chore: add x-requested-with header in CORS setting

* support API2GPT platform

* chore: update balance renderer

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,23 @@
+---
+name: 报告问题
+about: 使用简练详细的语言描述你遇到的问题
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**例行检查**
++ [ ] 我已确认目前没有类似 issue
++ [ ] 我已确认我已升级到最新版本
++ [ ] 我理解并愿意跟进此 issue，协助测试和提供反馈 
++ [ ] 我理解并认可上述内容，并理解项目维护者精力有限，不遵循规则的 issue 可能会被无视或直接关闭
+
+**问题描述**
+
+**复现步骤**
+
+**预期结果**
+
+**相关截图**
+如果没有的话，请删除此节。

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 项目群聊
+    url: https://openai.justsong.cn/
+    about: QQ 群：828520184，自动审核，备注 One API
+  - name: 赞赏支持
+    url: https://iamazing.cn/page/reward
+    about: 请作者喝杯咖啡，以激励作者持续开发
+  - name: 付费部署或定制功能
+    url: https://openai.justsong.cn/
+    about: 加群后联系群主

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,18 @@
+---
+name: 功能请求
+about: 使用简练详细的语言描述希望加入的新功能
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+**例行检查**
++ [ ] 我已确认目前没有类似 issue
++ [ ] 我已确认我已升级到最新版本
++ [ ] 我理解并愿意跟进此 issue，协助测试和提供反馈
++ [ ] 我理解并认可上述内容，并理解项目维护者精力有限，不遵循规则的 issue 可能会被无视或直接关闭
+
+**功能描述**
+
+**应用场景**

README.md

@@ -29,10 +29,10 @@ _✨ All in one 的 OpenAI 接口，整合各种 API 访问方式，开箱即用
 </p>
 
 <p align="center">
-  <a href="https://github.com/songquanpeng/one-api/releases">程序下载</a>
-  ·
   <a href="https://github.com/songquanpeng/one-api#部署">部署教程</a>
   ·
+  <a href="https://github.com/songquanpeng/one-api#使用方法">使用方法</a>
+  ·
   <a href="https://github.com/songquanpeng/one-api/issues">意见反馈</a>
   ·
   <a href="https://github.com/songquanpeng/one-api#截图展示">截图展示</a>
@@ -55,10 +55,11 @@ _✨ All in one 的 OpenAI 接口，整合各种 API 访问方式，开箱即用
    + [x] [API2D](https://api2d.com/r/197971)
    + [x] [OhMyGPT](https://aigptx.top?aff=uFpUl2Kf)
    + [x] [AI Proxy](https://aiproxy.io/?i=OneAPI) （邀请码：`OneAPI`）
+   + [x] [OpenAI-SB](https://openai-sb.com)
+   + [x] [API2GPT](http://console.api2gpt.com/m/00002S)
+   + [x] [CloseAI](https://console.openai-asia.com/r/2412)
    + [x] [AI.LS](https://ai.ls)
    + [x] [OpenAI Max](https://openaimax.com)
-   + [x] [OpenAI-SB](https://openai-sb.com)
-   + [x] [CloseAI](https://console.openai-asia.com/r/2412)
    + [x] 自定义渠道：例如各种未收录的第三方代理服务
 2. 支持通过**负载均衡**的方式访问多个渠道。
 3. 支持 **stream 模式**，可以通过流式传输实现打字机效果。
@@ -74,15 +75,18 @@ _✨ All in one 的 OpenAI 接口，整合各种 API 访问方式，开箱即用
     1. 支持自定义系统名称，logo 以及页脚。
     2. 支持自定义首页和关于页面，可以选择使用 HTML & Markdown 代码进行自定义，或者使用一个单独的网页通过 iframe 嵌入。
 13. 支持通过系统访问令牌访问管理 API。
-14. 支持用户管理，支持**多种用户登录注册方式**：
+14. 支持 Cloudflare Turnstile 用户校验。
+15. 支持用户管理，支持**多种用户登录注册方式**：
     + 邮箱登录注册以及通过邮箱进行密码重置。
     + [GitHub 开放授权](https://github.com/settings/applications/new)。
     + 微信公众号授权（需要额外部署 [WeChat Server](https://github.com/songquanpeng/wechat-server)）。
-15. 未来其他大模型开放 API 后，将第一时间支持，并将其封装成同样的 API 访问方式。
+16. 未来其他大模型开放 API 后，将第一时间支持，并将其封装成同样的 API 访问方式。
 
 ## 部署
 ### 基于 Docker 进行部署
-执行：`docker run -d --restart always -p 3000:3000 -v /home/ubuntu/data/one-api:/data justsong/one-api`
+部署命令：`docker run --name one-api -d --restart always -p 3000:3000 -v /home/ubuntu/data/one-api:/data justsong/one-api`
+
+更新命令：`docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR`
 
 `-p 3000:3000` 中的第一个 `3000` 是宿主机的端口，可以根据需要进行修改。
 
@@ -117,6 +121,8 @@ sudo certbot --nginx
 sudo service nginx restart
 ```
 
+初始账号用户名为 `root`，密码为 `123456`。
+
 ### 手动部署
 1. 从 [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) 下载可执行文件或者从源码编译：
    ```shell
@@ -149,6 +155,47 @@ sudo service nginx restart
 
 环境变量的具体使用方法详见[此处](#环境变量)。
 
+### 部署第三方服务配合 One API 使用
+> 欢迎 PR 添加更多示例。
+
+#### ChatGPT Next Web
+项目主页：https://github.com/Yidadaa/ChatGPT-Next-Web
+
+```bash
+docker run --name chat-next-web -d -p 3001:3000 -e BASE_URL=https://openai.justsong.cn yidadaa/chatgpt-next-web
+```
+
+注意修改端口号和 `BASE_URL`。
+
+#### ChatGPT Web
+项目主页：https://github.com/Chanzhaoyu/chatgpt-web
+
+```bash
+docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://openai.justsong.cn -e OPENAI_API_KEY=sk-xxx chenzhaoyu94/chatgpt-web
+```
+
+注意修改端口号、`OPENAI_API_BASE_URL` 和 `OPENAI_API_KEY`。
+
+### 部署到第三方平台
+<details>
+<summary><strong>部署到 Zeabur</strong></summary>
+<div>
+
+> Zeabur 的服务器在国外，自动解决了网络的问题，同时免费的额度也足够个人使用。
+
+1. 首先 fork 一份代码。
+2. 进入 [Zeabur](https://zeabur.com/)，登录，进入控制台。
+3. 新建一个 Project，在 Service -> Add Service 选择 Marketplace，选择 MySQL，并记下连接参数（用户名、密码、地址、端口）。
+4. 复制链接参数，运行 ```create database `one-api` ``` 创建数据库。
+5. 然后在 Service -> Add Service，选择 Git（第一次使用需要先授权），选择你 fork 的仓库。
+6. Deploy 会自动开始，先取消。进入下方 Variable，添加一个 `PORT`，值为 `3000`，再添加一个 `SQL_DSN`，值为 `<username>:<password>@tcp(<addr>:<port>)/one-api` ，然后保存。 注意如果不填写 `SQL_DSN`，数据将无法持久化，重新部署后数据会丢失。
+7. 选择 Redeploy。
+8. 进入下方 Domains，选择一个合适的域名前缀，如 "my-one-api"，最终域名为 "my-one-api.zeabur.app"，也可以 CNAME 自己的域名。
+9. 等待部署完成，点击生成的域名进入 One API。
+
+</div>
+</details>
+
 ## 配置
 系统本身开箱即用。
 
@@ -156,11 +203,24 @@ sudo service nginx restart
 
 等到系统启动后，使用 `root` 用户登录系统并做进一步的配置。
 
-## 使用方式
-在`渠道`页面中添加你的 API Key，之后在`令牌`页面中新增一个访问令牌。
+## 使用方法
+在`渠道`页面中添加你的 API Key，之后在`令牌`页面中新增访问令牌。
 
 之后就可以使用你的令牌访问 One API 了，使用方式与 [OpenAI API](https://platform.openai.com/docs/api-reference/introduction) 一致。
 
+你需要在各种用到 OpenAI API 的地方设置 API Base 为你的 One API 的部署地址，例如：`https://openai.justsong.cn`，API Key 则为你在 One API 中生成的令牌。
+
+注意，具体的 API Base 的格式取决于你所使用的客户端。
+
+```mermaid
+graph LR
+    A(用户)
+    A --->|请求| B(One API)
+    B -->|中继请求| C(OpenAI)
+    B -->|中继请求| D(Azure)
+    B -->|中继请求| E(其他下游渠道)
+```
+
 可以通过在令牌后面添加渠道 ID 的方式指定使用哪一个渠道处理本次请求，例如：`Authorization: Bearer ONE_API_KEY-CHANNEL_ID`。
 注意，需要是管理员用户创建的令牌才能指定渠道 ID。
 
@@ -171,7 +231,7 @@ sudo service nginx restart
    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
 2. `SESSION_SECRET`：设置之后将使用固定的会话密钥，这样系统重新启动后已登录用户的 cookie 将依旧有效。
    + 例子：`SESSION_SECRET=random_string`
-3. `SQL_DSN`：设置之后将使用指定数据库而非 SQLite。
+3. `SQL_DSN`：设置之后将使用指定数据库而非 SQLite，请使用 MySQL 8.0 版本。
    + 例子：`SQL_DSN=root:123456@tcp(localhost:3306)/one-api`
 4. `FRONTEND_BASE_URL`：设置之后将使用指定的前端地址，而非后端地址。
    + 例子：`FRONTEND_BASE_URL=https://openai.justsong.cn`
@@ -200,4 +260,14 @@ https://openai.justsong.cn
    + 请检查你的令牌额度是否足够，这个和账户额度是分开的。
    + 令牌额度仅供用户设置最大使用量，用户可自由设置。
 2. 宝塔部署后访问出现空白页面？
-   + 自动配置的问题，详见[#97](https://github.com/songquanpeng/one-api/issues/97)。
+   + 自动配置的问题，详见[#97](https://github.com/songquanpeng/one-api/issues/97)。
+3. 提示无可用渠道？
+   + 请检查的用户分组和渠道分组设置。
+   + 以及渠道的模型设置。
+
+## 注意
+本项目为开源项目，请在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及法律法规的情况下使用，不得用于非法用途。
+
+本项目使用 MIT 协议进行开源，请以某种方式保留 One API 的版权信息。
+
+依据 MIT 协议，使用者需自行承担使用本项目的风险与责任，本开源项目开发者与此无关。

common/constants.go

@@ -1,9 +1,10 @@
 package common
 
 import (
-	"github.com/google/uuid"
 	"sync"
 	"time"
+
+	"github.com/google/uuid"
 )
 
 var StartTime = time.Now().Unix() // unit: second
@@ -35,6 +36,8 @@ var WeChatAuthEnabled = false
 var TurnstileCheckEnabled = false
 var RegisterEnabled = true
 
+var LogConsumeEnabled = true
+
 var SMTPServer = ""
 var SMTPPort = 587
 var SMTPAccount = ""
@@ -131,6 +134,7 @@ const (
 	ChannelTypeAILS      = 9
 	ChannelTypeAIProxy   = 10
 	ChannelTypePaLM      = 11
+	ChannelTypeAPI2GPT   = 12
 )
 
 var ChannelBaseURLs = []string{
@@ -146,4 +150,5 @@ var ChannelBaseURLs = []string{
 	"https://api.caipacity.com",   // 9
 	"https://api.aiproxy.io",      // 10
 	"",                            // 11
+	"https://api.api2gpt.com",     // 12
 }

common/group-ratio.go

@@ -17,6 +17,7 @@ func GroupRatio2JSONString() string {
 }
 
 func UpdateGroupRatioByJSONString(jsonStr string) error {
+	GroupRatio = make(map[string]float64)
 	return json.Unmarshal([]byte(jsonStr), &GroupRatio)
 }
 

common/model-ratio.go

@@ -2,16 +2,23 @@ package common
 
 import "encoding/json"
 
+// ModelRatio
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://openai.com/pricing
 // TODO: when a new api is enabled, check the pricing here
+// 1 === $0.002 / 1K tokens
 var ModelRatio = map[string]float64{
 	"gpt-4":                   15,
 	"gpt-4-0314":              15,
+	"gpt-4-0613":              15,
 	"gpt-4-32k":               30,
 	"gpt-4-32k-0314":          30,
-	"gpt-3.5-turbo":           1, // $0.002 / 1K tokens
-	"gpt-3.5-turbo-0301":      1,
+	"gpt-4-32k-0613":          30,
+	"gpt-3.5-turbo":           0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-0301":      0.75,
+	"gpt-3.5-turbo-0613":      0.75,
+	"gpt-3.5-turbo-16k":       1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k-0613":  1.5,
 	"text-ada-001":            0.2,
 	"text-babbage-001":        0.25,
 	"text-curie-001":          1,
@@ -39,6 +46,7 @@ func ModelRatio2JSONString() string {
 }
 
 func UpdateModelRatioByJSONString(jsonStr string) error {
+	ModelRatio = make(map[string]float64)
 	return json.Unmarshal([]byte(jsonStr), &ModelRatio)
 }
 

controller/channel-billing.go

@@ -4,13 +4,14 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
 // https://github.com/songquanpeng/one-api/issues/79
@@ -37,6 +38,119 @@ type OpenAIUsageResponse struct {
 	TotalUsage float64 `json:"total_usage"` // unit: 0.01 dollar
 }
 
+type OpenAISBUsageResponse struct {
+	Msg  string `json:"msg"`
+	Data *struct {
+		Credit string `json:"credit"`
+	} `json:"data"`
+}
+
+type AIProxyUserOverviewResponse struct {
+	Success   bool   `json:"success"`
+	Message   string `json:"message"`
+	ErrorCode int    `json:"error_code"`
+	Data      struct {
+		TotalPoints float64 `json:"totalPoints"`
+	} `json:"data"`
+}
+
+type API2GPTUsageResponse struct {
+	Object         string  `json:"object"`
+	TotalGranted   float64 `json:"total_granted"`
+	TotalUsed      float64 `json:"total_used"`
+	TotalRemaining float64 `json:"total_remaining"`
+}
+
+// GetAuthHeader get auth header
+func GetAuthHeader(token string) http.Header {
+	h := http.Header{}
+	h.Add("Authorization", fmt.Sprintf("Bearer %s", token))
+	return h
+}
+
+func GetResponseBody(method, url string, channel *model.Channel, headers http.Header) ([]byte, error) {
+	client := &http.Client{}
+	req, err := http.NewRequest(method, url, nil)
+	if err != nil {
+		return nil, err
+	}
+	for k := range headers {
+		req.Header.Add(k, headers.Get(k))
+	}
+	res, err := client.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	body, err := io.ReadAll(res.Body)
+	if err != nil {
+		return nil, err
+	}
+	err = res.Body.Close()
+	if err != nil {
+		return nil, err
+	}
+	return body, nil
+}
+
+func updateChannelOpenAISBBalance(channel *model.Channel) (float64, error) {
+	url := fmt.Sprintf("https://api.openai-sb.com/sb-api/user/status?api_key=%s", channel.Key)
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
+	if err != nil {
+		return 0, err
+	}
+	response := OpenAISBUsageResponse{}
+	err = json.Unmarshal(body, &response)
+	if err != nil {
+		return 0, err
+	}
+	if response.Data == nil {
+		return 0, errors.New(response.Msg)
+	}
+	balance, err := strconv.ParseFloat(response.Data.Credit, 64)
+	if err != nil {
+		return 0, err
+	}
+	channel.UpdateBalance(balance)
+	return balance, nil
+}
+
+func updateChannelAIProxyBalance(channel *model.Channel) (float64, error) {
+	url := "https://aiproxy.io/api/report/getUserOverview"
+	headers := http.Header{}
+	headers.Add("Api-Key", channel.Key)
+	body, err := GetResponseBody("GET", url, channel, headers)
+	if err != nil {
+		return 0, err
+	}
+	response := AIProxyUserOverviewResponse{}
+	err = json.Unmarshal(body, &response)
+	if err != nil {
+		return 0, err
+	}
+	if !response.Success {
+		return 0, fmt.Errorf("code: %d, message: %s", response.ErrorCode, response.Message)
+	}
+	channel.UpdateBalance(response.Data.TotalPoints)
+	return response.Data.TotalPoints, nil
+}
+
+func updateChannelAPI2GPTBalance(channel *model.Channel) (float64, error) {
+	url := "https://api.api2gpt.com/dashboard/billing/credit_grants"
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
+
+	if err != nil {
+		return 0, err
+	}
+	response := API2GPTUsageResponse{}
+	err = json.Unmarshal(body, &response)
+	fmt.Print(response)
+	if err != nil {
+		return 0, err
+	}
+	channel.UpdateBalance(response.TotalRemaining)
+	return response.TotalRemaining, nil
+}
+
 func updateChannelBalance(channel *model.Channel) (float64, error) {
 	baseURL := common.ChannelBaseURLs[channel.Type]
 	switch channel.Type {
@@ -48,27 +162,18 @@ func updateChannelBalance(channel *model.Channel) (float64, error) {
 		return 0, errors.New("尚未实现")
 	case common.ChannelTypeCustom:
 		baseURL = channel.BaseURL
+	case common.ChannelTypeOpenAISB:
+		return updateChannelOpenAISBBalance(channel)
+	case common.ChannelTypeAIProxy:
+		return updateChannelAIProxyBalance(channel)
+	case common.ChannelTypeAPI2GPT:
+		return updateChannelAPI2GPTBalance(channel)
 	default:
 		return 0, errors.New("尚未实现")
 	}
 	url := fmt.Sprintf("%s/v1/dashboard/billing/subscription", baseURL)
 
-	client := &http.Client{}
-	req, err := http.NewRequest("GET", url, nil)
-	if err != nil {
-		return 0, err
-	}
-	auth := fmt.Sprintf("Bearer %s", channel.Key)
-	req.Header.Add("Authorization", auth)
-	res, err := client.Do(req)
-	if err != nil {
-		return 0, err
-	}
-	body, err := io.ReadAll(res.Body)
-	if err != nil {
-		return 0, err
-	}
-	err = res.Body.Close()
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
 	if err != nil {
 		return 0, err
 	}
@@ -84,20 +189,7 @@ func updateChannelBalance(channel *model.Channel) (float64, error) {
 		startDate = now.AddDate(0, 0, -100).Format("2006-01-02")
 	}
 	url = fmt.Sprintf("%s/v1/dashboard/billing/usage?start_date=%s&end_date=%s", baseURL, startDate, endDate)
-	req, err = http.NewRequest("GET", url, nil)
-	if err != nil {
-		return 0, err
-	}
-	req.Header.Add("Authorization", auth)
-	res, err = client.Do(req)
-	if err != nil {
-		return 0, err
-	}
-	body, err = io.ReadAll(res.Body)
-	if err != nil {
-		return 0, err
-	}
-	err = res.Body.Close()
+	body, err = GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
 	if err != nil {
 		return 0, err
 	}

controller/model.go

@@ -71,6 +71,33 @@ func init() {
 			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-4",
 			Object:     "model",
@@ -89,6 +116,15 @@ func init() {
 			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",
@@ -107,6 +143,15 @@ func init() {
 			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:         "text-embedding-ada-002",
 			Object:     "model",

controller/relay-utils.go

@@ -58,6 +58,20 @@ func countTokenMessages(messages []Message, model string) int {
 	return tokenNum
 }
 
+func countTokenInput(input any, model string) int {
+	switch input.(type) {
+	case string:
+		return countTokenText(input.(string), model)
+	case []string:
+		text := ""
+		for _, s := range input.([]string) {
+			text += s
+		}
+		return countTokenText(text, model)
+	}
+	return 0
+}
+
 func countTokenText(text string, model string) int {
 	tokenEncoder := getTokenEncoder(model)
 	token := tokenEncoder.Encode(text, nil, nil)

controller/relay.go

@@ -32,13 +32,13 @@ const (
 type GeneralOpenAIRequest struct {
 	Model       string    `json:"model"`
 	Messages    []Message `json:"messages"`
-	Prompt      string    `json:"prompt"`
+	Prompt      any       `json:"prompt"`
 	Stream      bool      `json:"stream"`
 	MaxTokens   int       `json:"max_tokens"`
 	Temperature float64   `json:"temperature"`
 	TopP        float64   `json:"top_p"`
 	N           int       `json:"n"`
-	Input       string    `json:"input"`
+	Input       any       `json:"input"`
 }
 
 type ChatRequest struct {
@@ -177,6 +177,7 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		// 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)
 	} else if channelType == common.ChannelTypePaLM {
 		err := relayPaLM(textRequest, c)
@@ -187,9 +188,9 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	case RelayModeChatCompletions:
 		promptTokens = countTokenMessages(textRequest.Messages, textRequest.Model)
 	case RelayModeCompletions:
-		promptTokens = countTokenText(textRequest.Prompt, textRequest.Model)
+		promptTokens = countTokenInput(textRequest.Prompt, textRequest.Model)
 	case RelayModeModeration:
-		promptTokens = countTokenText(textRequest.Input, textRequest.Model)
+		promptTokens = countTokenInput(textRequest.Input, textRequest.Model)
 	}
 	preConsumedTokens := common.PreConsumedQuota
 	if textRequest.MaxTokens != 0 {
@@ -239,16 +240,15 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	defer func() {
 		if consumeQuota {
 			quota := 0
-			usingGPT4 := strings.HasPrefix(textRequest.Model, "gpt-4")
-			completionRatio := 1
-			if usingGPT4 {
+			completionRatio := 1.34 // default for gpt-3
+			if strings.HasPrefix(textRequest.Model, "gpt-4") {
 				completionRatio = 2
 			}
 			if isStream {
 				responseTokens := countTokenText(streamResponseText, textRequest.Model)
-				quota = promptTokens + responseTokens*completionRatio
+				quota = promptTokens + int(float64(responseTokens)*completionRatio)
 			} else {
-				quota = textResponse.Usage.PromptTokens + textResponse.Usage.CompletionTokens*completionRatio
+				quota = textResponse.Usage.PromptTokens + int(float64(textResponse.Usage.CompletionTokens)*completionRatio)
 			}
 			quota = int(float64(quota) * ratio)
 			if ratio != 0 && quota <= 0 {
@@ -259,8 +259,12 @@ func relayHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			if err != nil {
 				common.SysError("Error consuming token remain quota: " + err.Error())
 			}
+			tokenName := c.GetString("token_name")
 			userId := c.GetInt("id")
-			model.RecordLog(userId, model.LogTypeConsume, fmt.Sprintf("使用模型 %s 消耗 %d 点额度（模型倍率 %.2f，分组倍率 %.2f）", textRequest.Model, quota, modelRatio, groupRatio))
+			model.RecordLog(userId, model.LogTypeConsume, fmt.Sprintf("通过令牌「%s」使用模型 %s 消耗 %d 点额度（模型倍率 %.2f，分组倍率 %.2f）", tokenName, textRequest.Model, quota, modelRatio, groupRatio))
+			model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+			channelId := c.GetInt("channel_id")
+			model.UpdateChannelUsedQuota(channelId, quota)
 		}
 	}()
 
@@ -395,3 +399,15 @@ func RelayNotImplemented(c *gin.Context) {
 		"error": err,
 	})
 }
+
+func RelayNotFound(c *gin.Context) {
+	err := OpenAIError{
+		Message: fmt.Sprintf("API not found: %s:%s", c.Request.Method, c.Request.URL.Path),
+		Type:    "one_api_error",
+		Param:   "",
+		Code:    "api_not_found",
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"error": err,
+	})
+}

middleware/auth.go

@@ -112,6 +112,7 @@ func TokenAuth() func(c *gin.Context) {
 		}
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
+		c.Set("token_name", token.Name)
 		requestURL := c.Request.URL.String()
 		consumeQuota := true
 		if strings.HasPrefix(requestURL, "/v1/models") {

middleware/cors.go

@@ -10,6 +10,6 @@ func CORS() gin.HandlerFunc {
 	config.AllowAllOrigins = true
 	config.AllowCredentials = true
 	config.AllowMethods = []string{"GET", "POST", "PUT", "DELETE", "OPTIONS"}
-	config.AllowHeaders = []string{"Origin", "Content-Length", "Content-Type", "Authorization", "Accept", "Connection"}
+	config.AllowHeaders = []string{"Origin", "Content-Length", "Content-Type", "Authorization", "Accept", "Connection", "x-requested-with"}
 	return cors.New(config)
 }

model/ability.go

@@ -30,15 +30,18 @@ func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 
 func (channel *Channel) AddAbilities() error {
 	models_ := strings.Split(channel.Models, ",")
+	groups_ := strings.Split(channel.Group, ",")
 	abilities := make([]Ability, 0, len(models_))
 	for _, model := range models_ {
-		ability := Ability{
-			Group:     channel.Group,
-			Model:     model,
-			ChannelId: channel.Id,
-			Enabled:   channel.Status == common.ChannelStatusEnabled,
+		for _, group := range groups_ {
+			ability := Ability{
+				Group:     group,
+				Model:     model,
+				ChannelId: channel.Id,
+				Enabled:   channel.Status == common.ChannelStatusEnabled,
+			}
+			abilities = append(abilities, ability)
 		}
-		abilities = append(abilities, ability)
 	}
 	return DB.Create(&abilities).Error
 }

model/channel.go

@@ -1,6 +1,7 @@
 package model
 
 import (
+	"gorm.io/gorm"
 	"one-api/common"
 )
 
@@ -20,6 +21,7 @@ type Channel struct {
 	BalanceUpdatedTime int64   `json:"balance_updated_time" gorm:"bigint"`
 	Models             string  `json:"models"`
 	Group              string  `json:"group" gorm:"type:varchar(32);default:'default'"`
+	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
 }
 
 func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
@@ -136,3 +138,10 @@ func UpdateChannelStatusById(id int, status int) {
 		common.SysError("failed to update channel status: " + err.Error())
 	}
 }
+
+func UpdateChannelUsedQuota(id int, quota int) {
+	err := DB.Model(&Channel{}).Where("id = ?", id).Update("used_quota", gorm.Expr("used_quota + ?", quota)).Error
+	if err != nil {
+		common.SysError("failed to update channel used quota: " + err.Error())
+	}
+}

model/log.go

@@ -22,6 +22,9 @@ const (
 )
 
 func RecordLog(userId int, logType int, content string) {
+	if logType == LogTypeConsume && !common.LogConsumeEnabled {
+		return
+	}
 	log := &Log{
 		UserId:    userId,
 		CreatedAt: common.GetTimestamp(),

model/option.go

@@ -34,6 +34,7 @@ func InitOptionMap() {
 	common.OptionMap["TurnstileCheckEnabled"] = strconv.FormatBool(common.TurnstileCheckEnabled)
 	common.OptionMap["RegisterEnabled"] = strconv.FormatBool(common.RegisterEnabled)
 	common.OptionMap["AutomaticDisableChannelEnabled"] = strconv.FormatBool(common.AutomaticDisableChannelEnabled)
+	common.OptionMap["LogConsumeEnabled"] = strconv.FormatBool(common.LogConsumeEnabled)
 	common.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(common.ChannelDisableThreshold, 'f', -1, 64)
 	common.OptionMap["SMTPServer"] = ""
 	common.OptionMap["SMTPFrom"] = ""
@@ -134,6 +135,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.RegisterEnabled = boolValue
 		case "AutomaticDisableChannelEnabled":
 			common.AutomaticDisableChannelEnabled = boolValue
+		case "LogConsumeEnabled":
+			common.LogConsumeEnabled = boolValue
 		}
 	}
 	switch key {

model/user.go

@@ -23,6 +23,8 @@ type User struct {
 	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'"`
 }
 
@@ -262,3 +264,15 @@ func GetRootUserEmail() (email string) {
 	DB.Model(&User{}).Where("role = ?", common.RoleRootUser).Select("email").Find(&email)
 	return email
 }
+
+func UpdateUserUsedQuotaAndRequestCount(id int, quota int) {
+	err := DB.Model(&User{}).Where("id = ?", id).Updates(
+		map[string]interface{}{
+			"used_quota":    gorm.Expr("used_quota + ?", quota),
+			"request_count": gorm.Expr("request_count + ?", 1),
+		},
+	).Error
+	if err != nil {
+		common.SysError("Failed to update user used quota and request count: " + err.Error())
+	}
+}

router/web-router.go

@@ -7,7 +7,9 @@ import (
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
+	"one-api/controller"
 	"one-api/middleware"
+	"strings"
 )
 
 func SetWebRouter(router *gin.Engine, buildFS embed.FS, indexPage []byte) {
@@ -16,6 +18,10 @@ func SetWebRouter(router *gin.Engine, buildFS embed.FS, indexPage []byte) {
 	router.Use(middleware.Cache())
 	router.Use(static.Serve("/", common.EmbedFolder(buildFS, "web/build")))
 	router.NoRoute(func(c *gin.Context) {
+		if strings.HasPrefix(c.Request.RequestURI, "/v1") {
+			controller.RelayNotFound(c)
+			return
+		}
 		c.Header("Cache-Control", "no-cache")
 		c.Data(http.StatusOK, "text/html; charset=utf-8", indexPage)
 	})

web/src/components/ChannelsTable.js

@@ -4,7 +4,7 @@ import { Link } from 'react-router-dom';
 import { API, showError, showInfo, showSuccess, timestamp2string } from '../helpers';
 
 import { CHANNEL_OPTIONS, ITEMS_PER_PAGE } from '../constants';
-import { renderGroup } from '../helpers/render';
+import { renderGroup, renderNumber } from '../helpers/render';
 
 function renderTimestamp(timestamp) {
   return (
@@ -27,6 +27,22 @@ function renderType(type) {
   return <Label basic color={type2label[type].color}>{type2label[type].text}</Label>;
 }
 
+function renderBalance(type, balance) {
+  switch (type) {
+    case 1: // OpenAI
+    case 8: // 自定义
+      return <span>${balance.toFixed(2)}</span>;
+    case 5: // OpenAI-SB
+      return <span>¥{(balance / 10000).toFixed(2)}</span>;
+    case 10: // AI Proxy
+      return <span>{renderNumber(balance)}</span>;
+    case 12: // API2GPT
+      return <span>¥{balance.toFixed(2)}</span>;
+    default:
+      return <span>不支持</span>;
+  }
+}
+
 const ChannelsTable = () => {
   const [channels, setChannels] = useState([]);
   const [loading, setLoading] = useState(true);
@@ -336,7 +352,7 @@ const ChannelsTable = () => {
                     <Popup
                       content={channel.balance_updated_time ? renderTimestamp(channel.balance_updated_time) : '未更新'}
                       key={channel.id}
-                      trigger={<span>${channel.balance.toFixed(2)}</span>}
+                      trigger={renderBalance(channel.type, channel.balance)}
                       basic
                     />
                   </Table.Cell>
@@ -415,7 +431,8 @@ const ChannelsTable = () => {
               <Button size='small' loading={loading} onClick={testAllChannels}>
                 测试所有已启用通道
               </Button>
-              <Button size='small' onClick={updateAllChannelsBalance} loading={loading || updatingBalance}>更新所有已启用通道余额</Button>
+              <Button size='small' onClick={updateAllChannelsBalance}
+                      loading={loading || updatingBalance}>更新所有已启用通道余额</Button>
               <Pagination
                 floated='right'
                 activePage={activePage}

web/src/components/Footer.js

@@ -1,11 +1,31 @@
-import React from 'react';
+import React, { useEffect, useState } from 'react';
 
 import { Container, Segment } from 'semantic-ui-react';
 import { getFooterHTML, getSystemName } from '../helpers';
 
 const Footer = () => {
   const systemName = getSystemName();
-  const footer = getFooterHTML();
+  const [footer, setFooter] = useState(getFooterHTML());
+  let remainCheckTimes = 5;
+
+  const loadFooter = () => {
+    let footer_html = localStorage.getItem('footer_html');
+    if (footer_html) {
+      setFooter(footer_html);
+    }
+  };
+
+  useEffect(() => {
+    const timer = setInterval(() => {
+      if (remainCheckTimes <= 0) {
+        clearInterval(timer);
+        return;
+      }
+      remainCheckTimes--;
+      loadFooter();
+    }, 200);
+    return () => clearTimeout(timer);
+  }, []);
 
   return (
     <Segment vertical>

web/src/components/OtherSetting.js

@@ -1,5 +1,5 @@
 import React, { useEffect, useState } from 'react';
-import { Button, Divider, Form, Grid, Header, Modal } from 'semantic-ui-react';
+import { Button, Divider, Form, Grid, Header, Message, Modal } from 'semantic-ui-react';
 import { API, showError, showSuccess } from '../helpers';
 import { marked } from 'marked';
 
@@ -10,13 +10,13 @@ const OtherSetting = () => {
     About: '',
     SystemName: '',
     Logo: '',
-    HomePageContent: '',
+    HomePageContent: ''
   });
   let [loading, setLoading] = useState(false);
   const [showUpdateModal, setShowUpdateModal] = useState(false);
   const [updateData, setUpdateData] = useState({
     tag_name: '',
-    content: '',
+    content: ''
   });
 
   const getOptions = async () => {
@@ -43,7 +43,7 @@ const OtherSetting = () => {
     setLoading(true);
     const res = await API.put('/api/option/', {
       key,
-      value,
+      value
     });
     const { success, message } = res.data;
     if (success) {
@@ -97,7 +97,7 @@ const OtherSetting = () => {
     } else {
       setUpdateData({
         tag_name: tag_name,
-        content: marked.parse(body),
+        content: marked.parse(body)
       });
       setShowUpdateModal(true);
     }
@@ -153,7 +153,7 @@ const OtherSetting = () => {
               style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
             />
           </Form.Group>
-          <Form.Button onClick={()=>submitOption('HomePageContent')}>保存首页内容</Form.Button>
+          <Form.Button onClick={() => submitOption('HomePageContent')}>保存首页内容</Form.Button>
           <Form.Group widths='equal'>
             <Form.TextArea
               label='关于'
@@ -165,6 +165,7 @@ const OtherSetting = () => {
             />
           </Form.Group>
           <Form.Button onClick={submitAbout}>保存关于</Form.Button>
+          <Message>移除 One API 的版权标识必须首先获得授权，后续版本将通过授权码强制执行。</Message>
           <Form.Group widths='equal'>
             <Form.Input
               label='页脚'

web/src/components/SystemSetting.js

@@ -34,6 +34,7 @@ const SystemSetting = () => {
     TopUpLink: '',
     AutomaticDisableChannelEnabled: '',
     ChannelDisableThreshold: 0,
+    LogConsumeEnabled: '',
   });
   const [originInputs, setOriginInputs] = useState({});
   let [loading, setLoading] = useState(false);
@@ -68,6 +69,7 @@ const SystemSetting = () => {
       case 'TurnstileCheckEnabled':
       case 'RegisterEnabled':
       case 'AutomaticDisableChannelEnabled':
+      case 'LogConsumeEnabled':
         value = inputs[key] === 'true' ? 'false' : 'true';
         break;
       default:
@@ -349,6 +351,12 @@ const SystemSetting = () => {
               placeholder='为一个 JSON 文本，键为分组名称，值为倍率'
             />
           </Form.Group>
+          <Form.Checkbox
+            checked={inputs.LogConsumeEnabled === 'true'}
+            label='启用额度消费日志记录'
+            name='LogConsumeEnabled'
+            onChange={handleInputChange}
+          />
           <Form.Button onClick={submitOperationConfig}>保存运营设置</Form.Button>
           <Divider />
           <Header as='h3'>

web/src/components/UsersTable.js

@@ -4,7 +4,7 @@ import { Link } from 'react-router-dom';
 import { API, showError, showSuccess } from '../helpers';
 
 import { ITEMS_PER_PAGE } from '../constants';
-import { renderGroup, renderText } from '../helpers/render';
+import { renderGroup, renderNumber, renderText } from '../helpers/render';
 
 function renderRole(role) {
   switch (role) {
@@ -197,7 +197,7 @@ const UsersTable = () => {
                 sortUser('quota');
               }}
             >
-              剩余额度
+              统计信息
             </Table.HeaderCell>
             <Table.HeaderCell
               style={{ cursor: 'pointer' }}
@@ -241,7 +241,11 @@ const UsersTable = () => {
                   </Table.Cell>
                   <Table.Cell>{renderGroup(user.group)}</Table.Cell>
                   <Table.Cell>{user.email ? renderText(user.email, 30) : '无'}</Table.Cell>
-                  <Table.Cell>{user.quota}</Table.Cell>
+                  <Table.Cell>
+                    <Popup content='剩余额度' trigger={<Label>{renderNumber(user.quota)}</Label>} />
+                    <Popup content='已用额度' trigger={<Label>{renderNumber(user.used_quota)}</Label>} />
+                    <Popup content='请求次数' trigger={<Label>{renderNumber(user.request_count)}</Label>} />
+                  </Table.Cell>
                   <Table.Cell>{renderRole(user.role)}</Table.Cell>
                   <Table.Cell>{renderStatus(user.status)}</Table.Cell>
                   <Table.Cell>

web/src/constants/channel.constants.js

@@ -8,5 +8,6 @@ export const CHANNEL_OPTIONS = [
   { key: 6, text: 'OpenAI Max', value: 6, color: 'violet' },
   { key: 7, text: 'OhMyGPT', value: 7, color: 'purple' },
   { key: 9, text: 'AI.LS', value: 9, color: 'yellow' },
-  { key: 10, text: 'AI Proxy', value: 10, color: 'purple' }
+  { key: 10, text: 'AI Proxy', value: 10, color: 'purple' },
+  { key: 12, text: 'API2GPT', value: 12, color: 'blue' }
 ];

web/src/helpers/render.js

@@ -8,12 +8,31 @@ export function renderText(text, limit) {
 }
 
 export function renderGroup(group) {
-  if (group === "") {
-    return <Label>default</Label>
-  } else if (group === "vip" || group === "pro") {
-    return <Label color='yellow'>{group}</Label>
-  } else if (group === "svip" || group === "premium") {
-    return <Label color='red'>{group}</Label>
+  if (group === '') {
+    return <Label>default</Label>;
+  }
+  let groups = group.split(',');
+  groups.sort();
+  return <>
+    {groups.map((group) => {
+      if (group === 'vip' || group === 'pro') {
+        return <Label color='yellow'>{group}</Label>;
+      } else if (group === 'svip' || group === 'premium') {
+        return <Label color='red'>{group}</Label>;
+      }
+      return <Label>{group}</Label>;
+    })}
+  </>;
+}
+
+export function renderNumber(num) {
+  if (num >= 1000000000) {
+    return (num / 1000000000).toFixed(1) + 'B';
+  } else if (num >= 1000000) {
+    return (num / 1000000).toFixed(1) + 'M';
+  } else if (num >= 10000) {
+    return (num / 1000).toFixed(1) + 'k';
+  } else {
+    return num;
   }
-  return <Label>{group}</Label>
 }

web/src/pages/Channel/EditChannel.js

@@ -15,8 +15,8 @@ const EditChannel = () => {
     key: '',
     base_url: '',
     other: '',
-    group: 'default',
     models: [],
+    groups: ['default']
   };
   const [batch, setBatch] = useState(false);
   const [inputs, setInputs] = useState(originInputs);
@@ -37,6 +37,11 @@ const EditChannel = () => {
       } else {
         data.models = data.models.split(",")
       }
+      if (data.group === "") {
+        data.groups = []
+      } else {
+        data.groups = data.group.split(",")
+      }
       setInputs(data);
     } else {
       showError(message);
@@ -61,7 +66,7 @@ const EditChannel = () => {
 
   const fetchGroups = async () => {
     try {
-      let res = await API.get(`/api/group`);
+      let res = await API.get(`/api/group/`);
       setGroupOptions(res.data.data.map((group) => ({
         key: group,
         text: group,
@@ -94,6 +99,7 @@ const EditChannel = () => {
     }
     let res;
     localInputs.models = localInputs.models.join(",")
+    localInputs.group = localInputs.groups.join(",")
     if (isEdit) {
       res = await API.put(`/api/channel/`, { ...localInputs, id: parseInt(channelId) });
     } else {
@@ -185,14 +191,14 @@ const EditChannel = () => {
             <Form.Dropdown
               label='分组'
               placeholder={'请选择分组'}
-              name='group'
+              name='groups'
               fluid
-              search
+              multiple
               selection
               allowAdditions
               additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
               onChange={handleInputChange}
-              value={inputs.group}
+              value={inputs.groups}
               autoComplete='new-password'
               options={groupOptions}
             />

web/src/pages/User/EditUser.js

@@ -25,7 +25,7 @@ const EditUser = () => {
   };
   const fetchGroups = async () => {
     try {
-      let res = await API.get(`/api/group`);
+      let res = await API.get(`/api/group/`);
       setGroupOptions(res.data.data.map((group) => ({
         key: group,
         text: group,