "TurnstileCheckEnabled":
 			common.TurnstileCheckEnabled = boolValue
 		case "RegisterEnabled":
@@ -156,6 +167,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.EmailDomainRestrictionEnabled = boolValue
 		case "AutomaticDisableChannelEnabled":
 			common.AutomaticDisableChannelEnabled = boolValue
+		case "AutomaticEnableChannelEnabled":
+			common.AutomaticEnableChannelEnabled = boolValue
 		case "LogConsumeEnabled":
 			common.LogConsumeEnabled = boolValue
 		case "DisplayInCurrencyEnabled":
@@ -166,6 +179,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.DrawingEnabled = boolValue
 		case "DataExportEnabled":
 			common.DataExportEnabled = boolValue
+		case "DefaultCollapseSidebar":
+			common.DefaultCollapseSidebar = boolValue
 		}
 	}
 	switch key {
@@ -186,12 +201,16 @@ func updateOptionMap(key string, value string) (err error) {
 		common.ServerAddress = value
 	case "PayAddress":
 		common.PayAddress = value
+	case "CustomCallbackAddress":
+		common.CustomCallbackAddress = value
 	case "EpayId":
 		common.EpayId = value
 	case "EpayKey":
 		common.EpayKey = value
 	case "Price":
 		common.Price, _ = strconv.ParseFloat(value, 64)
+	case "MinTopUp":
+		common.MinTopUp, _ = strconv.Atoi(value)
 	case "TopupGroupRatio":
 		err = common.UpdateTopupGroupRatioByJSONString(value)
 	case "GitHubClientId":
@@ -210,6 +229,10 @@ func updateOptionMap(key string, value string) (err error) {
 		common.WeChatServerToken = value
 	case "WeChatAccountQRCodeImageURL":
 		common.WeChatAccountQRCodeImageURL = value
+	case "TelegramBotToken":
+		common.TelegramBotToken = value
+	case "TelegramBotName":
+		common.TelegramBotName = value
 	case "TurnstileSiteKey":
 		common.TurnstileSiteKey = value
 	case "TurnstileSecretKey":
@@ -228,6 +251,8 @@ func updateOptionMap(key string, value string) (err error) {
 		common.RetryTimes, _ = strconv.Atoi(value)
 	case "DataExportInterval":
 		common.DataExportInterval, _ = strconv.Atoi(value)
+	case "DataExportDefaultTime":
+		common.DataExportDefaultTime = value
 	case "ModelRatio":
 		err = common.UpdateModelRatioByJSONString(value)
 	case "GroupRatio":
@@ -238,6 +263,8 @@ func updateOptionMap(key string, value string) (err error) {
 		common.TopUpLink = value
 	case "ChatLink":
 		common.ChatLink = value
+	case "ChatLink2":
+		common.ChatLink2 = value
 	case "ChannelDisableThreshold":
 		common.ChannelDisableThreshold, _ = strconv.ParseFloat(value, 64)
 	case "QuotaPerUnit":
--- a/model/token.go
+++ b/model/token.go
@@ -47,7 +47,9 @@ func ValidateUserToken(key string) (token *Token, err error) {
 	token, err = CacheGetTokenByKey(key)
 	if err == nil {
 		if token.Status == common.TokenStatusExhausted {
-			return nil, errors.New("该令牌额度已用尽 token.Status == common.TokenStatusExhausted " + key)
+			keyPrefix := key[:3]
+			keySuffix := key[len(key)-3:]
+			return nil, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
 		} else if token.Status == common.TokenStatusExpired {
 			return nil, errors.New("该令牌已过期")
 		}
@@ -73,7 +75,9 @@ func ValidateUserToken(key string) (token *Token, err error) {
 					common.SysError("failed to update token status" + err.Error())
 				}
 			}
-			return nil, errors.New(fmt.Sprintf("%s 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", token.Key, token.RemainQuota))
+			keyPrefix := key[:3]
+			keySuffix := key[len(key)-3:]
+			return nil, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
 		}
 		return token, nil
 	}
@@ -100,6 +104,16 @@ func GetTokenById(id int) (*Token, error) {
 	return &token, err
 }

+func GetTokenByKey(key string) (*Token, error) {
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
+	var token Token
+	err := DB.Where(keyCol+" = ?", key).First(&token).Error
+	return &token, err
+}
+
 func (token *Token) Insert() error {
 	var err error
 	err = DB.Create(token).Error
--- a/model/usedata.go
+++ b/model/usedata.go
@@ -2,6 +2,7 @@ package model

 import (
 	"fmt"
+	"gorm.io/gorm"
 	"one-api/common"
 	"sync"
 	"time"
@@ -14,6 +15,7 @@ type QuotaData struct {
 	Username  string `json:"username" gorm:"index:idx_qdt_model_user_name,priority:2;size:64;default:''"`
 	ModelName string `json:"model_name" gorm:"index:idx_qdt_model_user_name,priority:1;size:64;default:''"`
 	CreatedAt int64  `json:"created_at" gorm:"bigint;index:idx_qdt_created_at,priority:2"`
+	TokenUsed int    `json:"token_used" gorm:"default:0"`
 	Count     int    `json:"count" gorm:"default:0"`
 	Quota     int    `json:"quota" gorm:"default:0"`
 }
@@ -37,9 +39,7 @@ func UpdateQuotaData() {
 var CacheQuotaData = make(map[string]*QuotaData)
 var CacheQuotaDataLock = sync.Mutex{}

-func LogQuotaDataCache(userId int, username string, modelName string, quota int, createdAt int64) {
-	// 只精确到小时
-	createdAt = createdAt - (createdAt % 3600)
+func logQuotaDataCache(userId int, username string, modelName string, quota int, createdAt int64, tokenUsed int) {
 	key := fmt.Sprintf("%d-%s-%s-%d", userId, username, modelName, createdAt)
 	quotaData, ok := CacheQuotaData[key]
 	if ok {
@@ -53,15 +53,19 @@ func LogQuotaDataCache(userId int, username string, modelName string, quota int,
 			CreatedAt: createdAt,
 			Count:     1,
 			Quota:     quota,
+			TokenUsed: tokenUsed,
 		}
 	}
 	CacheQuotaData[key] = quotaData
 }

-func LogQuotaData(userId int, username string, modelName string, quota int, createdAt int64) {
+func LogQuotaData(userId int, username string, modelName string, quota int, createdAt int64, tokenUsed int) {
+	// 只精确到小时
+	createdAt = createdAt - (createdAt % 3600)
+
 	CacheQuotaDataLock.Lock()
 	defer CacheQuotaDataLock.Unlock()
-	LogQuotaDataCache(userId, username, modelName, quota, createdAt)
+	logQuotaDataCache(userId, username, modelName, quota, createdAt, tokenUsed)
 }

 func SaveQuotaDataCache() {
@@ -77,9 +81,10 @@ func SaveQuotaDataCache() {
 		DB.Table("quota_data").Where("user_id = ? and username = ? and model_name = ? and created_at = ?",
 			quotaData.UserID, quotaData.Username, quotaData.ModelName, quotaData.CreatedAt).First(quotaDataDB)
 		if quotaDataDB.Id > 0 {
-			quotaDataDB.Count += quotaData.Count
-			quotaDataDB.Quota += quotaData.Quota
-			DB.Table("quota_data").Save(quotaDataDB)
+			//quotaDataDB.Count += quotaData.Count
+			//quotaDataDB.Quota += quotaData.Quota
+			//DB.Table("quota_data").Save(quotaDataDB)
+			increaseQuotaData(quotaData.UserID, quotaData.Username, quotaData.ModelName, quotaData.Count, quotaData.Quota, quotaData.CreatedAt)
 		} else {
 			DB.Table("quota_data").Create(quotaData)
 		}
@@ -88,10 +93,21 @@ func SaveQuotaDataCache() {
 	common.SysLog(fmt.Sprintf("保存数据看板数据成功，共保存%d条数据", size))
 }

+func increaseQuotaData(userId int, username string, modelName string, count int, quota int, createdAt int64) {
+	err := DB.Table("quota_data").Where("user_id = ? and username = ? and model_name = ? and created_at = ?",
+		userId, username, modelName, createdAt).Updates(map[string]interface{}{
+		"count": gorm.Expr("count + ?", count),
+		"quota": gorm.Expr("quota + ?", quota),
+	}).Error
+	if err != nil {
+		common.SysLog(fmt.Sprintf("increaseQuotaData error: %s", err))
+	}
+}
+
 func GetQuotaDataByUsername(username string, startTime int64, endTime int64) (quotaData []*QuotaData, err error) {
 	var quotaDatas []*QuotaData
 	// 从quota_data表中查询数据
-	err = DB.Table("quota_data").Where("username = ?", username).Find(&quotaDatas).Error
+	err = DB.Table("quota_data").Where("username = ? and created_at >= ? and created_at <= ?", username, startTime, endTime).Find(&quotaDatas).Error
 	return quotaDatas, err
 }

--- a/model/user.go
+++ b/model/user.go
@@ -3,10 +3,11 @@ package model
 import (
 	"errors"
 	"fmt"
-	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
 	"time"
+
+	"gorm.io/gorm"
 )

 // User if you add sensitive fields, don't forget to clean them in setupLogin function.
@@ -21,12 +22,13 @@ type User struct {
 	Email            string         `json:"email" gorm:"index" validate:"max=50"`
 	GitHubId         string         `json:"github_id" gorm:"column:github_id;index"`
 	WeChatId         string         `json:"wechat_id" gorm:"column:wechat_id;index"`
+	TelegramId       string         `json:"telegram_id" gorm:"column:telegram_id;index"`
 	VerificationCode string         `json:"verification_code" gorm:"-:all"`                                    // this field is only for Email verification, don't save it to database!
 	AccessToken      string         `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
 	Quota            int            `json:"quota" gorm:"type:int;default:0"`
 	UsedQuota        int            `json:"used_quota" gorm:"type:int;default:0;column:used_quota"` // used quota
 	RequestCount     int            `json:"request_count" gorm:"type:int;default:0;"`               // request number
-	Group            string         `json:"group" gorm:"type:varchar(32);default:'default'"`
+	Group            string         `json:"group" gorm:"type:varchar(64);default:'default'"`
 	AffCode          string         `json:"aff_code" gorm:"type:varchar(32);column:aff_code;uniqueIndex"`
 	AffCount         int            `json:"aff_count" gorm:"type:int;default:0;column:aff_count"`
 	AffQuota         int            `json:"aff_quota" gorm:"type:int;default:0;column:aff_quota"`           // 邀请剩余额度
@@ -286,6 +288,17 @@ func (user *User) FillUserByUsername() error {
 	return nil
 }

+func (user *User) FillUserByTelegramId() error {
+	if user.TelegramId == "" {
+		return errors.New("Telegram id 为空！")
+	}
+	err := DB.Where(User{TelegramId: user.TelegramId}).First(user).Error
+	if errors.Is(err, gorm.ErrRecordNotFound) {
+		return errors.New("该 Telegram 账户未绑定")
+	}
+	return nil
+}
+
 func IsEmailAlreadyTaken(email string) bool {
 	return DB.Where("email = ?", email).Find(&User{}).RowsAffected == 1
 }
@@ -302,6 +315,10 @@ func IsUsernameAlreadyTaken(username string) bool {
 	return DB.Where("username = ?", username).Find(&User{}).RowsAffected == 1
 }

+func IsTelegramIdAlreadyTaken(telegramId string) bool {
+	return DB.Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
+}
+
 func ResetUserPasswordByEmail(email string, password string) error {
 	if email == "" || password == "" {
 		return errors.New("邮箱地址或密码为空！")
@@ -452,7 +469,7 @@ func updateUserRequestCount(id int, count int) {
 	}
 }

-func GetUsernameById(id int) (username string) {
-	DB.Model(&User{}).Where("id = ?", id).Select("username").Find(&username)
-	return username
+func GetUsernameById(id int) (username string, err error) {
+	err = DB.Model(&User{}).Where("id = ?", id).Select("username").Find(&username).Error
+	return username, err
 }
--- a/relay/channel/adapter.go
+++ b/relay/channel/adapter.go
@@ -0,0 +1,21 @@
+package channel
+
+import (
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor interface {
+	// Init IsStream bool
+	Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest)
+	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
+	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
+	ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error)
+	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode)
+	GetModelList() []string
+	GetChannelName() string
+}
--- 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/ali/adaptor.go
+++ b/relay/channel/ali/adaptor.go
@@ -0,0 +1,80 @@
+package ali
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	fullRequestURL := fmt.Sprintf("%s/api/v1/services/aigc/text-generation/generation", info.BaseUrl)
+	if info.RelayMode == constant.RelayModeEmbeddings {
+		fullRequestURL = fmt.Sprintf("%s/api/v1/services/embeddings/text-embedding/text-embedding", info.BaseUrl)
+	}
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	if info.IsStream {
+		req.Header.Set("X-DashScope-SSE", "enable")
+	}
+	if c.GetString("plugin") != "" {
+		req.Header.Set("X-DashScope-Plugin", c.GetString("plugin"))
+	}
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch relayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		baiduRequest := requestOpenAI2Ali(*request)
+		return baiduRequest, nil
+	}
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = aliStreamHandler(c, resp)
+	} else {
+		switch info.RelayMode {
+		case constant.RelayModeEmbeddings:
+			err, usage = aliEmbeddingHandler(c, resp)
+		default:
+			err, usage = aliHandler(c, resp)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/ali/constants.go
+++ b/relay/channel/ali/constants.go
@@ -0,0 +1,8 @@
+package ali
+
+var ModelList = []string{
+	"qwen-turbo", "qwen-plus", "qwen-max", "qwen-max-longcontext",
+	"text-embedding-v1",
+}
+
+var ChannelName = "ali"
--- a/relay/channel/ali/dto.go
+++ b/relay/channel/ali/dto.go
@@ -0,0 +1,70 @@
+package ali
+
+type AliMessage struct {
+	User string `json:"user"`
+	Bot  string `json:"bot"`
+}
+
+type AliInput struct {
+	Prompt  string       `json:"prompt"`
+	History []AliMessage `json:"history"`
+}
+
+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"`
+}
+
+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
+}
--- a/relay/channel/ali/relay-ali.go
+++ b/relay/channel/ali/relay-ali.go
@@ -1,4 +1,4 @@
-package controller
+package ali

 import (
 	"bufio"
@@ -7,98 +7,31 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	"one-api/service"
 	"strings"
 )

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

-type AliMessage struct {
-	User string `json:"user"`
-	Bot  string `json:"bot"`
-}
-
-type AliInput struct {
-	Prompt  string       `json:"prompt"`
-	History []AliMessage `json:"history"`
-}
-
-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"`
-}
-
-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
-}
-
-func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
+func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliChatRequest {
 	messages := make([]AliMessage, 0, len(request.Messages))
 	prompt := ""
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
 		if message.Role == "system" {
 			messages = append(messages, AliMessage{
-				User: string(message.Content),
+				User: message.StringContent(),
 				Bot:  "Okay",
 			})
 			continue
 		} else {
 			if i == len(request.Messages)-1 {
-				prompt = string(message.Content)
+				prompt = message.StringContent()
 				break
 			}
 			messages = append(messages, AliMessage{
-				User: string(message.Content),
+				User: message.StringContent(),
 				Bot:  string(request.Messages[i+1].Content),
 			})
 			i++
@@ -119,7 +52,7 @@ func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
 	}
 }

-func embeddingRequestOpenAI2Ali(request GeneralOpenAIRequest) *AliEmbeddingRequest {
+func embeddingRequestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliEmbeddingRequest {
 	return &AliEmbeddingRequest{
 		Model: "text-embedding-v1",
 		Input: struct {
@@ -130,21 +63,21 @@ func embeddingRequestOpenAI2Ali(request GeneralOpenAIRequest) *AliEmbeddingReque
 	}
 }

-func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var aliResponse AliEmbeddingResponse
 	err := json.NewDecoder(resp.Body).Decode(&aliResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}

 	if aliResponse.Code != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: aliResponse.Message,
 				Type:    aliResponse.Code,
 				Param:   aliResponse.RequestId,
@@ -157,7 +90,7 @@ 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 service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -165,16 +98,16 @@ func aliEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 	return nil, &fullTextResponse.Usage
 }

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

 	for _, item := range response.Output.Embeddings {
-		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, dto.OpenAIEmbeddingResponseItem{
 			Object:    `embedding`,
 			Index:     item.TextIndex,
 			Embedding: item.Embedding,
@@ -183,22 +116,22 @@ func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *OpenAIEmbeddin
 	return &openAIEmbeddingResponse
 }

-func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
+func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
 	content, _ := json.Marshal(response.Output.Text)
-	choice := OpenAITextResponseChoice{
+	choice := dto.OpenAITextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: dto.Message{
 			Role:    "assistant",
 			Content: content,
 		},
 		FinishReason: response.Output.FinishReason,
 	}
-	fullTextResponse := OpenAITextResponse{
+	fullTextResponse := dto.OpenAITextResponse{
 		Id:      response.RequestId,
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
-		Usage: Usage{
+		Choices: []dto.OpenAITextResponseChoice{choice},
+		Usage: dto.Usage{
 			PromptTokens:     response.Usage.InputTokens,
 			CompletionTokens: response.Usage.OutputTokens,
 			TotalTokens:      response.Usage.InputTokens + response.Usage.OutputTokens,
@@ -207,25 +140,25 @@ func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

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

-func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
+func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var usage dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -255,7 +188,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	lastResponseText := ""
 	c.Stream(func(w io.Writer) bool {
 		select {
@@ -288,28 +221,28 @@ 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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, &usage
 }

-func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func aliHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var aliResponse AliChatResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if aliResponse.Code != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: aliResponse.Message,
 				Type:    aliResponse.Code,
 				Param:   aliResponse.RequestId,
@@ -321,7 +254,7 @@ func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode
 	fullTextResponse := responseAli2OpenAI(&aliResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/api_request.go
+++ b/relay/channel/api_request.go
@@ -0,0 +1,52 @@
+package channel
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/relay/common"
+	"one-api/service"
+)
+
+func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Request) {
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+	if info.IsStream && c.Request.Header.Get("Accept") == "" {
+		req.Header.Set("Accept", "text/event-stream")
+	}
+}
+
+func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.GetRequestURL(info)
+	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, info)
+	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 := service.GetHttpClient().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/baidu/adaptor.go
+++ b/relay/channel/baidu/adaptor.go
@@ -0,0 +1,92 @@
+package baidu
+
+import (
+	"errors"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	var fullRequestURL string
+	switch info.UpstreamModelName {
+	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 = getBaiduAccessToken(info.ApiKey); err != nil {
+		return "", err
+	}
+	fullRequestURL += "?access_token=" + accessToken
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch relayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		baiduRequest := requestOpenAI2Baidu(*request)
+		return baiduRequest, nil
+	}
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = baiduStreamHandler(c, resp)
+	} else {
+		switch info.RelayMode {
+		case constant.RelayModeEmbeddings:
+			err, usage = baiduEmbeddingHandler(c, resp)
+		default:
+			err, usage = baiduHandler(c, resp)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/baidu/constants.go
+++ b/relay/channel/baidu/constants.go
@@ -0,0 +1,12 @@
+package baidu
+
+var ModelList = []string{
+	"ERNIE-Bot-4",
+	"ERNIE-Bot-8K",
+	"ERNIE-Bot",
+	"ERNIE-Speed",
+	"ERNIE-Bot-turbo",
+	"Embedding-V1",
+}
+
+var ChannelName = "baidu"
--- a/relay/channel/baidu/dto.go
+++ b/relay/channel/baidu/dto.go
@@ -0,0 +1,71 @@
+package baidu
+
+import (
+	"one-api/dto"
+	"time"
+)
+
+type BaiduMessage 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 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            dto.Usage `json:"usage"`
+	Error
+}
+
+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   dto.Usage            `json:"usage"`
+	Error
+}
+
+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:"-"`
+}
+
+type BaiduTokenResponse struct {
+	ExpiresIn   int    `json:"expires_in"`
+	AccessToken string `json:"access_token"`
+}
--- a/relay/channel/baidu/relay-baidu.go
+++ b/relay/channel/baidu/relay-baidu.go
@@ -1,4 +1,4 @@
-package controller
+package baidu

 import (
 	"bufio"
@@ -9,6 +9,9 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
 	"sync"
 	"time"
@@ -16,80 +19,15 @@ import (

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

-type BaiduTokenResponse struct {
-	ExpiresIn   int    `json:"expires_in"`
-	AccessToken string `json:"access_token"`
-}
-
-type BaiduMessage 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 BaiduError 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 {
+func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
 	messages := make([]BaiduMessage, 0, len(request.Messages))
 	for _, message := range request.Messages {
 		if message.Role == "system" {
 			messages = append(messages, BaiduMessage{
 				Role:    "user",
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 			messages = append(messages, BaiduMessage{
 				Role:    "assistant",
@@ -98,7 +36,7 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 		} else {
 			messages = append(messages, BaiduMessage{
 				Role:    message.Role,
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -108,57 +46,57 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 	}
 }

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

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

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

-func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbeddingResponse {
-	openAIEmbeddingResponse := OpenAIEmbeddingResponse{
+func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *dto.OpenAIEmbeddingResponse {
+	openAIEmbeddingResponse := dto.OpenAIEmbeddingResponse{
 		Object: "list",
-		Data:   make([]OpenAIEmbeddingResponseItem, 0, len(response.Data)),
+		Data:   make([]dto.OpenAIEmbeddingResponseItem, 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, dto.OpenAIEmbeddingResponseItem{
 			Object:    item.Object,
 			Index:     item.Index,
 			Embedding: item.Embedding,
@@ -167,8 +105,8 @@ func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbe
 	return &openAIEmbeddingResponse
 }

-func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage Usage
+func baiduStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var usage dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -195,7 +133,7 @@ func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -225,28 +163,28 @@ 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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, &usage
 }

-func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func baiduHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var baiduResponse BaiduChatResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: baiduResponse.ErrorMsg,
 				Type:    "baidu_error",
 				Param:   "",
@@ -258,7 +196,7 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	fullTextResponse := responseBaidu2OpenAI(&baiduResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -266,23 +204,23 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	return nil, &fullTextResponse.Usage
 }

-func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var baiduResponse BaiduEmbeddingResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: baiduResponse.ErrorMsg,
 				Type:    "baidu_error",
 				Param:   "",
@@ -294,7 +232,7 @@ 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 service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
@@ -337,7 +275,7 @@ 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 := service.GetImpatientHttpClient().Do(req)
 	if err != nil {
 		return nil, err
 	}
--- a/relay/channel/claude/adaptor.go
+++ b/relay/channel/claude/adaptor.go
@@ -0,0 +1,65 @@
+package claude
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/complete", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("x-api-key", info.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 *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = claudeStreamHandler(c, resp)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = claudeHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/claude/constants.go
+++ b/relay/channel/claude/constants.go
@@ -0,0 +1,7 @@
+package claude
+
+var ModelList = []string{
+	"claude-instant-1", "claude-2", "claude-2.0", "claude-2.1",
+}
+
+var ChannelName = "claude"
--- a/relay/channel/claude/dto.go
+++ b/relay/channel/claude/dto.go
@@ -0,0 +1,29 @@
+package claude
+
+type ClaudeMetadata struct {
+	UserId string `json:"user_id"`
+}
+
+type ClaudeRequest struct {
+	Model             string   `json:"model"`
+	Prompt            string   `json:"prompt"`
+	MaxTokensToSample uint     `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"`
+}
--- a/relay/channel/claude/relay-claude.go
+++ b/relay/channel/claude/relay-claude.go
@@ -1,4 +1,4 @@
-package controller
+package claude

 import (
 	"bufio"
@@ -8,37 +8,11 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	"one-api/service"
 	"strings"
 )

-type ClaudeMetadata struct {
-	UserId string `json:"user_id"`
-}
-
-type ClaudeRequest struct {
-	Model             string   `json:"model"`
-	Prompt            string   `json:"prompt"`
-	MaxTokensToSample uint     `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":
@@ -50,7 +24,7 @@ func stopReasonClaude2OpenAI(reason string) string {
 	}
 }

-func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
+func requestOpenAI2Claude(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
 	claudeRequest := ClaudeRequest{
 		Model:             textRequest.Model,
 		Prompt:            "",
@@ -78,41 +52,41 @@ func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
 	return &claudeRequest
 }

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

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

-func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func claudeStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	responseText := ""
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createdTime := common.GetTimestamp()
@@ -142,7 +116,7 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithS
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -172,28 +146,28 @@ 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 service.OpenAIErrorWrapper(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 claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	var claudeResponse ClaudeResponse
 	err = json.Unmarshal(responseBody, &claudeResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if claudeResponse.Error.Type != "" {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: claudeResponse.Error.Message,
 				Type:    claudeResponse.Error.Type,
 				Param:   "",
@@ -203,8 +177,8 @@ func claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 		}, nil
 	}
 	fullTextResponse := responseClaude2OpenAI(&claudeResponse)
-	completionTokens := countTokenText(claudeResponse.Completion, model)
-	usage := Usage{
+	completionTokens := service.CountTokenText(claudeResponse.Completion, model)
+	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -212,7 +186,7 @@ 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 service.OpenAIErrorWrapper(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/adaptor.go
+++ b/relay/channel/gemini/adaptor.go
@@ -0,0 +1,64 @@
+package gemini
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	version := "v1"
+	action := "generateContent"
+	if info.IsStream {
+		action = "streamGenerateContent"
+	}
+	return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("x-goog-api-key", info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return CovertGemini2OpenAI(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = geminiChatStreamHandler(c, resp)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/gemini/constant.go
+++ b/relay/channel/gemini/constant.go
@@ -0,0 +1,12 @@
+package gemini
+
+const (
+	GeminiVisionMaxImageNum = 16
+)
+
+var ModelList = []string{
+	"gemini-pro",
+	"gemini-pro-vision",
+}
+
+var ChannelName = "google gemini"
--- a/relay/channel/gemini/dto.go
+++ b/relay/channel/gemini/dto.go
@@ -0,0 +1,62 @@
+package gemini
+
+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 uint     `json:"maxOutputTokens,omitempty"`
+	CandidateCount  int      `json:"candidateCount,omitempty"`
+	StopSequences   []string `json:"stopSequences,omitempty"`
+}
+
+type GeminiChatCandidate struct {
+	Content       GeminiChatContent        `json:"content"`
+	FinishReason  string                   `json:"finishReason"`
+	Index         int64                    `json:"index"`
+	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+}
+
+type GeminiChatSafetyRating struct {
+	Category    string `json:"category"`
+	Probability string `json:"probability"`
+}
+
+type GeminiChatPromptFeedback struct {
+	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+}
+
+type GeminiChatResponse struct {
+	Candidates     []GeminiChatCandidate    `json:"candidates"`
+	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
+}
--- a/relay/channel/gemini/relay-gemini.go
+++ b/relay/channel/gemini/relay-gemini.go
@@ -1,4 +1,4 @@
-package controller
+package gemini

 import (
 	"bufio"
@@ -7,77 +7,36 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"

 	"github.com/gin-gonic/gin"
 )

-const (
-	GeminiVisionMaxImageNum = 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 uint     `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 {
+func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatRequest {
 	geminiRequest := GeminiChatRequest{
 		Contents: make([]GeminiChatContent, 0, len(textRequest.Messages)),
-		//SafetySettings: []GeminiChatSafetySettings{
-		//	{
-		//		Category:  "HARM_CATEGORY_HARASSMENT",
-		//		Threshold: "BLOCK_ONLY_HIGH",
-		//	},
-		//	{
-		//		Category:  "HARM_CATEGORY_HATE_SPEECH",
-		//		Threshold: "BLOCK_ONLY_HIGH",
-		//	},
-		//	{
-		//		Category:  "HARM_CATEGORY_SEXUALLY_EXPLICIT",
-		//		Threshold: "BLOCK_ONLY_HIGH",
-		//	},
-		//	{
-		//		Category:  "HARM_CATEGORY_DANGEROUS_CONTENT",
-		//		Threshold: "BLOCK_ONLY_HIGH",
-		//	},
-		//},
+		SafetySettings: []GeminiChatSafetySettings{
+			{
+				Category:  "HARM_CATEGORY_HARASSMENT",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_HATE_SPEECH",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_DANGEROUS_CONTENT",
+				Threshold: common.GeminiSafetySetting,
+			},
+		},
 		GenerationConfig: GeminiChatGenerationConfig{
 			Temperature:     textRequest.Temperature,
 			TopP:            textRequest.TopP,
@@ -97,7 +56,7 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
 			Role: message.Role,
 			Parts: []GeminiPart{
 				{
-					Text: string(message.Content),
+					Text: message.StringContent(),
 				},
 			},
 		}
@@ -106,16 +65,16 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
 		imageNum := 0
 		for _, part := range openaiContent {

-			if part.Type == ContentTypeText {
+			if part.Type == dto.ContentTypeText {
 				parts = append(parts, GeminiPart{
 					Text: part.Text,
 				})
-			} else if part.Type == ContentTypeImageURL {
+			} else if part.Type == dto.ContentTypeImageURL {
 				imageNum += 1
 				if imageNum > GeminiVisionMaxImageNum {
 					continue
 				}
-				mimeType, data, _ := common.GetImageFromUrl(part.ImageUrl.(MessageImageUrl).Url)
+				mimeType, data, _ := common.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
 				parts = append(parts, GeminiPart{
 					InlineData: &GeminiInlineData{
 						MimeType: mimeType,
@@ -154,11 +113,6 @@ func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
 	return &geminiRequest
 }

-type GeminiChatResponse struct {
-	Candidates     []GeminiChatCandidate    `json:"candidates"`
-	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
-}
-
 func (g *GeminiChatResponse) GetResponseText() string {
 	if g == nil {
 		return ""
@@ -169,38 +123,22 @@ 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 GeminiChatSafetyRating struct {
-	Category    string `json:"category"`
-	Probability string `json:"probability"`
-}
-
-type GeminiChatPromptFeedback struct {
-	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
-}
-
-func responseGeminiChat2OpenAI(response *GeminiChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
+func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResponse {
+	fullTextResponse := dto.OpenAITextResponse{
 		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Choices: make([]OpenAITextResponseChoice, 0, len(response.Candidates)),
+		Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.Candidates)),
 	}
 	content, _ := json.Marshal("")
 	for i, candidate := range response.Candidates {
-		choice := OpenAITextResponseChoice{
+		choice := dto.OpenAITextResponseChoice{
 			Index: i,
-			Message: Message{
+			Message: dto.Message{
 				Role:    "assistant",
 				Content: content,
 			},
-			FinishReason: stopFinishReason,
+			FinishReason: relaycommon.StopFinishReason,
 		}
 		content, _ = json.Marshal(candidate.Content.Parts[0].Text)
 		if len(candidate.Content.Parts) > 0 {
@@ -211,18 +149,18 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *OpenAITextResponse
 	return &fullTextResponse
 }

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

-func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	responseText := ""
 	dataChan := make(chan string)
 	stopChan := make(chan bool)
@@ -252,7 +190,7 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorW
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -264,14 +202,14 @@ 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 dto.ChatCompletionsStreamResponseChoice
 			choice.Delta.Content = dummy.Content
-			response := ChatCompletionsStreamResponse{
+			response := dto.ChatCompletionsStreamResponse{
 				Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
 				Object:  "chat.completion.chunk",
 				Created: common.GetTimestamp(),
 				Model:   "gemini-pro",
-				Choices: []ChatCompletionsStreamResponseChoice{choice},
+				Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
 			}
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
@@ -287,28 +225,28 @@ 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 service.OpenAIErrorWrapper(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 geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	var geminiResponse GeminiChatResponse
 	err = json.Unmarshal(responseBody, &geminiResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if len(geminiResponse.Candidates) == 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: "No candidates returned",
 				Type:    "server_error",
 				Param:   "",
@@ -318,8 +256,8 @@ func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, mo
 		}, nil
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
-	completionTokens := countTokenText(geminiResponse.GetResponseText(), model)
-	usage := Usage{
+	completionTokens := service.CountTokenText(geminiResponse.GetResponseText(), model)
+	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -327,7 +265,7 @@ 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 service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- 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 +1,95 @@
+package openai
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/ai360"
+	"one-api/relay/channel/moonshot"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+)
+
+type Adaptor struct {
+	ChannelType int
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+	a.ChannelType = info.ChannelType
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.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(info.RequestURLPath, "?")[0]
+		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
+		task := strings.TrimPrefix(requestURL, "/v1/")
+		model_ := info.UpstreamModelName
+		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 relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
+	}
+	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	if info.ChannelType == common.ChannelTypeAzure {
+		req.Header.Set("api-key", info.ApiKey)
+		return nil
+	}
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	if info.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 *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = OpenaiStreamHandler(c, resp, info.RelayMode)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	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 {
+	return ChannelName
+}
--- a/relay/channel/openai/constant.go
+++ b/relay/channel/openai/constant.go
@@ -0,0 +1,21 @@
+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",
+}
+
+var ChannelName = "openai"
--- a/relay/channel/openai/relay-openai.go
+++ b/relay/channel/openai/relay-openai.go
@@ -1,4 +1,4 @@
-package controller
+package openai

 import (
 	"bufio"
@@ -8,12 +8,15 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
 	"strings"
 	"sync"
 	"time"
 )

-func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*OpenAIErrorWithStatusCode, string) {
+func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string) {
 	var responseTextBuilder strings.Builder
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
@@ -54,8 +57,8 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 		}
 		streamResp := "[" + strings.Join(streamItems, ",") + "]"
 		switch relayMode {
-		case RelayModeChatCompletions:
-			var streamResponses []ChatCompletionsStreamResponseSimple
+		case relayconstant.RelayModeChatCompletions:
+			var streamResponses []dto.ChatCompletionsStreamResponseSimple
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
 				common.SysError("error unmarshalling stream response: " + err.Error())
@@ -66,8 +69,8 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 					responseTextBuilder.WriteString(choice.Delta.Content)
 				}
 			}
-		case RelayModeCompletions:
-			var streamResponses []CompletionsStreamResponse
+		case relayconstant.RelayModeCompletions:
+			var streamResponses []dto.CompletionsStreamResponse
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
 				common.SysError("error unmarshalling stream response: " + err.Error())
@@ -83,9 +86,9 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 			// wait data out
 			time.Sleep(2 * time.Second)
 		}
-		stopChan <- true
+		common.SafeSend(stopChan, true)
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -102,28 +105,28 @@ 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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	wg.Wait()
 	return nil, responseTextBuilder.String()
 }

-func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
-	var textResponse TextResponse
+func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var textResponse dto.TextResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if textResponse.Error.Type != "" {
-		return &OpenAIErrorWithStatusCode{
+		return &dto.OpenAIErrorWithStatusCode{
 			OpenAIError: textResponse.Error,
 			StatusCode:  resp.StatusCode,
 		}, nil
@@ -140,19 +143,19 @@ 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 service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}

 	if textResponse.Usage.TotalTokens == 0 {
 		completionTokens := 0
 		for _, choice := range textResponse.Choices {
-			completionTokens += countTokenText(string(choice.Message.Content), model)
+			completionTokens += service.CountTokenText(string(choice.Message.Content), model)
 		}
-		textResponse.Usage = Usage{
+		textResponse.Usage = dto.Usage{
 			PromptTokens:     promptTokens,
 			CompletionTokens: completionTokens,
 			TotalTokens:      promptTokens + completionTokens,
--- a/relay/channel/palm/adaptor.go
+++ b/relay/channel/palm/adaptor.go
@@ -0,0 +1,59 @@
+package palm
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1beta2/models/chat-bison-001:generateMessage", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("x-goog-api-key", info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = palmStreamHandler(c, resp)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = palmHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/palm/constants.go
+++ b/relay/channel/palm/constants.go
@@ -0,0 +1,7 @@
+package palm
+
+var ModelList = []string{
+	"PaLM-2",
+}
+
+var ChannelName = "google palm"
--- a/relay/channel/palm/dto.go
+++ b/relay/channel/palm/dto.go
@@ -0,0 +1,38 @@
+package palm
+
+import "one-api/dto"
+
+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           uint       `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   []dto.Message     `json:"messages"`
+	Filters    []PaLMFilter      `json:"filters"`
+	Error      PaLMError         `json:"error"`
+}
--- a/relay/channel/palm/relay-palm.go
+++ b/relay/channel/palm/relay-palm.go
@@ -1,4 +1,4 @@
-package controller
+package palm

 import (
 	"encoding/json"
@@ -7,47 +7,15 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 )

 // 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           uint       `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 {
+func requestOpenAI2PaLM(textRequest dto.GeneralOpenAIRequest) *PaLMChatRequest {
 	palmRequest := PaLMChatRequest{
 		Prompt: PaLMPrompt{
 			Messages: make([]PaLMChatMessage, 0, len(textRequest.Messages)),
@@ -59,7 +27,7 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 	}
 	for _, message := range textRequest.Messages {
 		palmMessage := PaLMChatMessage{
-			Content: string(message.Content),
+			Content: message.StringContent(),
 		}
 		if message.Role == "user" {
 			palmMessage.Author = "0"
@@ -71,15 +39,15 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 	return &palmRequest
 }

-func responsePaLM2OpenAI(response *PaLMChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
-		Choices: make([]OpenAITextResponseChoice, 0, len(response.Candidates)),
+func responsePaLM2OpenAI(response *PaLMChatResponse) *dto.OpenAITextResponse {
+	fullTextResponse := dto.OpenAITextResponse{
+		Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.Candidates)),
 	}
 	for i, candidate := range response.Candidates {
 		content, _ := json.Marshal(candidate.Content)
-		choice := OpenAITextResponseChoice{
+		choice := dto.OpenAITextResponseChoice{
 			Index: i,
-			Message: Message{
+			Message: dto.Message{
 				Role:    "assistant",
 				Content: content,
 			},
@@ -90,20 +58,20 @@ func responsePaLM2OpenAI(response *PaLMChatResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

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

-func palmStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func palmStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	responseText := ""
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createdTime := common.GetTimestamp()
@@ -144,7 +112,7 @@ func palmStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSta
 		dataChan <- string(jsonResponse)
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -157,28 +125,28 @@ 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 service.OpenAIErrorWrapper(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 palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	var palmResponse PaLMChatResponse
 	err = json.Unmarshal(responseBody, &palmResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if palmResponse.Error.Code != 0 || len(palmResponse.Candidates) == 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: palmResponse.Error.Message,
 				Type:    palmResponse.Error.Status,
 				Param:   "",
@@ -188,8 +156,8 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	completionTokens := countTokenText(palmResponse.Candidates[0].Content, model)
-	usage := Usage{
+	completionTokens := service.CountTokenText(palmResponse.Candidates[0].Content, model)
+	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
 		TotalTokens:      promptTokens + completionTokens,
@@ -197,7 +165,7 @@ 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 service.OpenAIErrorWrapper(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 +1,73 @@
+package tencent
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+)
+
+type Adaptor struct {
+	Sign string
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/hyllm/v1/chat/completions", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", a.Sign)
+	req.Header.Set("X-TC-Action", info.UpstreamModelName)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.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 := parseTencentConfig(apiKey)
+	if err != nil {
+		return nil, err
+	}
+	tencentRequest := requestOpenAI2Tencent(*request)
+	tencentRequest.AppId = appId
+	tencentRequest.SecretId = secretId
+	// we have to calculate the sign here
+	a.Sign = getTencentSign(*tencentRequest, secretKey)
+	return tencentRequest, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = tencentStreamHandler(c, resp)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = tencentHandler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/tencent/constants.go
+++ b/relay/channel/tencent/constants.go
@@ -0,0 +1,9 @@
+package tencent
+
+var ModelList = []string{
+	"ChatPro",
+	"ChatStd",
+	"hunyuan",
+}
+
+var ChannelName = "tencent"
--- a/relay/channel/tencent/dto.go
+++ b/relay/channel/tencent/dto.go
@@ -0,0 +1,61 @@
+package tencent
+
+import "one-api/dto"
+
+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   dto.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
+}
--- a/relay/channel/tencent/relay-tencent.go
+++ b/relay/channel/tencent/relay-tencent.go
@@ -1,4 +1,4 @@
-package controller
+package tencent

 import (
 	"bufio"
@@ -12,6 +12,9 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"sort"
 	"strconv"
 	"strings"
@@ -19,72 +22,14 @@ import (

 // 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 {
+func requestOpenAI2Tencent(request dto.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: string(message.Content),
+				Content: message.StringContent(),
 			})
 			messages = append(messages, TencentMessage{
 				Role:    "assistant",
@@ -93,7 +38,7 @@ func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
 			continue
 		}
 		messages = append(messages, TencentMessage{
-			Content: string(message.Content),
+			Content: message.StringContent(),
 			Role:    message.Role,
 		})
 	}
@@ -112,17 +57,17 @@ func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
 	}
 }

-func responseTencent2OpenAI(response *TencentChatResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
+func responseTencent2OpenAI(response *TencentChatResponse) *dto.OpenAITextResponse {
+	fullTextResponse := dto.OpenAITextResponse{
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
 		Usage:   response.Usage,
 	}
 	if len(response.Choices) > 0 {
 		content, _ := json.Marshal(response.Choices[0].Messages.Content)
-		choice := OpenAITextResponseChoice{
+		choice := dto.OpenAITextResponseChoice{
 			Index: 0,
-			Message: Message{
+			Message: dto.Message{
 				Role:    "assistant",
 				Content: content,
 			},
@@ -133,24 +78,24 @@ func responseTencent2OpenAI(response *TencentChatResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

-func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *ChatCompletionsStreamResponse {
-	response := ChatCompletionsStreamResponse{
+func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *dto.ChatCompletionsStreamResponse {
+	response := dto.ChatCompletionsStreamResponse{
 		Object:  "chat.completion.chunk",
 		Created: common.GetTimestamp(),
 		Model:   "tencent-hunyuan",
 	}
 	if len(TencentResponse.Choices) > 0 {
-		var choice ChatCompletionsStreamResponseChoice
+		var choice dto.ChatCompletionsStreamResponseChoice
 		choice.Delta.Content = TencentResponse.Choices[0].Delta.Content
 		if TencentResponse.Choices[0].FinishReason == "stop" {
-			choice.FinishReason = &stopFinishReason
+			choice.FinishReason = &relaycommon.StopFinishReason
 		}
 		response.Choices = append(response.Choices, choice)
 	}
 	return &response
 }

-func tencentStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+func tencentStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	var responseText string
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
@@ -181,7 +126,7 @@ func tencentStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWith
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -209,28 +154,28 @@ func tencentStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWith
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
 	return nil, responseText
 }

-func tencentHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func tencentHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var TencentResponse TencentChatResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(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
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if TencentResponse.Error.Code != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: TencentResponse.Error.Message,
 				Code:    TencentResponse.Error.Code,
 			},
@@ -240,7 +185,7 @@ func tencentHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatus
 	fullTextResponse := responseTencent2OpenAI(&TencentResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/xunfei/adaptor.go
+++ b/relay/channel/xunfei/adaptor.go
@@ -0,0 +1,68 @@
+package xunfei
+
+import (
+	"errors"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+)
+
+type Adaptor struct {
+	request *dto.GeneralOpenAIRequest
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return "", nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	a.request = request
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	// xunfei's request is not http request, so we don't need to do anything here
+	dummyResp := &http.Response{}
+	dummyResp.StatusCode = http.StatusOK
+	return dummyResp, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	splits := strings.Split(info.ApiKey, "|")
+	if len(splits) != 3 {
+		return nil, service.OpenAIErrorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
+	}
+	if a.request == nil {
+		return nil, service.OpenAIErrorWrapper(errors.New("request is nil"), "request_is_nil", http.StatusBadRequest)
+	}
+	if info.IsStream {
+		err, usage = xunfeiStreamHandler(c, *a.request, splits[0], splits[1], splits[2])
+	} else {
+		err, usage = xunfeiHandler(c, *a.request, splits[0], splits[1], splits[2])
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/xunfei/constants.go
+++ b/relay/channel/xunfei/constants.go
@@ -0,0 +1,11 @@
+package xunfei
+
+var ModelList = []string{
+	"SparkDesk",
+	"SparkDesk-v1.1",
+	"SparkDesk-v2.1",
+	"SparkDesk-v3.1",
+	"SparkDesk-v3.5",
+}
+
+var ChannelName = "xunfei"
--- a/relay/channel/xunfei/dto.go
+++ b/relay/channel/xunfei/dto.go
@@ -0,0 +1,59 @@
+package xunfei
+
+import "one-api/dto"
+
+type XunfeiMessage struct {
+	Role    string `json:"role"`
+	Content string `json:"content"`
+}
+
+type XunfeiChatRequest struct {
+	Header struct {
+		AppId string `json:"app_id"`
+	} `json:"header"`
+	Parameter struct {
+		Chat struct {
+			Domain      string  `json:"domain,omitempty"`
+			Temperature float64 `json:"temperature,omitempty"`
+			TopK        int     `json:"top_k,omitempty"`
+			MaxTokens   uint    `json:"max_tokens,omitempty"`
+			Auditing    bool    `json:"auditing,omitempty"`
+		} `json:"chat"`
+	} `json:"parameter"`
+	Payload struct {
+		Message struct {
+			Text []XunfeiMessage `json:"text"`
+		} `json:"message"`
+	} `json:"payload"`
+}
+
+type XunfeiChatResponseTextItem struct {
+	Content string `json:"content"`
+	Role    string `json:"role"`
+	Index   int    `json:"index"`
+}
+
+type XunfeiChatResponse struct {
+	Header struct {
+		Code    int    `json:"code"`
+		Message string `json:"message"`
+		Sid     string `json:"sid"`
+		Status  int    `json:"status"`
+	} `json:"header"`
+	Payload struct {
+		Choices struct {
+			Status int                          `json:"status"`
+			Seq    int                          `json:"seq"`
+			Text   []XunfeiChatResponseTextItem `json:"text"`
+		} `json:"choices"`
+		Usage struct {
+			//Text struct {
+			//	QuestionTokens   string `json:"question_tokens"`
+			//	PromptTokens     string `json:"prompt_tokens"`
+			//	CompletionTokens string `json:"completion_tokens"`
+			//	TotalTokens      string `json:"total_tokens"`
+			//} `json:"text"`
+			Text dto.Usage `json:"text"`
+		} `json:"usage"`
+	} `json:"payload"`
+}
--- a/relay/channel/xunfei/relay-xunfei.go
+++ b/relay/channel/xunfei/relay-xunfei.go
@@ -1,4 +1,4 @@
-package controller
+package xunfei

 import (
 	"crypto/hmac"
@@ -12,6 +12,9 @@ import (
 	"net/http"
 	"net/url"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
 	"time"
 )
@@ -19,69 +22,13 @@ import (
 // https://console.xfyun.cn/services/cbm
 // https://www.xfyun.cn/doc/spark/Web.html

-type XunfeiMessage struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
-}
-
-type XunfeiChatRequest struct {
-	Header struct {
-		AppId string `json:"app_id"`
-	} `json:"header"`
-	Parameter struct {
-		Chat struct {
-			Domain      string  `json:"domain,omitempty"`
-			Temperature float64 `json:"temperature,omitempty"`
-			TopK        int     `json:"top_k,omitempty"`
-			MaxTokens   uint    `json:"max_tokens,omitempty"`
-			Auditing    bool    `json:"auditing,omitempty"`
-		} `json:"chat"`
-	} `json:"parameter"`
-	Payload struct {
-		Message struct {
-			Text []XunfeiMessage `json:"text"`
-		} `json:"message"`
-	} `json:"payload"`
-}
-
-type XunfeiChatResponseTextItem struct {
-	Content string `json:"content"`
-	Role    string `json:"role"`
-	Index   int    `json:"index"`
-}
-
-type XunfeiChatResponse struct {
-	Header struct {
-		Code    int    `json:"code"`
-		Message string `json:"message"`
-		Sid     string `json:"sid"`
-		Status  int    `json:"status"`
-	} `json:"header"`
-	Payload struct {
-		Choices struct {
-			Status int                          `json:"status"`
-			Seq    int                          `json:"seq"`
-			Text   []XunfeiChatResponseTextItem `json:"text"`
-		} `json:"choices"`
-		Usage struct {
-			//Text struct {
-			//	QuestionTokens   string `json:"question_tokens"`
-			//	PromptTokens     string `json:"prompt_tokens"`
-			//	CompletionTokens string `json:"completion_tokens"`
-			//	TotalTokens      string `json:"total_tokens"`
-			//} `json:"text"`
-			Text Usage `json:"text"`
-		} `json:"usage"`
-	} `json:"payload"`
-}
-
-func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, domain string) *XunfeiChatRequest {
+func requestOpenAI2Xunfei(request dto.GeneralOpenAIRequest, xunfeiAppId string, domain string) *XunfeiChatRequest {
 	messages := make([]XunfeiMessage, 0, len(request.Messages))
 	for _, message := range request.Messages {
 		if message.Role == "system" {
 			messages = append(messages, XunfeiMessage{
 				Role:    "user",
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 			messages = append(messages, XunfeiMessage{
 				Role:    "assistant",
@@ -90,7 +37,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 		} else {
 			messages = append(messages, XunfeiMessage{
 				Role:    message.Role,
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -104,7 +51,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 	return &xunfeiRequest
 }

-func responseXunfei2OpenAI(response *XunfeiChatResponse) *OpenAITextResponse {
+func responseXunfei2OpenAI(response *XunfeiChatResponse) *dto.OpenAITextResponse {
 	if len(response.Payload.Choices.Text) == 0 {
 		response.Payload.Choices.Text = []XunfeiChatResponseTextItem{
 			{
@@ -113,24 +60,24 @@ func responseXunfei2OpenAI(response *XunfeiChatResponse) *OpenAITextResponse {
 		}
 	}
 	content, _ := json.Marshal(response.Payload.Choices.Text[0].Content)
-	choice := OpenAITextResponseChoice{
+	choice := dto.OpenAITextResponseChoice{
 		Index: 0,
-		Message: Message{
+		Message: dto.Message{
 			Role:    "assistant",
 			Content: content,
 		},
-		FinishReason: stopFinishReason,
+		FinishReason: relaycommon.StopFinishReason,
 	}
-	fullTextResponse := OpenAITextResponse{
+	fullTextResponse := dto.OpenAITextResponse{
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Choices: []OpenAITextResponseChoice{choice},
+		Choices: []dto.OpenAITextResponseChoice{choice},
 		Usage:   response.Payload.Usage.Text,
 	}
 	return &fullTextResponse
 }

-func streamResponseXunfei2OpenAI(xunfeiResponse *XunfeiChatResponse) *ChatCompletionsStreamResponse {
+func streamResponseXunfei2OpenAI(xunfeiResponse *XunfeiChatResponse) *dto.ChatCompletionsStreamResponse {
 	if len(xunfeiResponse.Payload.Choices.Text) == 0 {
 		xunfeiResponse.Payload.Choices.Text = []XunfeiChatResponseTextItem{
 			{
@@ -138,16 +85,16 @@ func streamResponseXunfei2OpenAI(xunfeiResponse *XunfeiChatResponse) *ChatComple
 			},
 		}
 	}
-	var choice ChatCompletionsStreamResponseChoice
+	var choice dto.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = xunfeiResponse.Payload.Choices.Text[0].Content
 	if xunfeiResponse.Payload.Choices.Status == 2 {
-		choice.FinishReason = &stopFinishReason
+		choice.FinishReason = &relaycommon.StopFinishReason
 	}
-	response := ChatCompletionsStreamResponse{
+	response := dto.ChatCompletionsStreamResponse{
 		Object:  "chat.completion.chunk",
 		Created: common.GetTimestamp(),
 		Model:   "SparkDesk",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response
 }
@@ -178,14 +125,14 @@ func buildXunfeiAuthUrl(hostUrl string, apiKey, apiSecret string) string {
 	return callUrl
 }

-func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+func xunfeiStreamHandler(c *gin.Context, textRequest dto.GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
 	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
 	if err != nil {
-		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
 	}
-	setEventStreamHeaders(c)
-	var usage Usage
+	service.SetEventStreamHeaders(c)
+	var usage dto.Usage
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case xunfeiResponse := <-dataChan:
@@ -208,13 +155,13 @@ func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId
 	return nil, &usage
 }

-func xunfeiHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+func xunfeiHandler(c *gin.Context, textRequest dto.GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
 	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
 	if err != nil {
-		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
 	}
-	var usage Usage
+	var usage dto.Usage
 	var content string
 	var xunfeiResponse XunfeiChatResponse
 	stop := false
@@ -237,14 +184,14 @@ func xunfeiHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId strin
 	response := responseXunfei2OpenAI(&xunfeiResponse)
 	jsonResponse, err := json.Marshal(response)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	_, _ = c.Writer.Write(jsonResponse)
 	return nil, &usage
 }

-func xunfeiMakeRequest(textRequest GeneralOpenAIRequest, domain, authUrl, appId string) (chan XunfeiChatResponse, chan bool, error) {
+func xunfeiMakeRequest(textRequest dto.GeneralOpenAIRequest, domain, authUrl, appId string) (chan XunfeiChatResponse, chan bool, error) {
 	d := websocket.Dialer{
 		HandshakeTimeout: 5 * time.Second,
 	}
--- a/relay/channel/zhipu/adaptor.go
+++ b/relay/channel/zhipu/adaptor.go
@@ -0,0 +1,61 @@
+package zhipu
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	method := "invoke"
+	if info.IsStream {
+		method = "sse-invoke"
+	}
+	return fmt.Sprintf("%s/api/paas/v3/model-api/%s/%s", info.BaseUrl, info.UpstreamModelName, method), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	token := getZhipuToken(info.ApiKey)
+	req.Header.Set("Authorization", token)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return requestOpenAI2Zhipu(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = zhipuStreamHandler(c, resp)
+	} else {
+		err, usage = zhipuHandler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/zhipu/constants.go
+++ b/relay/channel/zhipu/constants.go
@@ -0,0 +1,7 @@
+package zhipu
+
+var ModelList = []string{
+	"chatglm_turbo", "chatglm_pro", "chatglm_std", "chatglm_lite",
+}
+
+var ChannelName = "zhipu"
--- a/relay/channel/zhipu/dto.go
+++ b/relay/channel/zhipu/dto.go
@@ -0,0 +1,46 @@
+package zhipu
+
+import (
+	"one-api/dto"
+	"time"
+)
+
+type ZhipuMessage struct {
+	Role    string `json:"role"`
+	Content string `json:"content"`
+}
+
+type ZhipuRequest struct {
+	Prompt      []ZhipuMessage `json:"prompt"`
+	Temperature float64        `json:"temperature,omitempty"`
+	TopP        float64        `json:"top_p,omitempty"`
+	RequestId   string         `json:"request_id,omitempty"`
+	Incremental bool           `json:"incremental,omitempty"`
+}
+
+type ZhipuResponseData struct {
+	TaskId     string         `json:"task_id"`
+	RequestId  string         `json:"request_id"`
+	TaskStatus string         `json:"task_status"`
+	Choices    []ZhipuMessage `json:"choices"`
+	dto.Usage  `json:"usage"`
+}
+
+type ZhipuResponse struct {
+	Code    int               `json:"code"`
+	Msg     string            `json:"msg"`
+	Success bool              `json:"success"`
+	Data    ZhipuResponseData `json:"data"`
+}
+
+type ZhipuStreamMetaResponse struct {
+	RequestId  string `json:"request_id"`
+	TaskId     string `json:"task_id"`
+	TaskStatus string `json:"task_status"`
+	dto.Usage  `json:"usage"`
+}
+
+type zhipuTokenData struct {
+	Token      string
+	ExpiryTime time.Time
+}
--- a/relay/channel/zhipu/relay-zhipu.go
+++ b/relay/channel/zhipu/relay-zhipu.go
@@ -1,4 +1,4 @@
-package controller
+package zhipu

 import (
 	"bufio"
@@ -8,6 +8,9 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
 	"sync"
 	"time"
@@ -18,46 +21,6 @@ import (
 // https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/invoke
 // https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/sse-invoke

-type ZhipuMessage struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
-}
-
-type ZhipuRequest struct {
-	Prompt      []ZhipuMessage `json:"prompt"`
-	Temperature float64        `json:"temperature,omitempty"`
-	TopP        float64        `json:"top_p,omitempty"`
-	RequestId   string         `json:"request_id,omitempty"`
-	Incremental bool           `json:"incremental,omitempty"`
-}
-
-type ZhipuResponseData struct {
-	TaskId     string         `json:"task_id"`
-	RequestId  string         `json:"request_id"`
-	TaskStatus string         `json:"task_status"`
-	Choices    []ZhipuMessage `json:"choices"`
-	Usage      `json:"usage"`
-}
-
-type ZhipuResponse struct {
-	Code    int               `json:"code"`
-	Msg     string            `json:"msg"`
-	Success bool              `json:"success"`
-	Data    ZhipuResponseData `json:"data"`
-}
-
-type ZhipuStreamMetaResponse struct {
-	RequestId  string `json:"request_id"`
-	TaskId     string `json:"task_id"`
-	TaskStatus string `json:"task_status"`
-	Usage      `json:"usage"`
-}
-
-type zhipuTokenData struct {
-	Token      string
-	ExpiryTime time.Time
-}
-
 var zhipuTokens sync.Map
 var expSeconds int64 = 24 * 3600

@@ -108,13 +71,13 @@ func getZhipuToken(apikey string) string {
 	return tokenString
 }

-func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
+func requestOpenAI2Zhipu(request dto.GeneralOpenAIRequest) *ZhipuRequest {
 	messages := make([]ZhipuMessage, 0, len(request.Messages))
 	for _, message := range request.Messages {
 		if message.Role == "system" {
 			messages = append(messages, ZhipuMessage{
 				Role:    "system",
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 			messages = append(messages, ZhipuMessage{
 				Role:    "user",
@@ -123,7 +86,7 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 		} else {
 			messages = append(messages, ZhipuMessage{
 				Role:    message.Role,
-				Content: string(message.Content),
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -135,19 +98,19 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 	}
 }

-func responseZhipu2OpenAI(response *ZhipuResponse) *OpenAITextResponse {
-	fullTextResponse := OpenAITextResponse{
+func responseZhipu2OpenAI(response *ZhipuResponse) *dto.OpenAITextResponse {
+	fullTextResponse := dto.OpenAITextResponse{
 		Id:      response.Data.TaskId,
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Choices: make([]OpenAITextResponseChoice, 0, len(response.Data.Choices)),
+		Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.Data.Choices)),
 		Usage:   response.Data.Usage,
 	}
 	for i, choice := range response.Data.Choices {
 		content, _ := json.Marshal(strings.Trim(choice.Content, "\""))
-		openaiChoice := OpenAITextResponseChoice{
+		openaiChoice := dto.OpenAITextResponseChoice{
 			Index: i,
-			Message: Message{
+			Message: dto.Message{
 				Role:    choice.Role,
 				Content: content,
 			},
@@ -161,34 +124,34 @@ func responseZhipu2OpenAI(response *ZhipuResponse) *OpenAITextResponse {
 	return &fullTextResponse
 }

-func streamResponseZhipu2OpenAI(zhipuResponse string) *ChatCompletionsStreamResponse {
-	var choice ChatCompletionsStreamResponseChoice
+func streamResponseZhipu2OpenAI(zhipuResponse string) *dto.ChatCompletionsStreamResponse {
+	var choice dto.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = zhipuResponse
-	response := ChatCompletionsStreamResponse{
+	response := dto.ChatCompletionsStreamResponse{
 		Object:  "chat.completion.chunk",
 		Created: common.GetTimestamp(),
 		Model:   "chatglm",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response
 }

-func streamMetaResponseZhipu2OpenAI(zhipuResponse *ZhipuStreamMetaResponse) (*ChatCompletionsStreamResponse, *Usage) {
-	var choice ChatCompletionsStreamResponseChoice
+func streamMetaResponseZhipu2OpenAI(zhipuResponse *ZhipuStreamMetaResponse) (*dto.ChatCompletionsStreamResponse, *dto.Usage) {
+	var choice dto.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = ""
-	choice.FinishReason = &stopFinishReason
-	response := ChatCompletionsStreamResponse{
+	choice.FinishReason = &relaycommon.StopFinishReason
+	response := dto.ChatCompletionsStreamResponse{
 		Id:      zhipuResponse.RequestId,
 		Object:  "chat.completion.chunk",
 		Created: common.GetTimestamp(),
 		Model:   "chatglm",
-		Choices: []ChatCompletionsStreamResponseChoice{choice},
+		Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response, &zhipuResponse.Usage
 }

-func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var usage *Usage
+func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var usage *dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -225,7 +188,7 @@ func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithSt
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
+	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -260,28 +223,28 @@ func zhipuStreamHandler(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, usage
 }

-func zhipuHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+func zhipuHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var zhipuResponse ZhipuResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(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 service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	err = json.Unmarshal(responseBody, &zhipuResponse)
 	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if !zhipuResponse.Success {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: dto.OpenAIError{
 				Message: zhipuResponse.Msg,
 				Type:    "zhipu_error",
 				Param:   "",
@@ -293,7 +256,7 @@ func zhipuHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	fullTextResponse := responseZhipu2OpenAI(&zhipuResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
--- a/relay/channel/zhipu_4v/adaptor.go
+++ b/relay/channel/zhipu_4v/adaptor.go
@@ -0,0 +1,61 @@
+package zhipu_4v
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/api/paas/v4/chat/completions", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	token := getZhipuToken(info.ApiKey)
+	req.Header.Set("Authorization", token)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return requestOpenAI2Zhipu(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		var responseText string
+		err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
+		usage = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}
--- a/relay/channel/zhipu_4v/constants.go
+++ b/relay/channel/zhipu_4v/constants.go
@@ -0,0 +1,7 @@
+package zhipu_4v
+
+var ModelList = []string{
+	"glm-4", "glm-4v", "glm-3-turbo",
+}
+
+var ChannelName = "zhipu_4v"
--- a/relay/channel/zhipu_4v/dto.go
+++ b/relay/channel/zhipu_4v/dto.go
@@ -0,0 +1,59 @@
+package zhipu_4v
+
+import (
+	"one-api/dto"
+	"time"
+)
+
+//	type ZhipuMessage struct {
+//		Role       string `json:"role,omitempty"`
+//		Content    string `json:"content,omitempty"`
+//		ToolCalls  any    `json:"tool_calls,omitempty"`
+//		ToolCallId any    `json:"tool_call_id,omitempty"`
+//	}
+//
+//	type ZhipuRequest struct {
+//		Model       string         `json:"model"`
+//		Stream      bool           `json:"stream,omitempty"`
+//		Messages    []ZhipuMessage `json:"messages"`
+//		Temperature float64        `json:"temperature,omitempty"`
+//		TopP        float64        `json:"top_p,omitempty"`
+//		MaxTokens   int            `json:"max_tokens,omitempty"`
+//		Stop        []string       `json:"stop,omitempty"`
+//		RequestId   string         `json:"request_id,omitempty"`
+//		Tools       any            `json:"tools,omitempty"`
+//		ToolChoice  any            `json:"tool_choice,omitempty"`
+//	}
+//
+//	type ZhipuV4TextResponseChoice struct {
+//		Index        int `json:"index"`
+//		ZhipuMessage `json:"message"`
+//		FinishReason string `json:"finish_reason"`
+//	}
+type ZhipuV4Response struct {
+	Id                  string                         `json:"id"`
+	Created             int64                          `json:"created"`
+	Model               string                         `json:"model"`
+	TextResponseChoices []dto.OpenAITextResponseChoice `json:"choices"`
+	Usage               dto.Usage                      `json:"usage"`
+	Error               dto.OpenAIError                `json:"error"`
+}
+
+//
+//type ZhipuV4StreamResponseChoice struct {
+//	Index        int          `json:"index,omitempty"`
+//	Delta        ZhipuMessage `json:"delta"`
+//	FinishReason *string      `json:"finish_reason,omitempty"`
+//}
+
+type ZhipuV4StreamResponse struct {
+	Id      string                                    `json:"id"`
+	Created int64                                     `json:"created"`
+	Choices []dto.ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage   dto.Usage                                 `json:"usage"`
+}
+
+type tokenData struct {
+	Token      string
+	ExpiryTime time.Time
+}
--- a/relay/channel/zhipu_4v/relay-zhipu_v4.go
+++ b/relay/channel/zhipu_4v/relay-zhipu_v4.go
@@ -0,0 +1,262 @@
+package zhipu_4v
+
+import (
+	"bufio"
+	"bytes"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"github.com/golang-jwt/jwt"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/service"
+	"strings"
+	"sync"
+	"time"
+)
+
+// https://open.bigmodel.cn/doc/api#chatglm_std
+// chatglm_std, chatglm_lite
+// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/invoke
+// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/sse-invoke
+
+var zhipuTokens sync.Map
+var expSeconds int64 = 24 * 3600
+
+func getZhipuToken(apikey string) string {
+	data, ok := zhipuTokens.Load(apikey)
+	if ok {
+		tokenData := data.(tokenData)
+		if time.Now().Before(tokenData.ExpiryTime) {
+			return tokenData.Token
+		}
+	}
+
+	split := strings.Split(apikey, ".")
+	if len(split) != 2 {
+		common.SysError("invalid zhipu key: " + apikey)
+		return ""
+	}
+
+	id := split[0]
+	secret := split[1]
+
+	expMillis := time.Now().Add(time.Duration(expSeconds)*time.Second).UnixNano() / 1e6
+	expiryTime := time.Now().Add(time.Duration(expSeconds) * time.Second)
+
+	timestamp := time.Now().UnixNano() / 1e6
+
+	payload := jwt.MapClaims{
+		"api_key":   id,
+		"exp":       expMillis,
+		"timestamp": timestamp,
+	}
+
+	token := jwt.NewWithClaims(jwt.SigningMethodHS256, payload)
+
+	token.Header["alg"] = "HS256"
+	token.Header["sign_type"] = "SIGN"
+
+	tokenString, err := token.SignedString([]byte(secret))
+	if err != nil {
+		return ""
+	}
+
+	zhipuTokens.Store(apikey, tokenData{
+		Token:      tokenString,
+		ExpiryTime: expiryTime,
+	})
+
+	return tokenString
+}
+
+func requestOpenAI2Zhipu(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIRequest {
+	messages := make([]dto.Message, 0, len(request.Messages))
+	for _, message := range request.Messages {
+		messages = append(messages, dto.Message{
+			Role:       message.Role,
+			Content:    message.Content,
+			ToolCalls:  message.ToolCalls,
+			ToolCallId: message.ToolCallId,
+		})
+	}
+	str, ok := request.Stop.(string)
+	var Stop []string
+	if ok {
+		Stop = []string{str}
+	} else {
+		Stop, _ = request.Stop.([]string)
+	}
+	return &dto.GeneralOpenAIRequest{
+		Model:       request.Model,
+		Stream:      request.Stream,
+		Messages:    messages,
+		Temperature: request.Temperature,
+		TopP:        request.TopP,
+		MaxTokens:   request.MaxTokens,
+		Stop:        Stop,
+		Tools:       request.Tools,
+		ToolChoice:  request.ToolChoice,
+	}
+}
+
+//func responseZhipu2OpenAI(response *dto.OpenAITextResponse) *dto.OpenAITextResponse {
+//	fullTextResponse := dto.OpenAITextResponse{
+//		Id:      response.Id,
+//		Object:  "chat.completion",
+//		Created: common.GetTimestamp(),
+//		Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.TextResponseChoices)),
+//		Usage:   response.Usage,
+//	}
+//	for i, choice := range response.TextResponseChoices {
+//		content, _ := json.Marshal(strings.Trim(choice.Content, "\""))
+//		openaiChoice := dto.OpenAITextResponseChoice{
+//			Index: i,
+//			Message: dto.Message{
+//				Role:    choice.Role,
+//				Content: content,
+//			},
+//			FinishReason: "",
+//		}
+//		if i == len(response.TextResponseChoices)-1 {
+//			openaiChoice.FinishReason = "stop"
+//		}
+//		fullTextResponse.Choices = append(fullTextResponse.Choices, openaiChoice)
+//	}
+//	return &fullTextResponse
+//}
+
+func streamResponseZhipu2OpenAI(zhipuResponse *ZhipuV4StreamResponse) *dto.ChatCompletionsStreamResponse {
+	var choice dto.ChatCompletionsStreamResponseChoice
+	choice.Delta.Content = zhipuResponse.Choices[0].Delta.Content
+	choice.Delta.Role = zhipuResponse.Choices[0].Delta.Role
+	choice.Delta.ToolCalls = zhipuResponse.Choices[0].Delta.ToolCalls
+	choice.Index = zhipuResponse.Choices[0].Index
+	choice.FinishReason = zhipuResponse.Choices[0].FinishReason
+	response := dto.ChatCompletionsStreamResponse{
+		Id:      zhipuResponse.Id,
+		Object:  "chat.completion.chunk",
+		Created: zhipuResponse.Created,
+		Model:   "glm-4",
+		Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
+	}
+	return &response
+}
+
+func lastStreamResponseZhipuV42OpenAI(zhipuResponse *ZhipuV4StreamResponse) (*dto.ChatCompletionsStreamResponse, *dto.Usage) {
+	response := streamResponseZhipu2OpenAI(zhipuResponse)
+	return response, &zhipuResponse.Usage
+}
+
+func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var usage *dto.Usage
+	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) < 6 { // ignore blank line or wrong format
+				continue
+			}
+			if data[:6] != "data: " && data[:6] != "[DONE]" {
+				continue
+			}
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	service.SetEventStreamHeaders(c)
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			if strings.HasPrefix(data, "data: [DONE]") {
+				data = data[:12]
+			}
+			// some implementations may add \r at the end of data
+			data = strings.TrimSuffix(data, "\r")
+
+			var streamResponse ZhipuV4StreamResponse
+			err := json.Unmarshal([]byte(data), &streamResponse)
+			if err != nil {
+				common.SysError("error unmarshalling stream response: " + err.Error())
+			}
+			var response *dto.ChatCompletionsStreamResponse
+			if strings.Contains(data, "prompt_tokens") {
+				response, usage = lastStreamResponseZhipuV42OpenAI(&streamResponse)
+			} else {
+				response = streamResponseZhipu2OpenAI(&streamResponse)
+			}
+			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:
+			return false
+		}
+	})
+	err := resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	return nil, usage
+}
+
+func zhipuHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var textResponse ZhipuV4Response
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if textResponse.Error.Type != "" {
+		return &dto.OpenAIErrorWithStatusCode{
+			OpenAIError: textResponse.Error,
+			StatusCode:  resp.StatusCode,
+		}, nil
+	}
+	// Reset response body
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+
+	// 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.
+	// 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])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	return nil, &textResponse.Usage
+}
--- a/relay/common/relay_info.go
+++ b/relay/common/relay_info.go
@@ -0,0 +1,71 @@
+package common
+
+import (
+	"github.com/gin-gonic/gin"
+	"one-api/common"
+	"one-api/relay/constant"
+	"strings"
+	"time"
+)
+
+type RelayInfo struct {
+	ChannelType       int
+	ChannelId         int
+	TokenId           int
+	UserId            int
+	Group             string
+	TokenUnlimited    bool
+	StartTime         time.Time
+	ApiType           int
+	IsStream          bool
+	RelayMode         int
+	UpstreamModelName string
+	RequestURLPath    string
+	ApiVersion        string
+	PromptTokens      int
+	ApiKey            string
+	BaseUrl           string
+}
+
+func GenRelayInfo(c *gin.Context) *RelayInfo {
+	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
+	tokenId := c.GetInt("token_id")
+	userId := c.GetInt("id")
+	group := c.GetString("group")
+	tokenUnlimited := c.GetBool("token_unlimited_quota")
+	startTime := time.Now()
+
+	apiType := constant.ChannelType2APIType(channelType)
+
+	info := &RelayInfo{
+		RelayMode:      constant.Path2RelayMode(c.Request.URL.Path),
+		BaseUrl:        c.GetString("base_url"),
+		RequestURLPath: c.Request.URL.String(),
+		ChannelType:    channelType,
+		ChannelId:      channelId,
+		TokenId:        tokenId,
+		UserId:         userId,
+		Group:          group,
+		TokenUnlimited: tokenUnlimited,
+		StartTime:      startTime,
+		ApiType:        apiType,
+		ApiVersion:     c.GetString("api_version"),
+		ApiKey:         strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
+	}
+	if info.BaseUrl == "" {
+		info.BaseUrl = common.ChannelBaseURLs[channelType]
+	}
+	if info.ChannelType == common.ChannelTypeAzure {
+		info.ApiVersion = GetAzureAPIVersion(c)
+	}
+	return info
+}
+
+func (info *RelayInfo) SetPromptTokens(promptTokens int) {
+	info.PromptTokens = promptTokens
+}
+
+func (info *RelayInfo) SetIsStream(isStream bool) {
+	info.IsStream = isStream
+}
--- a/relay/common/relay_utils.go
+++ b/relay/common/relay_utils.go
@@ -0,0 +1,77 @@
+package common
+
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"strconv"
+	"strings"
+)
+
+var StopFinishReason = "stop"
+
+func RelayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *dto.OpenAIErrorWithStatusCode) {
+	openAIErrorWithStatusCode = &dto.OpenAIErrorWithStatusCode{
+		StatusCode: resp.StatusCode,
+		OpenAIError: dto.OpenAIError{
+			Message: fmt.Sprintf("bad response status code %d", resp.StatusCode),
+			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 textResponse dto.TextResponse
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return
+	}
+	openAIErrorWithStatusCode.OpenAIError = textResponse.Error
+	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 GetAPIVersion(c *gin.Context) string {
+	query := c.Request.URL.Query()
+	apiVersion := query.Get("api-version")
+	if apiVersion == "" {
+		apiVersion = c.GetString("api_version")
+	}
+	return apiVersion
+}
+
+func GetAzureAPIVersion(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/constant/api_type.go
+++ b/relay/constant/api_type.go
@@ -0,0 +1,48 @@
+package constant
+
+import (
+	"one-api/common"
+)
+
+const (
+	APITypeOpenAI = iota
+	APITypeAnthropic
+	APITypePaLM
+	APITypeBaidu
+	APITypeZhipu
+	APITypeAli
+	APITypeXunfei
+	APITypeAIProxyLibrary
+	APITypeTencent
+	APITypeGemini
+	APITypeZhipu_v4
+
+	APITypeDummy // this one is only for count, do not add any channel after this
+)
+
+func ChannelType2APIType(channelType int) int {
+	apiType := APITypeOpenAI
+	switch channelType {
+	case common.ChannelTypeAnthropic:
+		apiType = APITypeAnthropic
+	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
+	case common.ChannelTypeZhipu_v4:
+		apiType = APITypeZhipu_v4
+	}
+	return apiType
+}
--- a/relay/constant/relay_mode.go
+++ b/relay/constant/relay_mode.go
@@ -0,0 +1,50 @@
+package constant
+
+import "strings"
+
+const (
+	RelayModeUnknown = iota
+	RelayModeChatCompletions
+	RelayModeCompletions
+	RelayModeEmbeddings
+	RelayModeModerations
+	RelayModeImagesGenerations
+	RelayModeEdits
+	RelayModeMidjourneyImagine
+	RelayModeMidjourneyDescribe
+	RelayModeMidjourneyBlend
+	RelayModeMidjourneyChange
+	RelayModeMidjourneySimpleChange
+	RelayModeMidjourneyNotify
+	RelayModeMidjourneyTaskFetch
+	RelayModeMidjourneyTaskFetchByCondition
+	RelayModeAudioSpeech
+	RelayModeAudioTranscription
+	RelayModeAudioTranslation
+)
+
+func Path2RelayMode(path string) int {
+	relayMode := RelayModeUnknown
+	if strings.HasPrefix(path, "/v1/chat/completions") {
+		relayMode = RelayModeChatCompletions
+	} else if strings.HasPrefix(path, "/v1/completions") {
+		relayMode = RelayModeCompletions
+	} else if strings.HasPrefix(path, "/v1/embeddings") {
+		relayMode = RelayModeEmbeddings
+	} else if strings.HasSuffix(path, "embeddings") {
+		relayMode = RelayModeEmbeddings
+	} else if strings.HasPrefix(path, "/v1/moderations") {
+		relayMode = RelayModeModerations
+	} else if strings.HasPrefix(path, "/v1/images/generations") {
+		relayMode = RelayModeImagesGenerations
+	} else if strings.HasPrefix(path, "/v1/edits") {
+		relayMode = RelayModeEdits
+	} else if strings.HasPrefix(path, "/v1/audio/speech") {
+		relayMode = RelayModeAudioSpeech
+	} else if strings.HasPrefix(path, "/v1/audio/transcriptions") {
+		relayMode = RelayModeAudioTranscription
+	} else if strings.HasPrefix(path, "/v1/audio/translations") {
+		relayMode = RelayModeAudioTranslation
+	}
+	return relayMode
+}
--- a/controller/relay-audio.go
+++ b/controller/relay-audio.go
@@ -1,4 +1,4 @@
-package controller
+package relay

 import (
 	"bytes"
@@ -10,8 +10,13 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/model"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
 	"strings"
+	"time"
 )

 var availableVoices = []string{
@@ -23,22 +28,22 @@ var availableVoices = []string{
 	"shimmer",
 }

-func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
-
+func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
 	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
 	group := c.GetString("group")
+	startTime := time.Now()

-	var audioRequest AudioRequest
+	var audioRequest dto.TextToSpeechRequest
 	if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
 		err := common.UnmarshalBodyReusable(c, &audioRequest)
 		if err != nil {
-			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
 		}
 	} else {
-		audioRequest = AudioRequest{
+		audioRequest = dto.TextToSpeechRequest{
 			Model: "whisper-1",
 		}
 	}
@@ -46,15 +51,15 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode

 	// request validation
 	if audioRequest.Model == "" {
-		return errorWrapper(errors.New("model is required"), "required_field_missing", http.StatusBadRequest)
+		return service.OpenAIErrorWrapper(errors.New("model is required"), "required_field_missing", http.StatusBadRequest)
 	}

 	if strings.HasPrefix(audioRequest.Model, "tts-1") {
 		if audioRequest.Voice == "" {
-			return errorWrapper(errors.New("voice is required"), "required_field_missing", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(errors.New("voice is required"), "required_field_missing", http.StatusBadRequest)
 		}
 		if !common.StringsContains(availableVoices, audioRequest.Voice) {
-			return errorWrapper(errors.New("voice must be one of "+strings.Join(availableVoices, ", ")), "invalid_field_value", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(errors.New("voice must be one of "+strings.Join(availableVoices, ", ")), "invalid_field_value", http.StatusBadRequest)
 		}
 	}

@@ -65,14 +70,14 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
 	userQuota, err := model.CacheGetUserQuota(userId)
 	if err != nil {
-		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(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)
+		return service.OpenAIErrorWrapper(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)
+		return service.OpenAIErrorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
 	}
 	if userQuota > 100*preConsumedQuota {
 		// in this case, we do not pre-consume quota
@@ -82,7 +87,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	if preConsumedQuota > 0 {
 		userQuota, err = model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
-			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
+			return service.OpenAIErrorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
 	}

@@ -92,7 +97,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
 		if err != nil {
-			return errorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
 		}
 		if modelMap[audioRequest.Model] != "" {
 			audioRequest.Model = modelMap[audioRequest.Model]
@@ -105,46 +110,63 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		baseURL = c.GetString("base_url")
 	}

-	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
+	fullRequestURL := relaycommon.GetFullRequestURL(baseURL, requestURL, channelType)
+	if relayMode == relayconstant.RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		apiVersion := relaycommon.GetAzureAPIVersion(c)
+		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/audio/transcriptions?api-version=%s", baseURL, audioRequest.Model, apiVersion)
+	}
+
 	requestBody := c.Request.Body

 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
-		return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "new_request_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+
+	if relayMode == relayconstant.RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		apiKey := c.Request.Header.Get("Authorization")
+		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+		req.Header.Set("api-key", apiKey)
+		req.ContentLength = c.Request.ContentLength
+	} else {
+		req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+	}
+
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))

-	resp, err := httpClient.Do(req)
+	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
-		return errorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}

 	err = req.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}
 	err = c.Request.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}

 	if resp.StatusCode != http.StatusOK {
-		return relayErrorHandler(resp)
+		return relaycommon.RelayErrorHandler(resp)
 	}

-	var audioResponse AudioResponse
+	var audioResponse dto.AudioResponse

 	defer func(ctx context.Context) {
 		go func() {
+			useTimeSeconds := time.Now().Unix() - startTime.Unix()
 			quota := 0
 			var promptTokens = 0
 			if strings.HasPrefix(audioRequest.Model, "tts-1") {
-				quota = countAudioToken(audioRequest.Input, audioRequest.Model)
+				quota = service.CountAudioToken(audioRequest.Input, audioRequest.Model)
 				promptTokens = quota
 			} else {
-				quota = countAudioToken(audioResponse.Text, audioRequest.Model)
+				quota = service.CountAudioToken(audioResponse.Text, audioRequest.Model)
 			}
 			quota = int(float64(quota) * ratio)
 			if ratio != 0 && quota <= 0 {
@@ -162,7 +184,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, 0, audioRequest.Model, tokenName, quota, logContent, tokenId, userQuota)
+				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, 0, audioRequest.Model, tokenName, quota, logContent, tokenId, userQuota, int(useTimeSeconds), false)
 				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 				channelId := c.GetInt("channel_id")
 				model.UpdateChannelUsedQuota(channelId, quota)
@@ -173,18 +195,18 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	responseBody, err := io.ReadAll(resp.Body)

 	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
 	}
 	if strings.HasPrefix(audioRequest.Model, "tts-1") {

 	} else {
 		err = json.Unmarshal(responseBody, &audioResponse)
 		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
 		}
 	}

@@ -197,11 +219,11 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode

 	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
-		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
 	}
 	return nil
 }
--- a/controller/relay-image.go
+++ b/controller/relay-image.go
@@ -1,4 +1,4 @@
-package controller
+package relay

 import (
 	"bytes"
@@ -10,28 +10,34 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/model"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
 	"strings"
+	"time"
 )

-func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
+func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
 	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
 	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
+	startTime := time.Now()

-	var imageRequest ImageRequest
+	var imageRequest dto.ImageRequest
 	if consumeQuota {
 		err := common.UnmarshalBodyReusable(c, &imageRequest)
 		if err != nil {
-			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
 		}
 	}

 	if imageRequest.Model == "" {
-		imageRequest.Model = "dall-e"
+		imageRequest.Model = "dall-e-2"
 	}
 	if imageRequest.Size == "" {
 		imageRequest.Size = "1024x1024"
@@ -41,29 +47,29 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	}
 	// Prompt validation
 	if imageRequest.Prompt == "" {
-		return errorWrapper(errors.New("prompt is required"), "required_field_missing", http.StatusBadRequest)
+		return service.OpenAIErrorWrapper(errors.New("prompt is required"), "required_field_missing", http.StatusBadRequest)
 	}

 	if strings.Contains(imageRequest.Size, "×") {
-		return errorWrapper(errors.New("size an unexpected error occurred in the parameter, please use 'x' instead of the multiplication sign '×'"), "invalid_field_value", http.StatusBadRequest)
+		return service.OpenAIErrorWrapper(errors.New("size an unexpected error occurred in the parameter, please use 'x' instead of the multiplication sign '×'"), "invalid_field_value", http.StatusBadRequest)
 	}
 	// Not "256x256", "512x512", or "1024x1024"
 	if imageRequest.Model == "dall-e-2" || imageRequest.Model == "dall-e" {
 		if imageRequest.Size != "" && imageRequest.Size != "256x256" && imageRequest.Size != "512x512" && imageRequest.Size != "1024x1024" {
-			return errorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
 		}
 	} else if imageRequest.Model == "dall-e-3" {
 		if imageRequest.Size != "" && imageRequest.Size != "1024x1024" && imageRequest.Size != "1024x1792" && imageRequest.Size != "1792x1024" {
-			return errorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
 		}
 		if imageRequest.N != 1 {
-			return errorWrapper(errors.New("n must be 1"), "invalid_field_value", http.StatusBadRequest)
+			return service.OpenAIErrorWrapper(errors.New("n must be 1"), "invalid_field_value", http.StatusBadRequest)
 		}
 	}

 	// N should between 1 and 10
 	if imageRequest.N != 0 && (imageRequest.N < 1 || imageRequest.N > 10) {
-		return errorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
+		return service.OpenAIErrorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
 	}

 	// map model name
@@ -73,7 +79,7 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
 		if err != nil {
-			return errorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
 		}
 		if modelMap[imageRequest.Model] != "" {
 			imageRequest.Model = modelMap[imageRequest.Model]
@@ -85,12 +91,18 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
-	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
+	fullRequestURL := relaycommon.GetFullRequestURL(baseURL, requestURL, channelType)
+	if channelType == common.ChannelTypeAzure && relayMode == relayconstant.RelayModeImagesGenerations {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/dall-e-quickstart?tabs=dalle3%2Ccommand-line&pivots=rest-api
+		apiVersion := relaycommon.GetAPIVersion(c)
+		// https://{resource_name}.openai.azure.com/openai/deployments/dall-e-3/images/generations?api-version=2023-06-01-preview
+		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/images/generations?api-version=%s", baseURL, imageRequest.Model, apiVersion)
+	}
 	var requestBody io.Reader
-	if isModelMapped {
+	if isModelMapped || channelType == common.ChannelTypeAzure { // make Azure channel request body
 		jsonStr, err := json.Marshal(imageRequest)
 		if err != nil {
-			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
 		}
 		requestBody = bytes.NewBuffer(jsonStr)
 	} else {
@@ -125,39 +137,49 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	quota := int(ratio*sizeRatio*qualityRatio*1000) * imageRequest.N

 	if consumeQuota && userQuota-quota < 0 {
-		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}

 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
-		return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "new_request_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))

+	token := c.Request.Header.Get("Authorization")
+	if channelType == common.ChannelTypeAzure { // Azure authentication
+		token = strings.TrimPrefix(token, "Bearer ")
+		req.Header.Set("api-key", token)
+	} else {
+		req.Header.Set("Authorization", token)
+	}
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))

-	resp, err := httpClient.Do(req)
+	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
-		return errorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}

 	err = req.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}
 	err = c.Request.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}

 	if resp.StatusCode != http.StatusOK {
-		return relayErrorHandler(resp)
+		return relaycommon.RelayErrorHandler(resp)
 	}

-	var textResponse ImageResponse
+	var textResponse dto.ImageResponse
 	defer func(ctx context.Context) {
+		useTimeSeconds := time.Now().Unix() - startTime.Unix()
 		if consumeQuota {
+			if resp.StatusCode != http.StatusOK {
+				return
+			}
 			err := model.PostConsumeTokenQuota(tokenId, userQuota, quota, 0, true)
 			if err != nil {
 				common.SysError("error consuming token remain quota: " + err.Error())
@@ -169,7 +191,7 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageRequest.Model, tokenName, quota, logContent, tokenId, userQuota)
+				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageRequest.Model, tokenName, quota, logContent, tokenId, userQuota, int(useTimeSeconds), false)
 				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 				channelId := c.GetInt("channel_id")
 				model.UpdateChannelUsedQuota(channelId, quota)
@@ -181,15 +203,15 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		responseBody, err := io.ReadAll(resp.Body)

 		if err != nil {
-			return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
 		}
 		err = resp.Body.Close()
 		if err != nil {
-			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
 		}
 		err = json.Unmarshal(responseBody, &textResponse)
 		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+			return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
 		}

 		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
@@ -202,11 +224,11 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode

 	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
-		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
 	}
 	return nil
 }
--- a/controller/relay-mj.go
+++ b/controller/relay-mj.go
@@ -1,4 +1,4 @@
-package controller
+package relay

 import (
 	"bytes"
@@ -9,7 +9,10 @@ import (
 	"log"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/model"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
 	"strconv"
 	"strings"
 	"time"
@@ -78,6 +81,7 @@ func RelayMidjourneyImage(c *gin.Context) {
 		c.JSON(http.StatusInternalServerError, gin.H{
 			"error": "http_get_image_failed",
 		})
+		return
 	}
 	defer resp.Body.Close()
 	if resp.StatusCode != http.StatusOK {
@@ -103,11 +107,11 @@ func RelayMidjourneyImage(c *gin.Context) {
 	return
 }

-func relayMidjourneyNotify(c *gin.Context) *MidjourneyResponse {
+func RelayMidjourneyNotify(c *gin.Context) *dto.MidjourneyResponse {
 	var midjRequest Midjourney
 	err := common.UnmarshalBodyReusable(c, &midjRequest)
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "bind_request_body_failed",
 			Properties:  nil,
@@ -116,7 +120,7 @@ func relayMidjourneyNotify(c *gin.Context) *MidjourneyResponse {
 	}
 	midjourneyTask := model.GetByOnlyMJId(midjRequest.MjId)
 	if midjourneyTask == nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "midjourney_task_not_found",
 			Properties:  nil,
@@ -134,7 +138,7 @@ func relayMidjourneyNotify(c *gin.Context) *MidjourneyResponse {
 	midjourneyTask.FailReason = midjRequest.FailReason
 	err = midjourneyTask.Update()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "update_midjourney_task_failed",
 		}
@@ -166,16 +170,16 @@ func getMidjourneyTaskModel(c *gin.Context, originTask *model.Midjourney) (midjo
 	return
 }

-func relayMidjourneyTask(c *gin.Context, relayMode int) *MidjourneyResponse {
+func RelayMidjourneyTask(c *gin.Context, relayMode int) *dto.MidjourneyResponse {
 	userId := c.GetInt("id")
 	var err error
 	var respBody []byte
 	switch relayMode {
-	case RelayModeMidjourneyTaskFetch:
+	case relayconstant.RelayModeMidjourneyTaskFetch:
 		taskId := c.Param("id")
 		originTask := model.GetByMJId(userId, taskId)
 		if originTask == nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "task_no_found",
 			}
@@ -183,18 +187,18 @@ func relayMidjourneyTask(c *gin.Context, relayMode int) *MidjourneyResponse {
 		midjourneyTask := getMidjourneyTaskModel(c, originTask)
 		respBody, err = json.Marshal(midjourneyTask)
 		if err != nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "unmarshal_response_body_failed",
 			}
 		}
-	case RelayModeMidjourneyTaskFetchByCondition:
+	case relayconstant.RelayModeMidjourneyTaskFetchByCondition:
 		var condition = struct {
 			IDs []string `json:"ids"`
 		}{}
 		err = c.BindJSON(&condition)
 		if err != nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "do_request_failed",
 			}
@@ -212,7 +216,7 @@ func relayMidjourneyTask(c *gin.Context, relayMode int) *MidjourneyResponse {
 		}
 		respBody, err = json.Marshal(tasks)
 		if err != nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "unmarshal_response_body_failed",
 			}
@@ -223,7 +227,7 @@ func relayMidjourneyTask(c *gin.Context, relayMode int) *MidjourneyResponse {

 	_, err = io.Copy(c.Writer, bytes.NewBuffer(respBody))
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "copy_response_body_failed",
 		}
@@ -243,7 +247,7 @@ const (
 	MJSubmitActionUpscale  = "UPSCALE" // 放大
 )

-func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
+func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyResponse {
 	imageModel := "midjourney"

 	tokenId := c.GetInt("token_id")
@@ -252,60 +256,60 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 	channelId := c.GetInt("channel_id")
-	var midjRequest MidjourneyRequest
+	var midjRequest dto.MidjourneyRequest
 	if consumeQuota {
 		err := common.UnmarshalBodyReusable(c, &midjRequest)
 		if err != nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "bind_request_body_failed",
 			}
 		}
 	}

-	if relayMode == RelayModeMidjourneyImagine { //绘画任务，此类任务可重复
+	if relayMode == relayconstant.RelayModeMidjourneyImagine { //绘画任务，此类任务可重复
 		if midjRequest.Prompt == "" {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "prompt_is_required",
 			}
 		}
 		midjRequest.Action = "IMAGINE"
-	} else if relayMode == RelayModeMidjourneyDescribe { //按图生文任务，此类任务可重复
+	} else if relayMode == relayconstant.RelayModeMidjourneyDescribe { //按图生文任务，此类任务可重复
 		midjRequest.Action = "DESCRIBE"
-	} else if relayMode == RelayModeMidjourneyBlend { //绘画任务，此类任务可重复
+	} else if relayMode == relayconstant.RelayModeMidjourneyBlend { //绘画任务，此类任务可重复
 		midjRequest.Action = "BLEND"
 	} else if midjRequest.TaskId != "" { //放大、变换任务，此类任务，如果重复且已有结果，远端api会直接返回最终结果
 		mjId := ""
-		if relayMode == RelayModeMidjourneyChange {
+		if relayMode == relayconstant.RelayModeMidjourneyChange {
 			if midjRequest.TaskId == "" {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "taskId_is_required",
 				}
 			} else if midjRequest.Action == "" {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "action_is_required",
 				}
 			} else if midjRequest.Index == 0 {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "index_can_only_be_1_2_3_4",
 				}
 			}
 			//action = midjRequest.Action
 			mjId = midjRequest.TaskId
-		} else if relayMode == RelayModeMidjourneySimpleChange {
+		} else if relayMode == relayconstant.RelayModeMidjourneySimpleChange {
 			if midjRequest.Content == "" {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "content_is_required",
 				}
 			}
 			params := convertSimpleChangeParams(midjRequest.Content)
 			if params == nil {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "content_parse_failed",
 				}
@@ -316,25 +320,25 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {

 		originTask := model.GetByMJId(userId, mjId)
 		if originTask == nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "task_no_found",
 			}
 		} else if originTask.Action == "UPSCALE" {
 			//return errorWrapper(errors.New("upscale task can not be change"), "request_params_error", http.StatusBadRequest).
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "upscale_task_can_not_be_change",
 			}
 		} else if originTask.Status != "SUCCESS" {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "task_status_is_not_success",
 			}
 		} else { //原任务的Status=SUCCESS，则可以做放大UPSCALE、变换VARIATION等动作，此时必须使用原来的请求地址才能正确处理
 			channel, err := model.GetChannelById(originTask.ChannelId, false)
 			if err != nil {
-				return &MidjourneyResponse{
+				return &dto.MidjourneyResponse{
 					Code:        4,
 					Description: "channel_not_found",
 				}
@@ -354,7 +358,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
 		if err != nil {
 			//return errorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "unmarshal_model_mapping_failed",
 			}
@@ -381,7 +385,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	if isModelMapped {
 		jsonStr, err := json.Marshal(midjRequest)
 		if err != nil {
-			return &MidjourneyResponse{
+			return &dto.MidjourneyResponse{
 				Code:        4,
 				Description: "marshal_text_request_failed",
 			}
@@ -391,7 +395,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 		requestBody = c.Request.Body
 	}
 	mjAction := "mj_" + strings.ToLower(midjRequest.Action)
-	modelPrice := common.GetModelPrice(mjAction)
+	modelPrice := common.GetModelPrice(mjAction, true)
 	// 如果没有配置价格，则使用默认价格
 	if modelPrice == -1 {
 		defaultPrice, ok := DefaultModelPrice[mjAction]
@@ -405,7 +409,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	ratio := modelPrice * groupRatio
 	userQuota, err := model.CacheGetUserQuota(userId)
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: err.Error(),
 		}
@@ -413,7 +417,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	quota := int(ratio * common.QuotaPerUnit)

 	if consumeQuota && userQuota-quota < 0 {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "quota_not_enough",
 		}
@@ -421,28 +425,28 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {

 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "create_request_failed",
 		}
 	}
-	//req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+	//req.Header.Set("ApiKey", c.Request.Header.Get("ApiKey"))

 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
 	//mjToken := ""
-	//if c.Request.Header.Get("Authorization") != "" {
-	//	mjToken = strings.Split(c.Request.Header.Get("Authorization"), " ")[1]
+	//if c.Request.Header.Get("ApiKey") != "" {
+	//	mjToken = strings.Split(c.Request.Header.Get("ApiKey"), " ")[1]
 	//}
-	//req.Header.Set("Authorization", "Bearer midjourney-proxy")
+	//req.Header.Set("ApiKey", "Bearer midjourney-proxy")
 	req.Header.Set("mj-api-secret", strings.Split(c.Request.Header.Get("Authorization"), " ")[1])
 	// print request header
 	log.Printf("request header: %s", req.Header)
 	log.Printf("request body: %s", midjRequest.Prompt)

-	resp, err := httpClient.Do(req)
+	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "do_request_failed",
 		}
@@ -450,19 +454,19 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {

 	err = req.Body.Close()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "close_request_body_failed",
 		}
 	}
 	err = c.Request.Body.Close()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "close_request_body_failed",
 		}
 	}
-	var midjResponse MidjourneyResponse
+	var midjResponse dto.MidjourneyResponse

 	defer func(ctx context.Context) {
 		if consumeQuota {
@@ -477,7 +481,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型固定价格 %.2f，分组倍率 %.2f，操作 %s", modelPrice, groupRatio, midjRequest.Action)
-				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent, tokenId, userQuota)
+				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent, tokenId, userQuota, 0, false)
 				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 				channelId := c.GetInt("channel_id")
 				model.UpdateChannelUsedQuota(channelId, quota)
@@ -491,14 +495,14 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	responseBody, err := io.ReadAll(resp.Body)

 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "read_response_body_failed",
 		}
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "close_response_body_failed",
 		}
@@ -508,13 +512,13 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 	log.Printf("responseBody: %s", string(responseBody))
 	log.Printf("midjResponse: %v", midjResponse)
 	if resp.StatusCode != 200 {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "fail_to_fetch_midjourney status_code: " + strconv.Itoa(resp.StatusCode),
 		}
 	}
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "unmarshal_response_body_failed",
 		}
@@ -544,6 +548,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {
 		Progress:    "0%",
 		FailReason:  "",
 		ChannelId:   c.GetInt("channel_id"),
+		Quota:       quota,
 	}

 	if midjResponse.Code != 1 && midjResponse.Code != 21 && midjResponse.Code != 22 {
@@ -576,7 +581,7 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {

 	err = midjourneyTask.Insert()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "insert_midjourney_task_failed",
 		}
@@ -597,14 +602,14 @@ func relayMidjourneySubmit(c *gin.Context, relayMode int) *MidjourneyResponse {

 	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "copy_response_body_failed",
 		}
 	}
 	err = resp.Body.Close()
 	if err != nil {
-		return &MidjourneyResponse{
+		return &dto.MidjourneyResponse{
 			Code:        4,
 			Description: "close_response_body_failed",
 		}
--- a/relay/relay-text.go
+++ b/relay/relay-text.go
@@ -0,0 +1,276 @@
+package relay
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"math"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/model"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
+	"strings"
+	"time"
+
+	"github.com/gin-gonic/gin"
+)
+
+func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo) (*dto.GeneralOpenAIRequest, error) {
+	textRequest := &dto.GeneralOpenAIRequest{}
+	err := common.UnmarshalBodyReusable(c, textRequest)
+	if err != nil {
+		return nil, err
+	}
+	if relayInfo.RelayMode == relayconstant.RelayModeModerations && textRequest.Model == "" {
+		textRequest.Model = "text-moderation-latest"
+	}
+	if relayInfo.RelayMode == relayconstant.RelayModeEmbeddings && textRequest.Model == "" {
+		textRequest.Model = c.Param("model")
+	}
+
+	if textRequest.MaxTokens < 0 || textRequest.MaxTokens > math.MaxInt32/2 {
+		return nil, errors.New("max_tokens is invalid")
+	}
+	if textRequest.Model == "" {
+		return nil, errors.New("model is required")
+	}
+	switch relayInfo.RelayMode {
+	case relayconstant.RelayModeCompletions:
+		if textRequest.Prompt == "" {
+			return nil, errors.New("field prompt is required")
+		}
+	case relayconstant.RelayModeChatCompletions:
+		if textRequest.Messages == nil || len(textRequest.Messages) == 0 {
+			return nil, errors.New("field messages is required")
+		}
+	case relayconstant.RelayModeEmbeddings:
+	case relayconstant.RelayModeModerations:
+		if textRequest.Input == "" {
+			return nil, errors.New("field input is required")
+		}
+	case relayconstant.RelayModeEdits:
+		if textRequest.Instruction == "" {
+			return nil, errors.New("field instruction is required")
+		}
+	}
+	relayInfo.IsStream = textRequest.Stream
+	relayInfo.UpstreamModelName = textRequest.Model
+	return textRequest, nil
+}
+
+func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
+
+	relayInfo := relaycommon.GenRelayInfo(c)
+
+	// get & validate textRequest 获取并验证文本请求
+	textRequest, err := getAndValidateTextRequest(c, relayInfo)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidateTextRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapper(err, "invalid_text_request", 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 service.OpenAIErrorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+		}
+		if modelMap[textRequest.Model] != "" {
+			textRequest.Model = modelMap[textRequest.Model]
+			isModelMapped = true
+		}
+	}
+	modelPrice := common.GetModelPrice(textRequest.Model, false)
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+
+	var preConsumedQuota int
+	var ratio float64
+	var modelRatio float64
+	promptTokens, err := getPromptTokens(textRequest, relayInfo)
+
+	// count messages token error 计算promptTokens错误
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "count_token_messages_failed", http.StatusInternalServerError)
+	}
+
+	if modelPrice == -1 {
+		preConsumedTokens := common.PreConsumedQuota
+		if textRequest.MaxTokens != 0 {
+			preConsumedTokens = promptTokens + int(textRequest.MaxTokens)
+		}
+		modelRatio = common.GetModelRatio(textRequest.Model)
+		ratio = modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapper(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo, *textRequest)
+	var requestBody io.Reader
+	if relayInfo.ApiType == relayconstant.APITypeOpenAI {
+		if isModelMapped {
+			jsonStr, err := json.Marshal(textRequest)
+			if err != nil {
+				return service.OpenAIErrorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
+			}
+			requestBody = bytes.NewBuffer(jsonStr)
+		} else {
+			requestBody = c.Request.Body
+		}
+	} else {
+		convertedRequest, err := adaptor.ConvertRequest(c, relayInfo.RelayMode, textRequest)
+		if err != nil {
+			return service.OpenAIErrorWrapper(err, "convert_request_failed", http.StatusInternalServerError)
+		}
+		jsonData, err := json.Marshal(convertedRequest)
+		if err != nil {
+			return service.OpenAIErrorWrapper(err, "json_marshal_failed", http.StatusInternalServerError)
+		}
+		requestBody = bytes.NewBuffer(jsonData)
+	}
+
+	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
+	relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
+
+	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+	postConsumeQuota(c, relayInfo, *textRequest, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice)
+	return nil
+}
+
+func getPromptTokens(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) (int, error) {
+	var promptTokens int
+	var err error
+
+	switch info.RelayMode {
+	case relayconstant.RelayModeChatCompletions:
+		promptTokens, err = service.CountTokenMessages(textRequest.Messages, textRequest.Model)
+	case relayconstant.RelayModeCompletions:
+		promptTokens, err = service.CountTokenInput(textRequest.Prompt, textRequest.Model), nil
+	case relayconstant.RelayModeModerations:
+		promptTokens, err = service.CountTokenInput(textRequest.Input, textRequest.Model), nil
+	default:
+		err = errors.New("unknown relay mode")
+		promptTokens = 0
+	}
+	info.PromptTokens = promptTokens
+	return promptTokens, err
+}
+
+// 预扣费并返回用户剩余配额
+func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommon.RelayInfo) (int, int, *dto.OpenAIErrorWithStatusCode) {
+	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
+	if err != nil {
+		return 0, 0, service.OpenAIErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
+	}
+	if userQuota <= 0 || userQuota-preConsumedQuota < 0 {
+		return 0, 0, service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+	}
+	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
+	if err != nil {
+		return 0, 0, service.OpenAIErrorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
+	}
+	if userQuota > 100*preConsumedQuota {
+		// 用户额度充足，判断令牌额度是否充足
+		if !relayInfo.TokenUnlimited {
+			// 非无限令牌，判断令牌额度是否充足
+			tokenQuota := c.GetInt("token_quota")
+			if tokenQuota > 100*preConsumedQuota {
+				// 令牌额度充足，信任令牌
+				preConsumedQuota = 0
+				common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
+			}
+		} else {
+			// 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 with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
+		}
+	}
+	if preConsumedQuota > 0 {
+		userQuota, err = model.PreConsumeTokenQuota(relayInfo.TokenId, preConsumedQuota)
+		if err != nil {
+			return 0, 0, service.OpenAIErrorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
+		}
+	}
+	return preConsumedQuota, userQuota, nil
+}
+
+func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRequest dto.GeneralOpenAIRequest, usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64, modelPrice float64) {
+	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
+	promptTokens := usage.PromptTokens
+	completionTokens := usage.CompletionTokens
+
+	tokenName := ctx.GetString("token_name")
+
+	quota := 0
+	if modelPrice == -1 {
+		completionRatio := common.GetCompletionRatio(textRequest.Model)
+		quota = promptTokens + int(float64(completionTokens)*completionRatio)
+		quota = int(float64(quota) * ratio)
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	totalTokens := promptTokens + completionTokens
+	var logContent string
+	if modelPrice == -1 {
+		logContent = fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
+	} else {
+		logContent = fmt.Sprintf("模型价格 %.2f，分组倍率 %.2f", modelPrice, groupRatio)
+	}
+
+	// record all the consume log even if quota is 0
+	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
+		logContent += fmt.Sprintf("（可能是上游超时）")
+		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, textRequest.Model, preConsumedQuota))
+	} else {
+		quotaDelta := quota - preConsumedQuota
+		err := model.PostConsumeTokenQuota(relayInfo.TokenId, userQuota, quotaDelta, preConsumedQuota, true)
+		if err != nil {
+			common.LogError(ctx, "error consuming token remain quota: "+err.Error())
+		}
+		err = model.CacheUpdateUserQuota(relayInfo.UserId)
+		if err != nil {
+			common.LogError(ctx, "error update user quota cache: "+err.Error())
+		}
+		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
+		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
+	}
+
+	logModel := textRequest.Model
+	if strings.HasPrefix(logModel, "gpt-4-gizmo") {
+		logModel = "gpt-4-gizmo-*"
+		logContent += fmt.Sprintf("，模型 %s", textRequest.Model)
+	}
+	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel, tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream)
+
+	//if quota != 0 {
+	//
+	//}
+}
--- a/relay/relay_adaptor.go
+++ b/relay/relay_adaptor.go
@@ -0,0 +1,44 @@
+package relay
+
+import (
+	"one-api/relay/channel"
+	"one-api/relay/channel/ali"
+	"one-api/relay/channel/baidu"
+	"one-api/relay/channel/claude"
+	"one-api/relay/channel/gemini"
+	"one-api/relay/channel/openai"
+	"one-api/relay/channel/palm"
+	"one-api/relay/channel/tencent"
+	"one-api/relay/channel/xunfei"
+	"one-api/relay/channel/zhipu"
+	"one-api/relay/channel/zhipu_4v"
+	"one-api/relay/constant"
+)
+
+func GetAdaptor(apiType int) channel.Adaptor {
+	switch apiType {
+	//case constant.APITypeAIProxyLibrary:
+	//	return &aiproxy.Adaptor{}
+	case constant.APITypeAli:
+		return &ali.Adaptor{}
+	case constant.APITypeAnthropic:
+		return &claude.Adaptor{}
+	case constant.APITypeBaidu:
+		return &baidu.Adaptor{}
+	case constant.APITypeGemini:
+		return &gemini.Adaptor{}
+	case constant.APITypeOpenAI:
+		return &openai.Adaptor{}
+	case constant.APITypePaLM:
+		return &palm.Adaptor{}
+	case constant.APITypeTencent:
+		return &tencent.Adaptor{}
+	case constant.APITypeXunfei:
+		return &xunfei.Adaptor{}
+	case constant.APITypeZhipu:
+		return &zhipu.Adaptor{}
+	case constant.APITypeZhipu_v4:
+		return &zhipu_4v.Adaptor{}
+	}
+	return nil
+}
--- a/router/api-router.go
+++ b/router/api-router.go
@@ -26,6 +26,8 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/oauth/wechat", middleware.CriticalRateLimit(), controller.WeChatAuth)
 		apiRouter.GET("/oauth/wechat/bind", middleware.CriticalRateLimit(), middleware.UserAuth(), controller.WeChatBind)
 		apiRouter.GET("/oauth/email/bind", middleware.CriticalRateLimit(), middleware.UserAuth(), controller.EmailBind)
+		apiRouter.GET("/oauth/telegram/login", middleware.CriticalRateLimit(), controller.TelegramLogin)
+		apiRouter.GET("/oauth/telegram/bind", middleware.CriticalRateLimit(), middleware.UserAuth(), controller.TelegramBind)

 		userRoute := apiRouter.Group("/user")
 		{
@@ -73,7 +75,7 @@ func SetApiRouter(router *gin.Engine) {
 		{
 			channelRoute.GET("/", controller.GetAllChannels)
 			channelRoute.GET("/search", controller.SearchChannels)
-			channelRoute.GET("/models", controller.ListModels)
+			channelRoute.GET("/models", controller.ChannelListModels)
 			channelRoute.GET("/:id", controller.GetChannel)
 			channelRoute.GET("/test", controller.TestAllChannels)
 			channelRoute.GET("/test/:id", controller.TestChannel)
@@ -84,6 +86,7 @@ func SetApiRouter(router *gin.Engine) {
 			channelRoute.DELETE("/disabled", controller.DeleteDisabledChannel)
 			channelRoute.DELETE("/:id", controller.DeleteChannel)
 			channelRoute.POST("/batch", controller.DeleteChannelBatch)
+			channelRoute.POST("/fix", controller.FixChannelsAbilities)
 		}
 		tokenRoute := apiRouter.Group("/token")
 		tokenRoute.Use(middleware.UserAuth())
--- a/router/relay-router.go
+++ b/router/relay-router.go
@@ -1,10 +1,10 @@
 package router

 import (
+	"github.com/gin-gonic/gin"
 	"one-api/controller"
 	"one-api/middleware"
-
-	"github.com/gin-gonic/gin"
+	"one-api/relay"
 )

 func SetRelayRouter(router *gin.Engine) {
@@ -17,7 +17,7 @@ func SetRelayRouter(router *gin.Engine) {
 		modelsRouter.GET("/:model", controller.RetrieveModel)
 	}
 	relayV1Router := router.Group("/v1")
-	relayV1Router.Use(middleware.RelayPanicRecover(), middleware.TokenAuth(), middleware.Distribute())
+	relayV1Router.Use(middleware.TokenAuth(), middleware.Distribute())
 	{
 		relayV1Router.POST("/completions", controller.Relay)
 		relayV1Router.POST("/chat/completions", controller.Relay)
@@ -44,7 +44,7 @@ func SetRelayRouter(router *gin.Engine) {
 		relayV1Router.POST("/moderations", controller.Relay)
 	}
 	relayMjRouter := router.Group("/mj")
-	relayMjRouter.GET("/image/:id", controller.RelayMidjourneyImage)
+	relayMjRouter.GET("/image/:id", relay.RelayMidjourneyImage)
 	relayMjRouter.Use(middleware.TokenAuth(), middleware.Distribute())
 	{
 		relayMjRouter.POST("/submit/imagine", controller.RelayMidjourney)
--- a/service/channel.go
+++ b/service/channel.go
@@ -0,0 +1,53 @@
+package service
+
+import (
+	"fmt"
+	"net/http"
+	"one-api/common"
+	relaymodel "one-api/dto"
+	"one-api/model"
+)
+
+// disable & notify
+func DisableChannel(channelId int, channelName string, reason string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled)
+	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
+	notifyRootUser(subject, content)
+}
+
+func EnableChannel(channelId int, channelName string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusEnabled)
+	subject := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	notifyRootUser(subject, content)
+}
+
+func ShouldDisableChannel(err *relaymodel.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" || err.Code == "billing_not_active" {
+		return true
+	}
+	return false
+}
+
+func ShouldEnableChannel(err error, openAIErr *relaymodel.OpenAIError) bool {
+	if !common.AutomaticEnableChannelEnabled {
+		return false
+	}
+	if err != nil {
+		return false
+	}
+	if openAIErr != nil {
+		return false
+	}
+	return true
+}
--- a/service/epay.go
+++ b/service/epay.go
@@ -0,0 +1,10 @@
+package service
+
+import "one-api/common"
+
+func GetCallbackAddress() string {
+	if common.CustomCallbackAddress == "" {
+		return common.ServerAddress
+	}
+	return common.CustomCallbackAddress
+}
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
1808837298@qq.com	912f46fcd2	feat: 记录请求的token用量	2024-03-04 14:58:30 +08:00
1808837298@qq.com	1ad1112351	feat: 解决渠道密钥长度限制问题	2024-03-04 14:55:26 +08:00
1808837298@qq.com	1f0a48a879	fix: 修复保存telegram设置后会将telegram登陆禁用的问题	2024-03-03 23:41:00 +08:00
1808837298@qq.com	d2de675564	chore: update README.md	2024-03-03 22:28:07 +08:00
Calcium-Ion	a5cfeeaa63	Merge pull request #79 from Ehco1996/telegram-login feat: support telegram login	2024-03-03 22:08:03 +08:00
1808837298@qq.com	37b307a784	fix: 修复预扣费判定无效导致用户可无限欠费问题	2024-03-03 22:07:20 +08:00
Ehco	02d5a5f16d	Merge branch 'main' into telegram-login	2024-03-03 19:42:06 +08:00
Ehco1996	699fe256d0	address comment	2024-03-03 19:41:15 +08:00
1808837298@qq.com	54088bc664	fix: 修复添加和编辑渠道无可选择模型	2024-03-03 15:53:48 +08:00
1808837298@qq.com	06b746a740	fix: remove useless code	2024-03-02 23:02:49 +08:00
1808837298@qq.com	4c43012e6c	fix: Improve handling of small weights in channel selection logic	2024-03-02 22:46:26 +08:00
1808837298@qq.com	a16e949318	feat: update SparkDesk model ratio	2024-03-02 22:08:59 +08:00
1808837298@qq.com	72194bda98	feat: 可自定义支付回调地址及最低购买数量	2024-03-02 22:07:32 +08:00
1808837298@qq.com	ca5c4d2dbd	Merge branch 'fix-model-name'	2024-03-02 21:16:05 +08:00
1808837298@qq.com	cbe0a1fa76	fix: add missing UpstreamModelName	2024-03-02 21:05:02 +08:00
1808837298@qq.com	d6d8ad2b7e	feat: 数据看板颜色统一	2024-03-02 20:56:29 +08:00
papersnake	7297c6269f	fix: add missing upstreamModelName	2024-03-02 12:26:39 +00:00
Ehco1996	cb92d6fd5f	revert compose	2024-03-02 19:58:36 +08:00
Ehco	e5cea80103	Merge pull request #1 from Ehco1996/telegram-login-complete feat: telegram login and bind	2024-03-02 17:24:34 +08:00
sljeff	84144306a8	feat: telegram login and bind	2024-03-02 17:15:52 +08:00
1808837298@qq.com	a8f0c5dab2	feat: 可设置默认折叠侧边栏	2024-03-02 02:12:02 +08:00
1808837298@qq.com	2b076eaed2	fix: fix typo	2024-03-01 22:39:42 +08:00
Ehco1996	194ff1ac57	Update makefile and user model, add Telegram integration	2024-03-01 22:33:30 +08:00
1808837298@qq.com	84cac72a45	feat: 修复智谱GLM-4V流模式异常	2024-03-01 22:31:08 +08:00
1808837298@qq.com	413d4f0a66	feat: Add channel search by model field (close #72 )	2024-03-01 21:57:52 +08:00
Ehco1996	690d2e6ba2	Add Telegram OAuth support	2024-03-01 21:54:24 +08:00
Ehco1996	140e843d93	Add Telegram bot token and name	2024-03-01 20:39:28 +08:00
1808837298@qq.com	feb40db2bc	feat: "/v1/models" 只返回用户可用模型 (close #78 )	2024-02-29 19:21:22 +08:00
1808837298@qq.com	b4645d1019	feat: 支持智谱GLM-4V	2024-02-29 18:31:03 +08:00
1808837298@qq.com	a3687b72f8	fix: fix preConsumeQuota error	2024-02-29 16:39:52 +08:00
1808837298@qq.com	6013219f5b	feat: 初步重构完成	2024-02-29 16:21:25 +08:00
1808837298@qq.com	5b18cd6b0a	feat: 初步重构	2024-02-29 01:08:18 +08:00
1808837298@qq.com	9b421478c1	fix: fix typo	2024-02-24 14:01:29 +08:00
1808837298@qq.com	569751f5db	fix: 修复测试渠道指定模型时实际使用gpt-3.5-turbo的问题 (close #67 )	2024-02-23 17:40:49 +08:00
1808837298@qq.com	608c945ae6	feat: 未配置在线支付时，限制用户输入金额 (close #74 )	2024-02-23 17:28:00 +08:00
1808837298@qq.com	05beade3ad	feat: 在线支付限制输入金额	2024-02-23 17:18:50 +08:00
1808837298@qq.com	81167c4322	feat: 记录更多的错误信息	2024-02-22 19:42:33 +08:00
1808837298@qq.com	6fa1837c24	feat: support logprobs	2024-02-22 17:52:03 +08:00
1808837298@qq.com	ba0c5bb4d9	feat: 优化令牌无效提示	2024-02-22 01:48:35 +08:00
1808837298@qq.com	5482fff62d	fix: 修复redis缓存用户额度不过期的问题	2024-02-20 00:23:31 +08:00
CaIon	1cde58c089	fix: 修正 Unicode 转义序列解析问题，close #63	2024-02-02 20:02:40 +08:00
CaIon	a0c4e9f10e	feat: add model gpt-3.5-turbo-0125	2024-02-02 12:46:12 +08:00
CaIon	d6d91e4340	feat: Happy New Year	2024-02-01 21:47:28 +08:00
CaIon	f19b11be8c	fix: fix test channel	2024-02-01 19:27:00 +08:00
CaIon	1bfc46aa70	ci: update workflows	2024-02-01 19:02:57 +08:00
CaIon	5c8f8b4901	feat: 添加成功时自动启用通道功能, close #27	2024-02-01 18:52:39 +08:00
CaIon	affe5111cc	feat: 支持测试渠道时自选模型	2024-02-01 18:31:42 +08:00
CaIon	0004c1022d	fix: support AI Gateway, close #52	2024-02-01 18:11:00 +08:00
CaIon	4274b925da	fix: support AI Gateway, close #52	2024-02-01 17:48:55 +08:00
CaIon	166770eebf	fix: 修复是否自动禁用选项不生效	2024-02-01 17:22:26 +08:00
CaIon	6d0479632a	fix: fix tool calls	2024-01-31 01:41:38 +08:00
CaIon	364d4f96c7	feat: add model text-embedding-3	2024-01-26 16:53:04 +08:00
CaIon	bce8a3e2be	feat: add model gpt-4-turbo-preview	2024-01-26 16:52:16 +08:00
CaIon	4920922929	fix: fix redis error	2024-01-26 16:09:50 +08:00
CaIon	70bdb8ca90	fix: fix redis error	2024-01-26 15:52:23 +08:00
CaIon	3dc5d4d95a	feat: update model-ratio	2024-01-26 14:21:10 +08:00
CaIon	ccaf64bbfc	chore: check before get userGroup	2024-01-25 20:10:32 +08:00
CaIon	ac3e27859c	feat: token缓存逻辑更新（实验性）	2024-01-25 20:09:06 +08:00
CaIon	e8188902c2	feat: 数据看板加入每列总计	2024-01-25 14:57:46 +08:00
CaIon	1ee8edcfd4	feat: 优化vision计费逻辑	2024-01-25 14:57:13 +08:00
CaIon	a3921ea54d	feat: add midjourney price log	2024-01-25 14:56:49 +08:00
CaIon	705171e495	chore: change use_time to int	2024-01-22 17:07:18 +08:00
CaIon	b3f46223a8	feat: 请求出现 0 token的时候，加入错误提示并打印日志	2024-01-21 20:44:26 +08:00
Calcium-Ion	5b2377eea9	Merge pull request #53 from Calcium-Ion/fork/main feat: 令牌聊天新增ChatGPT Web & Midjourney支持	2024-01-21 17:47:55 +08:00
CaIon	c59a33e8e9	feat: 令牌聊天新增ChatGPT Web & Midjourney支持	2024-01-21 17:43:40 +08:00
CaIon	e485bc7613	chore: remove unused import	2024-01-21 17:02:35 +08:00
CaIon	9bcd24fc2c	feat: 美化日志详情	2024-01-21 16:20:24 +08:00
CaIon	cbdce181af	feat: 日志优化逻辑，新增请求时间和是否为stream字段	2024-01-21 15:01:59 +08:00
CaIon	800f494698	Merge remote-tracking branch 'origin/main'	2024-01-20 00:13:36 +08:00
CaIon	7601610767	update package.json	2024-01-20 00:13:18 +08:00
Calcium-Ion	3a8be505c1	Merge pull request #51 from wxDadadada/main 修改数据看板文字	2024-01-17 14:29:01 +08:00
wxDadadada	51f7ad5de2	Update SiderBar.js	2024-01-17 12:48:55 +08:00
GuoRuqiang	f73a180fc3	Changes to be committed: modified: web/src/components/TokensTable.js	2024-01-16 18:50:01 +00:00
GuoRuqiang	e8db0a2c72	增加了一个超链聊天跳转在“运营设置里面”增加了“聊天页面2链接”，方便将项目（https://github.com/Dooy/chatgpt-web-midjourney-proxy）替换掉原来的AMA问天。 Changes to be committed: modified: common/constants.go modified: controller/misc.go modified: model/option.go modified: web/src/App.js modified: web/src/components/OperationSetting.js modified: web/src/components/TokensTable.js	2024-01-16 18:15:55 +00:00
Xyfacai	d3e070d963	fix: mj 错误处理	2024-01-14 16:17:45 +08:00
CaIon	e688e41360	perf: 美化绘画界面UI	2024-01-13 22:38:50 +08:00
CaIon	e41fcd563e	chore: 数据看板限制用户只能查询跨度一个月的数据	2024-01-13 01:32:23 +08:00
CaIon	a8715c61c8	fix: 修复数据看板渲染错误	2024-01-13 01:27:50 +08:00
CaIon	00306aa142	perf: 数据看板支持选择时间粒度	2024-01-13 00:33:52 +08:00
CaIon	d30b9321b2	chore: UpdateMidjourneyTaskBulk with SafeGoroutine	2024-01-12 18:38:45 +08:00
CaIon	2b3539fcaa	fix: 修复渠道一致性问题	2024-01-12 14:57:03 +08:00
CaIon	e2a1caba4c	fix: 修复渠道一致性问题	2024-01-12 14:36:15 +08:00
CaIon	febcadb42c	chore: add SafeGoroutine	2024-01-12 13:49:53 +08:00
CaIon	075b1ac113	fix: delete RelayPanicRecover	2024-01-12 13:48:13 +08:00
CaIon	6757166de5	Merge remote-tracking branch 'origin/main'	2024-01-12 13:46:08 +08:00
CaIon	2a9c3ac6af	fix: 修复mj错误返还费用问题	2024-01-12 13:45:52 +08:00
Calcium-Ion	2ccd6c04e0	Merge pull request #45 from AI-ASS/patch-1 fix: the Redis problem in the CacheGetUsername function	2024-01-12 13:17:20 +08:00
GAI Group	6aadcf0c78	fix: the Redis problem in the CacheGetUsername function fix: the Redis problem in the CacheGetUsername function	2024-01-12 13:15:43 +08:00
CaIon	312417f393	update README.md	2024-01-12 00:35:22 +08:00
CaIon	ad85792818	fix: user group size	2024-01-11 22:06:30 +08:00
CaIon	521ef5e219	fix: token model limit	2024-01-11 19:18:48 +08:00
CaIon	f07b9f8ab2	chore: cache username	2024-01-11 18:40:44 +08:00
CaIon	64e9e9cc20	fix: 完善令牌预扣费逻辑	2024-01-11 14:12:48 +08:00
CaIon	701a28d0da	fix: fix relay openai panic	2024-01-10 19:26:11 +08:00
CaIon	d04d2a6c4d	perf: UI美化	2024-01-10 18:32:44 +08:00
CaIon	e2317524f9	perf: 美化数据看板	2024-01-10 17:49:55 +08:00
CaIon	a3b726dd82	fix: 修复高并发下，高额度用户使用低额度令牌没有预扣费的问题	2024-01-10 14:23:23 +08:00
CaIon	042d55cfd3	fix: fix response choice json	2024-01-10 13:57:49 +08:00
CaIon	3432d9e0f6	fix: do not consume user quota if failed	2024-01-10 13:56:29 +08:00
CaIon	aca8d25372	feat: able to change gemini safety setting	2024-01-10 13:56:10 +08:00
CaIon	6a24e8953f	feat: able to fix channels	2024-01-10 13:23:43 +08:00
CaIon	3e13810ca2	fix: fix channel panic	2024-01-10 00:17:03 +08:00
CaIon	4a4df75830	docs: update Midjourney.md	2024-01-09 20:07:38 +08:00
CaIon	db29c96361	fix: add Tools support	2024-01-09 16:44:34 +08:00
CaIon	1618a8c9fc	perf: 优化数据看板性能	2024-01-09 16:20:04 +08:00
CaIon	75b6327f4f	feat: support Azure dall-e	2024-01-09 15:46:45 +08:00
CaIon	fb95216b5a	chore: delete model price log	2024-01-09 12:11:09 +08:00
CaIon	6ed365c267	fix: 修复数据看板筛选用户的时候不能指定时间的问题	2024-01-09 12:11:09 +08:00
CaIon	4f95b7d049	update README.md	2024-01-09 12:11:08 +08:00