feat: 完善audio计费

Merge pull request #555 from utopeadia/main
Continue fixing Ollama embedding return issue
2025-11-17 19:13:42 +08:00 · 2024-11-07 16:12:09 +08:00 · 2024-11-06 21:13:06 +08:00 · 2024-11-06 19:33:50 +08:00 · 2024-11-06 01:21:02 +00:00 · 2024-11-05 22:05:45 +08:00
144 changed files with 5685 additions and 9831 deletions
--- a/.github/FUNDING.yml
+++ b/.github/FUNDING.yml
@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: ['https://afdian.com/a/new-api'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,5 +1,5 @@
 blank_issues_enabled: false
 contact_links:
-  - name: 交流社区
-    url: https://linux.do
-    about: 项目交流社区
+  - name: 项目群聊
+    url: https://private-user-images.githubusercontent.com/61247483/283011625-de536a8a-0161-47a7-a0a2-66ef6de81266.jpeg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTEiLCJleHAiOjE3MDIyMjQzOTAsIm5iZiI6MTcwMjIyNDA5MCwicGF0aCI6Ii82MTI0NzQ4My8yODMwMTE2MjUtZGU1MzZhOGEtMDE2MS00N2E3LWEwYTItNjZlZjZkZTgxMjY2LmpwZWc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBSVdOSllBWDRDU1ZFSDUzQSUyRjIwMjMxMjEwJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDIzMTIxMFQxNjAxMzBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT02MGIxYmM3ZDQyYzBkOTA2ZTYyYmVmMzQ1NjY4NjM1YjY0NTUzNTM5NjE1NDZkYTIzODdhYTk4ZjZjODJmYzY2JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.TJ8CTfOSwR0-CHS1KLfomqgL0e4YH1luy8lSLrkv5Zg
+    about: QQ 群：629454374
--- a/.github/workflows/docker-image-amd64.yml
+++ b/.github/workflows/docker-image-amd64.yml
@@ -1,6 +1,9 @@
 name: Publish Docker image (amd64)

 on:
+  push:
+    tags:
+      - '*'
  workflow_dispatch:
    inputs:
      name:
@@ -39,7 +42,7 @@ jobs:
        uses: docker/metadata-action@v4
        with:
          images: |
-            pengzhile/new-api
+            calciumion/new-api
            ghcr.io/${{ github.repository }}

      - name: Build and push Docker images
--- 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: |
-            pengzhile/new-api
+            calciumion/new-api
            ghcr.io/${{ github.repository }}

      - name: Build and push Docker images
--- a/10
+++ b/10
@@ -1,13 +1,13 @@
-FROM oven/bun:latest AS builder
+FROM node:16 as builder

 WORKDIR /build
 COPY web/package.json .
-RUN bun install
+RUN npm install
 COPY ./web .
 COPY ./VERSION .
-RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build
+RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) npm run build

-FROM golang:1.21 AS builder2
+FROM golang AS builder2

 ENV GO111MODULE=on \
    CGO_ENABLED=1 \
@@ -25,7 +25,7 @@ FROM alpine
 RUN apk update \
    && apk upgrade \
    && apk add --no-cache ca-certificates tzdata \
-    && update-ca-certificates
+    && update-ca-certificates 2>/dev/null || true

 COPY --from=builder2 /build/one-api /
 EXPOSE 3000
--- a/README.md
+++ b/README.md
@@ -48,10 +48,11 @@
    4. Telegram Bot 名称是bot username 去掉@后的字符串
 13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
 14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
+15. **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道。

 ## 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-*, g-*）
+1. 第三方模型 **gps** （gpt-4-gizmo-*）
 2. 智谱glm-4v，glm-4v识图
 3. Anthropic Claude 3
 4. [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)，添加渠道时，密钥可以随便填写，默认的请求地址是[http://localhost:11434](http://localhost:11434)，如果需要修改请在渠道中修改
@@ -63,7 +64,7 @@
 10. Dify
 11. Vertex AI，目前兼容Claude，Gemini，Llama3.1

-您可以在渠道中添加自定义模型gpt-4-gizmo-*或g-*，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。
+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。

 ## 比原版One API多出的配置
 - `GENERATE_DEFAULT_TOKEN`：是否为新注册用户生成初始令牌，默认为 `false`。
@@ -133,6 +134,9 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/1c66b593-bb9e-4757-9720-ff2759539242)
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/af9a07ee-5101-4b3d-8bd9-ae21a4fd7e9e)

+## 交流群
+<img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="200">
+
 ## 相关项目
 - [One API](https://github.com/songquanpeng/one-api)：原版项目
 - [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)：Midjourney接口支持
--- a/common/constants.go
+++ b/common/constants.go
@@ -9,20 +9,9 @@ import (
 	"github.com/google/uuid"
 )

-// Pay Settings
-
-var StripeApiSecret = ""
-var StripeWebhookSecret = ""
-var StripePriceId = ""
-var PaymentEnabled = false
-var StripeUnitPrice = 8.0
-var MinTopUp = 5
-
 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 OutProxyUrl = ""
 var Footer = ""
 var Logo = ""
 var TopUpLink = ""
@@ -52,12 +41,10 @@ var PasswordLoginEnabled = true
 var PasswordRegisterEnabled = true
 var EmailVerificationEnabled = false
 var GitHubOAuthEnabled = false
-var LinuxDoOAuthEnabled = false
 var WeChatAuthEnabled = false
 var TelegramOAuthEnabled = false
 var TurnstileCheckEnabled = false
 var RegisterEnabled = true
-var UserSelfDeletionEnabled = false

 var EmailDomainRestrictionEnabled = false // 是否启用邮箱域名限制
 var EmailAliasRestrictionEnabled = false  // 是否启用邮箱别名限制
@@ -88,10 +75,6 @@ var SMTPToken = ""
 var GitHubClientId = ""
 var GitHubClientSecret = ""

-var LinuxDoClientId = ""
-var LinuxDoClientSecret = ""
-var LinuxDoMinLevel = 0
-
 var WeChatServerAddress = ""
 var WeChatServerToken = ""
 var WeChatAccountQRCodeImageURL = ""
@@ -200,12 +183,6 @@ const (
 	ChannelStatusAutoDisabled     = 3
 )

-const (
-	TopUpStatusPending = "pending"
-	TopUpStatusSuccess = "success"
-	TopUpStatusExpired = "expired"
-)
-
 const (
 	ChannelTypeUnknown        = 0
 	ChannelTypeOpenAI         = 1
@@ -245,6 +222,7 @@ const (
 	ChannelCloudflare         = 39
 	ChannelTypeSiliconFlow    = 40
 	ChannelTypeVertexAi       = 41
+	ChannelTypeMistral        = 42

 	ChannelTypeDummy // this one is only for count, do not add any channel after this

@@ -293,4 +271,5 @@ var ChannelBaseURLs = []string{
 	"https://api.cloudflare.com",                //39
 	"https://api.siliconflow.cn",                //40
 	"",                                          //41
+	"https://api.mistral.ai",                    //42
 }
--- a/common/hash.go
+++ b/common/hash.go
@@ -1,84 +0,0 @@
-package common
-
-import (
-	"crypto/hmac"
-	"crypto/sha1"
-	"crypto/sha256"
-	"encoding/hex"
-	"math/rand"
-	"time"
-)
-
-func Sha256Raw(data string) []byte {
-	h := sha256.New()
-	h.Write([]byte(data))
-	return h.Sum(nil)
-}
-
-func Sha1Raw(data []byte) []byte {
-	h := sha1.New()
-	h.Write([]byte(data))
-	return h.Sum(nil)
-}
-
-func Sha1(data string) string {
-	return hex.EncodeToString(Sha1Raw([]byte(data)))
-}
-
-func HmacSha256Raw(message, key []byte) []byte {
-	h := hmac.New(sha256.New, key)
-	h.Write(message)
-	return h.Sum(nil)
-}
-
-func HmacSha256(message, key string) string {
-	return hex.EncodeToString(HmacSha256Raw([]byte(message), []byte(key)))
-}
-
-func RandomBytes(length int) []byte {
-	rand.Seed(time.Now().UnixNano())
-	b := make([]byte, length)
-	if _, err := rand.Read(b); err != nil {
-		panic(err)
-	}
-
-	return b
-}
-
-func RandomString(length int) string {
-	const chars = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
-	result := make([]byte, length)
-	randomBytes := RandomBytes(length)
-	for i := 0; i < length; i++ {
-		result[i] = chars[randomBytes[i]%byte(len(chars))]
-	}
-
-	return string(result)
-}
-
-func RandomHex(length int) string {
-	const chars = "abcdef0123456789"
-	result := make([]byte, length)
-	randomBytes := RandomBytes(length)
-	for i := 0; i < length; i++ {
-		result[i] = chars[randomBytes[i]%byte(len(chars))]
-	}
-
-	return string(result)
-}
-
-func RandomNumber(length int) string {
-	const chars = "0123456789"
-	result := make([]byte, length)
-	randomBytes := RandomBytes(length)
-	for i := 0; i < length; i++ {
-		result[i] = chars[randomBytes[i]%byte(len(chars))]
-	}
-
-	return string(result)
-}
-
-func RandomUUID() string {
-	all := RandomHex(32)
-	return all[:8] + "-" + all[8:12] + "-" + all[12:16] + "-" + all[16:20] + "-" + all[20:]
-}
--- a/common/logger.go
+++ b/common/logger.go
@@ -2,6 +2,7 @@ package common

 import (
 	"context"
+	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -99,10 +100,12 @@ func LogQuota(quota int) string {
 	}
 }

-func LogQuotaF(quota float64) string {
-	if DisplayInCurrencyEnabled {
-		return fmt.Sprintf("＄%.6f 额度", quota/QuotaPerUnit)
-	} else {
-		return fmt.Sprintf("%d 点额度", int64(quota))
+// LogJson 仅供测试使用 only for test
+func LogJson(ctx context.Context, msg string, obj any) {
+	jsonStr, err := json.Marshal(obj)
+	if err != nil {
+		LogError(ctx, fmt.Sprintf("json marshal failed: %s", err.Error()))
+		return
 	}
+	LogInfo(ctx, fmt.Sprintf("%s | %s", msg, string(jsonStr)))
 }
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -23,136 +23,136 @@ const (

 var defaultModelRatio = map[string]float64{
 	//"midjourney":                50,
-	"gpt-4-gizmo-*":                       15,
-	"g-*":                                 15,
-	"gpt-4":                               15,
-	"gpt-4-0314":                          15,
-	"gpt-4-0613":                          15,
-	"gpt-4-32k":                           30,
-	"gpt-4-32k-0314":                      30,
-	"gpt-4-32k-0613":                      30,
-	"gpt-4o-mini":                         0.075, // $0.00015 / 1K tokens
-	"gpt-4o-mini-2024-07-18":              0.075,
-	"chatgpt-4o-latest":                   2.5,  // $0.01 / 1K tokens
-	"gpt-4o":                              1.25, // $0.005 / 1K tokens
-	"gpt-4o-2024-05-13":                   2.5,  // $0.005 / 1K tokens
-	"gpt-4o-2024-08-06":                   1.25, // $0.01 / 1K tokens
-	"gpt-4o-2024-11-20":                   1.25, // $0.01 / 1K tokens
-	"o1-preview":                          7.5,
-	"o1-preview-2024-09-12":               7.5,
-	"o1-mini":                             0.55, // $0.0011 / 1K tokens
-	"o1-mini-2024-09-12":                  0.55,
-	"o3-mini":                             0.55,
-	"o3-mini-2025-01-31":                  0.55,
-	"gpt-4-turbo":                         5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":              5,    // $0.01 / 1K tokens
-	"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":                       0.25, // $0.0005 / 1K tokens
-	"gpt-3.5-turbo-0301":                  0.75,
-	"gpt-3.5-turbo-0613":                  0.75,
-	"gpt-3.5-turbo-16k":                   1.5, // $0.003 / 1K tokens
-	"gpt-3.5-turbo-16k-0613":              1.5,
-	"gpt-3.5-turbo-instruct":              0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-1106":                  0.5,  // $0.001 / 1K tokens
-	"gpt-3.5-turbo-0125":                  0.25,
-	"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,
-	"text-davinci-002":                    10,
-	"text-davinci-003":                    10,
-	"text-davinci-edit-001":               10,
-	"code-davinci-edit-001":               10,
-	"whisper-1":                           15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
-	"tts-1":                               7.5, // 1k characters -> $0.015
-	"tts-1-1106":                          7.5, // 1k characters -> $0.015
-	"tts-1-hd":                            15,  // 1k characters -> $0.03
-	"tts-1-hd-1106":                       15,  // 1k characters -> $0.03
-	"davinci":                             10,
-	"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,
-	"text-moderation-latest":              0.1,
-	"claude-instant-1":                    0.4, // $0.8 / 1M tokens
-	"claude-2.0":                          4,   // $8 / 1M tokens
-	"claude-2.1":                          4,   // $8 / 1M tokens
-	"claude-3-7-sonnet-20250219":          1.5,
-	"claude-3-7-sonnet-20250219-thinking": 1.5,
-	"claude-3-5-haiku-20241022":           0.4,
-	"claude-3-haiku-20240307":             0.125, // $0.25 / 1M tokens
-	"claude-3-5-sonnet-20240620":          1.5,   // $3 / 1M tokens
-	"claude-3-5-sonnet-20241022":          1.5,   // $3 / 1M tokens
-	"claude-3-sonnet-20240229":            1.5,   // $3 / 1M tokens
-	"claude-3-opus-20240229":              7.5,   // $15 / 1M tokens
-	"ERNIE-4.0-8K":                        0.120 * RMB,
-	"ERNIE-3.5-8K":                        0.012 * RMB,
-	"ERNIE-3.5-8K-0205":                   0.024 * RMB,
-	"ERNIE-3.5-8K-1222":                   0.012 * RMB,
-	"ERNIE-Bot-8K":                        0.024 * RMB,
-	"ERNIE-3.5-4K-0205":                   0.012 * RMB,
-	"ERNIE-Speed-8K":                      0.004 * RMB,
-	"ERNIE-Speed-128K":                    0.004 * RMB,
-	"ERNIE-Lite-8K-0922":                  0.008 * RMB,
-	"ERNIE-Lite-8K-0308":                  0.003 * RMB,
-	"ERNIE-Tiny-8K":                       0.001 * RMB,
-	"BLOOMZ-7B":                           0.004 * RMB,
-	"Embedding-V1":                        0.002 * RMB,
-	"bge-large-zh":                        0.002 * RMB,
-	"bge-large-en":                        0.002 * RMB,
-	"tao-8k":                              0.002 * RMB,
-	"PaLM-2":                              1,
-	"gemini-pro":                          1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-pro-vision":                   1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-1.0-pro-vision-001":           1,
-	"gemini-1.0-pro-001":                  1,
-	"gemini-1.5-pro-latest":               1.75, // $3.5 / 1M tokens
-	"gemini-1.5-pro-exp-0827":             1.75, // $3.5 / 1M tokens
-	"gemini-1.5-flash-latest":             1,
-	"gemini-1.5-flash-exp-0827":           1,
-	"gemini-1.0-pro-latest":               1,
-	"gemini-1.0-pro-vision-latest":        1,
-	"gemini-ultra":                        1,
-	"chatglm_turbo":                       0.3572,     // ￥0.005 / 1k tokens
-	"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":                              0.05 * RMB, // ￥0.05 / 1k tokens
-	"glm-4-alltools":                      0.1 * RMB,  // ￥0.1 / 1k tokens
-	"glm-3-turbo":                         0.3572,
-	"glm-4-plus":                          0.05 * RMB,
-	"glm-4-0520":                          0.1 * RMB,
-	"glm-4-air":                           0.001 * RMB,
-	"glm-4-airx":                          0.01 * RMB,
-	"glm-4-long":                          0.001 * RMB,
-	"glm-4-flash":                         0,
-	"glm-4v-plus":                         0.01 * RMB,
-	"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-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
-	"SparkDesk-v4.0":                      1.2858,
-	"360GPT_S2_V9":                        0.8572, // ¥0.012 / 1k tokens
-	"360gpt-turbo":                        0.0858, // ¥0.0012 / 1k tokens
-	"360gpt-turbo-responsibility-8k":      0.8572, // ¥0.012 / 1k tokens
-	"360gpt-pro":                          0.8572, // ¥0.012 / 1k tokens
-	"embedding-bert-512-v1":               0.0715, // ¥0.001 / 1k tokens
-	"embedding_s1_v1":                     0.0715, // ¥0.001 / 1k tokens
-	"semantic_similarity_s1_v1":           0.0715, // ¥0.001 / 1k tokens
-	"hunyuan":                             7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
+	"gpt-4-gizmo-*":  15,
+	"gpt-4o-gizmo-*": 2.5,
+	"gpt-4-all":      15,
+	"gpt-4o-all":     15,
+	"gpt-4":          15,
+	//"gpt-4-0314":                   15, //deprecated
+	"gpt-4-0613": 15,
+	"gpt-4-32k":  30,
+	//"gpt-4-32k-0314":               30, //deprecated
+	"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
+	"chatgpt-4o-latest":               2.5,  // $0.01 / 1K tokens
+	"gpt-4o":                          1.25, // $0.01 / 1K tokens
+	"gpt-4o-audio-preview":            1.25, // $0.0015 / 1K tokens
+	"gpt-4o-audio-preview-2024-10-01": 1.25, // $0.0015 / 1K tokens
+	"gpt-4o-2024-08-06":               1.25, // $0.01 / 1K tokens
+	"gpt-4o-2024-05-13":               2.5,
+	"gpt-4o-realtime-preview":         2.5,
+	"o1-preview":                      7.5,
+	"o1-preview-2024-09-12":           7.5,
+	"o1-mini":                         1.5,
+	"o1-mini-2024-09-12":              1.5,
+	"gpt-4o-mini":                     0.075,
+	"gpt-4o-mini-2024-07-18":          0.075,
+	"gpt-4-turbo":                     5, // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":          5, // $0.01 / 1K tokens
+	//"gpt-3.5-turbo-0301":           0.75, //deprecated
+	"gpt-3.5-turbo":          0.25,
+	"gpt-3.5-turbo-0613":     0.75,
+	"gpt-3.5-turbo-16k":      1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k-0613": 1.5,
+	"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":     0.5,  // $0.001 / 1K tokens
+	"gpt-3.5-turbo-0125":     0.25,
+	"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,
+	//"text-davinci-002":               10,
+	//"text-davinci-003":               10,
+	"text-davinci-edit-001":          10,
+	"code-davinci-edit-001":          10,
+	"whisper-1":                      15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"tts-1":                          7.5, // 1k characters -> $0.015
+	"tts-1-1106":                     7.5, // 1k characters -> $0.015
+	"tts-1-hd":                       15,  // 1k characters -> $0.03
+	"tts-1-hd-1106":                  15,  // 1k characters -> $0.03
+	"davinci":                        10,
+	"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,
+	"text-moderation-latest":         0.1,
+	"claude-instant-1":               0.4,   // $0.8 / 1M tokens
+	"claude-2.0":                     4,     // $8 / 1M tokens
+	"claude-2.1":                     4,     // $8 / 1M tokens
+	"claude-3-haiku-20240307":        0.125, // $0.25 / 1M tokens
+	"claude-3-5-haiku-20241022":      0.5,   // $1 / 1M tokens
+	"claude-3-sonnet-20240229":       1.5,   // $3 / 1M tokens
+	"claude-3-5-sonnet-20240620":     1.5,
+	"claude-3-5-sonnet-20241022":     1.5,
+	"claude-3-opus-20240229":         7.5, // $15 / 1M tokens
+	"ERNIE-4.0-8K":                   0.120 * RMB,
+	"ERNIE-3.5-8K":                   0.012 * RMB,
+	"ERNIE-3.5-8K-0205":              0.024 * RMB,
+	"ERNIE-3.5-8K-1222":              0.012 * RMB,
+	"ERNIE-Bot-8K":                   0.024 * RMB,
+	"ERNIE-3.5-4K-0205":              0.012 * RMB,
+	"ERNIE-Speed-8K":                 0.004 * RMB,
+	"ERNIE-Speed-128K":               0.004 * RMB,
+	"ERNIE-Lite-8K-0922":             0.008 * RMB,
+	"ERNIE-Lite-8K-0308":             0.003 * RMB,
+	"ERNIE-Tiny-8K":                  0.001 * RMB,
+	"BLOOMZ-7B":                      0.004 * RMB,
+	"Embedding-V1":                   0.002 * RMB,
+	"bge-large-zh":                   0.002 * RMB,
+	"bge-large-en":                   0.002 * RMB,
+	"tao-8k":                         0.002 * RMB,
+	"PaLM-2":                         1,
+	"gemini-pro":                     1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro-vision-001":      1,
+	"gemini-1.0-pro-001":             1,
+	"gemini-1.5-pro-latest":          1.75, // $3.5 / 1M tokens
+	"gemini-1.5-pro-exp-0827":        1.75, // $3.5 / 1M tokens
+	"gemini-1.5-flash-latest":        1,
+	"gemini-1.5-flash-exp-0827":      1,
+	"gemini-1.0-pro-latest":          1,
+	"gemini-1.0-pro-vision-latest":   1,
+	"gemini-ultra":                   1,
+	"chatglm_turbo":                  0.3572,     // ￥0.005 / 1k tokens
+	"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":                         0.05 * RMB, // ￥0.05 / 1k tokens
+	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":                    0.3572,
+	"glm-4-plus":                     0.05 * RMB,
+	"glm-4-0520":                     0.1 * RMB,
+	"glm-4-air":                      0.001 * RMB,
+	"glm-4-airx":                     0.01 * RMB,
+	"glm-4-long":                     0.001 * RMB,
+	"glm-4-flash":                    0,
+	"glm-4v-plus":                    0.01 * RMB,
+	"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-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
+	"SparkDesk-v4.0":                 1.2858,
+	"360GPT_S2_V9":                   0.8572, // ¥0.012 / 1k tokens
+	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
+	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
+	"360gpt-pro":                     0.8572, // ¥0.012 / 1k tokens
+	"embedding-bert-512-v1":          0.0715, // ¥0.001 / 1k tokens
+	"embedding_s1_v1":                0.0715, // ¥0.001 / 1k tokens
+	"semantic_similarity_s1_v1":      0.0715, // ¥0.001 / 1k tokens
+	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
 	"yi-34b-chat-0205":       0.18,
@@ -187,10 +187,8 @@ var defaultModelRatio = map[string]float64{
 var defaultModelPrice = map[string]float64{
 	"suno_music":        0.1,
 	"suno_lyrics":       0.01,
-	"dall-e-2":          0.02,
 	"dall-e-3":          0.04,
 	"gpt-4-gizmo-*":     0.1,
-	"g-*":               0.1,
 	"mj_imagine":        0.1,
 	"mj_variation":      0.1,
 	"mj_reroll":         0.1,
@@ -220,10 +218,9 @@ var (

 var CompletionRatio map[string]float64 = nil
 var defaultCompletionRatio = map[string]float64{
-	"gpt-4-gizmo-*": 2,
-	"g-*":           2,
-	"gpt-4-all":     2,
-	"gpt-4o-all":    2,
+	"gpt-4-gizmo-*":  2,
+	"gpt-4o-gizmo-*": 3,
+	"gpt-4-all":      2,
 }

 func GetModelPriceMap() map[string]float64 {
@@ -256,8 +253,9 @@ func GetModelPrice(name string, printErr bool) (float64, bool) {
 	GetModelPriceMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
-	} else if strings.HasPrefix(name, "g-") {
-		name = "g-*"
+	}
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
 	}
 	price, ok := modelPriceMap[name]
 	if !ok {
@@ -298,8 +296,6 @@ func GetModelRatio(name string) float64 {
 	GetModelRatioMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
-	} else if strings.HasPrefix(name, "g-") {
-		name = "g-*"
 	}
 	ratio, ok := modelRatioMap[name]
 	if !ok {
@@ -340,49 +336,46 @@ func UpdateCompletionRatioByJSONString(jsonStr string) error {
 func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
-	} else if strings.HasPrefix(name, "g-") {
-		name = "g-*"
 	}
-	if strings.HasPrefix(name, "gpt-3.5") {
-		if strings.HasSuffix(name, "0125") {
-			return 3
-		}
-		if strings.HasSuffix(name, "1106") {
-			return 2
-		}
-		if name == "gpt-3.5-turbo" {
-			return 3
-		}
-
-		return 4.0 / 3.0
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
 	}
-	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
-		if strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4-turbo") || "gpt-4o-2024-05-13" == name {
-			return 3
-		}
-
+	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
 		if strings.HasPrefix(name, "gpt-4o") {
+			if name == "gpt-4o-2024-05-13" {
+				return 3
+			}
 			return 4
 		}
-
+		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
+			return 3
+		}
 		return 2
 	}
-	if "o1" == name || strings.HasPrefix(name, "o1-") {
-		return 4
-	}
-	if "o3" == name || strings.HasPrefix(name, "o3-") {
+	if strings.HasPrefix(name, "o1-") {
 		return 4
 	}
 	if name == "chatgpt-4o-latest" {
 		return 3
 	}
-	if strings.HasPrefix(name, "claude-instant-1") {
+	if strings.Contains(name, "claude-instant-1") {
 		return 3
-	} else if strings.HasPrefix(name, "claude-2") {
+	} else if strings.Contains(name, "claude-2") {
 		return 3
-	} else if strings.HasPrefix(name, "claude-3") {
+	} else if strings.Contains(name, "claude-3") {
 		return 5
 	}
+	if strings.HasPrefix(name, "gpt-3.5") {
+		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
+			// https://openai.com/blog/new-embedding-models-and-api-updates
+			// Updated GPT-3.5 Turbo model and lower pricing
+			return 3
+		}
+		if strings.HasSuffix(name, "1106") {
+			return 2
+		}
+		return 4.0 / 3.0
+	}
 	if strings.HasPrefix(name, "mistral-") {
 		return 3
 	}
@@ -429,6 +422,34 @@ func GetCompletionRatio(name string) float64 {
 	return 1
 }

+func GetAudioRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4o-realtime") {
+		return 20
+	}
+	return 20
+}
+
+func GetAudioCompletionRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4o-realtime") {
+		return 2
+	}
+	return 2
+}
+
+//func GetAudioPricePerMinute(name string) float64 {
+//	if strings.HasPrefix(name, "gpt-4o-realtime") {
+//		return 0.06
+//	}
+//	return 0.06
+//}
+//
+//func GetAudioCompletionPricePerMinute(name string) float64 {
+//	if strings.HasPrefix(name, "gpt-4o-realtime") {
+//		return 0.24
+//	}
+//	return 0.24
+//}
+
 func GetCompletionRatioMap() map[string]float64 {
 	if CompletionRatio == nil {
 		CompletionRatio = defaultCompletionRatio
--- a/common/utils.go
+++ b/common/utils.go
@@ -1,20 +1,15 @@
 package common

 import (
-	"context"
-	"errors"
 	crand "crypto/rand"
 	"encoding/base64"
 	"fmt"
 	"github.com/google/uuid"
-	"golang.org/x/net/proxy"
 	"html/template"
 	"log"
 	"math/big"
 	"math/rand"
 	"net"
-	"net/http"
-	"net/url"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -211,56 +206,3 @@ func RandomSleep() {
 	// Sleep for 0-3000 ms
 	time.Sleep(time.Duration(rand.Intn(3000)) * time.Millisecond)
 }
-
-func GetProxiedHttpClient(proxyUrl string) (*http.Client, error) {
-	if "" == proxyUrl {
-		return &http.Client{}, nil
-	}
-
-	u, err := url.Parse(proxyUrl)
-	if err != nil {
-		return nil, err
-	}
-
-	if strings.HasPrefix(proxyUrl, "http") {
-
-		return &http.Client{
-			Transport: &http.Transport{
-				Proxy: http.ProxyURL(u),
-			},
-		}, nil
-	} else if strings.HasPrefix(proxyUrl, "socks") {
-		dialer, err := proxy.FromURL(u, proxy.Direct)
-		if err != nil {
-			return nil, err
-		}
-
-		return &http.Client{
-			Transport: &http.Transport{
-				DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
-					return dialer.(proxy.ContextDialer).DialContext(ctx, network, addr)
-				},
-			},
-		}, nil
-	}
-
-	return nil, errors.New("unsupported proxy type")
-}
-
-func ProxiedHttpGet(url, proxyUrl string) (*http.Response, error) {
-	client, err := GetProxiedHttpClient(proxyUrl)
-	if err != nil {
-		return nil, err
-	}
-
-	return client.Get(url)
-}
-
-func ProxiedHttpHead(url, proxyUrl string) (*http.Response, error) {
-	client, err := GetProxiedHttpClient(proxyUrl)
-	if err != nil {
-		return nil, err
-	}
-
-	return client.Head(url)
-}
--- a/constant/system-setting.go
+++ b/constant/system-setting.go
@@ -0,0 +1,9 @@
+package constant
+
+var ServerAddress = "http://localhost:3000"
+var WorkerUrl = ""
+var WorkerValidKey = ""
+
+func EnableWorker() bool {
+	return WorkerUrl != ""
+}
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -102,17 +102,22 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 	if err != nil {
 		return err, nil
 	}
-	if resp != nil && resp.StatusCode != http.StatusOK {
-		err := service.RelayErrorHandler(resp)
-		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), err
+	var httpResp *http.Response
+	if resp != nil {
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			err := service.RelayErrorHandler(httpResp)
+			return fmt.Errorf("status code %d: %s", httpResp.StatusCode, err.Error.Message), err
+		}
 	}
-	usage, respErr := adaptor.DoResponse(c, resp, meta)
+	usageA, respErr := adaptor.DoResponse(c, httpResp, meta)
 	if respErr != nil {
 		return fmt.Errorf("%s", respErr.Error.Message), respErr
 	}
-	if usage == nil {
+	if usageA == nil {
 		return errors.New("usage is nil"), nil
 	}
+	usage := usageA.(*dto.Usage)
 	result := w.Result()
 	respBody, err := io.ReadAll(result.Body)
 	if err != nil {
@@ -146,7 +151,7 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 		Model:  "", // this will be set later
 		Stream: false,
 	}
-	if "o1" == model || strings.HasPrefix(model, "o1-") {
+	if strings.HasPrefix(model, "o1-") {
 		testRequest.MaxCompletionTokens = 1
 	} else {
 		testRequest.MaxTokens = 1
--- a/controller/github.go
+++ b/controller/github.go
@@ -133,8 +133,6 @@ func GitHubOAuth(c *gin.Context) {
 		}
 	} else {
 		if common.RegisterEnabled {
-			user.InviterId, _ = model.GetUserIdByAffCode(c.Query("aff"))
-
 			user.Username = "github_" + strconv.Itoa(model.GetMaxUserId()+1)
 			if githubUser.Name != "" {
 				user.DisplayName = githubUser.Name
@@ -145,7 +143,7 @@ func GitHubOAuth(c *gin.Context) {
 			user.Role = common.RoleCommonUser
 			user.Status = common.UserStatusEnabled

-			if err := user.Insert(user.InviterId); err != nil {
+			if err := user.Insert(0); err != nil {
 				c.JSON(http.StatusOK, gin.H{
 					"success": false,
 					"message": err.Error(),
--- a/controller/linuxdo.go
+++ b/controller/linuxdo.go
@@ -1,247 +0,0 @@
-package controller
-
-import (
-	"bytes"
-	"encoding/base64"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"github.com/gin-contrib/sessions"
-	"github.com/gin-gonic/gin"
-	"net/http"
-	"net/url"
-	"one-api/common"
-	"one-api/model"
-	"strconv"
-	"time"
-)
-
-type LinuxDoOAuthResponse struct {
-	AccessToken string `json:"access_token"`
-	Scope       string `json:"scope"`
-	TokenType   string `json:"token_type"`
-}
-
-type LinuxDoUser struct {
-	ID         int    `json:"id"`
-	Username   string `json:"username"`
-	Name       string `json:"name"`
-	Active     bool   `json:"active"`
-	TrustLevel int    `json:"trust_level"`
-	Silenced   bool   `json:"silenced"`
-}
-
-func getLinuxDoUserInfoByCode(code string) (*LinuxDoUser, error) {
-	if code == "" {
-		return nil, errors.New("无效的参数")
-	}
-	auth := base64.StdEncoding.EncodeToString([]byte(common.LinuxDoClientId + ":" + common.LinuxDoClientSecret))
-	form := url.Values{
-		"grant_type": {"authorization_code"},
-		"code":       {code},
-	}
-	req, err := http.NewRequest("POST", "https://connect.linux.do/oauth2/token", bytes.NewBufferString(form.Encode()))
-	if err != nil {
-		return nil, err
-	}
-	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
-	req.Header.Set("Authorization", "Basic "+auth)
-	req.Header.Set("Accept", "application/json")
-	client := http.Client{
-		Timeout: 5 * time.Second,
-	}
-	res, err := client.Do(req)
-	if err != nil {
-		common.SysLog(err.Error())
-		return nil, errors.New("无法连接至 LINUX DO 服务器，请稍后重试！")
-	}
-	defer res.Body.Close()
-	var oAuthResponse LinuxDoOAuthResponse
-	err = json.NewDecoder(res.Body).Decode(&oAuthResponse)
-	if err != nil {
-		return nil, err
-	}
-	req, err = http.NewRequest("GET", "https://connect.linux.do/api/user", nil)
-	if err != nil {
-		return nil, err
-	}
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", oAuthResponse.AccessToken))
-	res2, err := client.Do(req)
-	if err != nil {
-		common.SysLog(err.Error())
-		return nil, errors.New("无法连接至 LINUX DO 服务器，请稍后重试！")
-	}
-	defer res2.Body.Close()
-	var linuxdoUser LinuxDoUser
-	err = json.NewDecoder(res2.Body).Decode(&linuxdoUser)
-	if err != nil {
-		return nil, err
-	}
-	if linuxdoUser.ID == 0 {
-		return nil, errors.New("返回值非法，用户字段为空，请稍后重试！")
-	}
-	if linuxdoUser.TrustLevel < common.LinuxDoMinLevel {
-		return nil, errors.New("用户 LINUX DO 信任等级不足！")
-	}
-	return &linuxdoUser, nil
-}
-
-func LinuxDoOAuth(c *gin.Context) {
-	session := sessions.Default(c)
-	state := c.Query("state")
-	if state == "" || session.Get("oauth_state") == nil || state != session.Get("oauth_state").(string) {
-		c.JSON(http.StatusForbidden, gin.H{
-			"success": false,
-			"message": "state is empty or not same",
-		})
-		return
-	}
-	username := session.Get("username")
-	if username != nil {
-		LinuxDoBind(c)
-		return
-	}
-
-	if !common.LinuxDoOAuthEnabled {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": "管理员未开启通过 LINUX DO 登录以及注册",
-		})
-		return
-	}
-	code := c.Query("code")
-	linuxdoUser, err := getLinuxDoUserInfoByCode(code)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	user := model.User{
-		LinuxDoId:    strconv.Itoa(linuxdoUser.ID),
-		LinuxDoLevel: linuxdoUser.TrustLevel,
-	}
-	if model.IsLinuxDoIdAlreadyTaken(user.LinuxDoId) {
-		err := user.FillUserByLinuxDoId()
-		if err != nil {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": err.Error(),
-			})
-			return
-		}
-
-		if user.Id == 0 {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "用户已注销",
-			})
-			return
-		}
-
-		user.LinuxDoLevel = linuxdoUser.TrustLevel
-		err = user.Update(false)
-		if err != nil {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": err.Error(),
-			})
-			return
-		}
-	} else {
-		if common.RegisterEnabled {
-			affCode := c.Query("aff")
-			user.InviterId, _ = model.GetUserIdByAffCode(affCode)
-
-			user.Username = "linuxdo_" + strconv.Itoa(model.GetMaxUserId()+1)
-			if linuxdoUser.Name != "" {
-				user.DisplayName = linuxdoUser.Name
-			} else {
-				user.DisplayName = linuxdoUser.Username
-			}
-			user.Role = common.RoleCommonUser
-			user.Status = common.UserStatusEnabled
-
-			if err := user.Insert(user.InviterId); err != nil {
-				c.JSON(http.StatusOK, gin.H{
-					"success": false,
-					"message": err.Error(),
-				})
-				return
-			}
-		} else {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "管理员关闭了新用户注册",
-			})
-			return
-		}
-	}
-
-	if user.Status != common.UserStatusEnabled {
-		c.JSON(http.StatusOK, gin.H{
-			"message": "用户已被封禁",
-			"success": false,
-		})
-		return
-	}
-	setupLogin(&user, c)
-}
-
-func LinuxDoBind(c *gin.Context) {
-	if !common.LinuxDoOAuthEnabled {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": "管理员未开启通过 LINUX DO 登录以及注册",
-		})
-		return
-	}
-	code := c.Query("code")
-	linuxdoUser, err := getLinuxDoUserInfoByCode(code)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	user := model.User{
-		LinuxDoId:    strconv.Itoa(linuxdoUser.ID),
-		LinuxDoLevel: linuxdoUser.TrustLevel,
-	}
-	if model.IsLinuxDoIdAlreadyTaken(user.LinuxDoId) {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": "该 LINUX DO 账户已被绑定",
-		})
-		return
-	}
-	session := sessions.Default(c)
-	id := session.Get("id")
-	// id := c.GetInt("id")  // critical bug!
-	user.Id = id.(int)
-	err = user.FillUserById()
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	user.LinuxDoId = strconv.Itoa(linuxdoUser.ID)
-	user.LinuxDoLevel = linuxdoUser.TrustLevel
-	err = user.Update(false)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	c.JSON(http.StatusOK, gin.H{
-		"success": true,
-		"message": "bind",
-	})
-	return
-}
--- a/controller/log.go
+++ b/controller/log.go
@@ -192,7 +192,7 @@ func DeleteHistoryLogs(c *gin.Context) {
 		})
 		return
 	}
-	count, err := model.DeleteOldLog(c.Request.Context(), targetTimestamp, 100)
+	count, err := model.DeleteOldLog(targetTimestamp)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
--- a/controller/midjourney.go
+++ b/controller/midjourney.go
@@ -233,7 +233,7 @@ func GetAllMidjourney(c *gin.Context) {
 	}
 	if constant.MjForwardUrlEnabled {
 		for i, midjourney := range logs {
-			midjourney.ImageUrl = common.ServerAddress + "/mj/image/" + midjourney.MjId
+			midjourney.ImageUrl = constant.ServerAddress + "/mj/image/" + midjourney.MjId
 			logs[i] = midjourney
 		}
 	}
@@ -265,7 +265,7 @@ func GetUserMidjourney(c *gin.Context) {
 	}
 	if constant.MjForwardUrlEnabled {
 		for i, midjourney := range logs {
-			midjourney.ImageUrl = common.ServerAddress + "/mj/image/" + midjourney.MjId
+			midjourney.ImageUrl = constant.ServerAddress + "/mj/image/" + midjourney.MjId
 			logs[i] = midjourney
 		}
 	}
--- a/controller/misc.go
+++ b/controller/misc.go
@@ -38,8 +38,6 @@ func GetStatus(c *gin.Context) {
 			"email_verification":       common.EmailVerificationEnabled,
 			"github_oauth":             common.GitHubOAuthEnabled,
 			"github_client_id":         common.GitHubClientId,
-			"linuxdo_oauth":            common.LinuxDoOAuthEnabled,
-			"linuxdo_client_id":        common.LinuxDoClientId,
 			"telegram_oauth":           common.TelegramOAuthEnabled,
 			"telegram_bot_name":        common.TelegramBotName,
 			"system_name":              common.SystemName,
@@ -47,9 +45,9 @@ func GetStatus(c *gin.Context) {
 			"footer_html":              common.Footer,
 			"wechat_qrcode":            common.WeChatAccountQRCodeImageURL,
 			"wechat_login":             common.WeChatAuthEnabled,
-			"server_address":           common.ServerAddress,
-			"stripe_unit_price":        common.StripeUnitPrice,
-			"min_topup":                common.MinTopUp,
+			"server_address":           constant.ServerAddress,
+			"price":                    constant.Price,
+			"min_topup":                constant.MinTopUp,
 			"turnstile_check":          common.TurnstileCheckEnabled,
 			"turnstile_site_key":       common.TurnstileSiteKey,
 			"top_up_link":              common.TopUpLink,
@@ -63,7 +61,7 @@ func GetStatus(c *gin.Context) {
 			"enable_data_export":       common.DataExportEnabled,
 			"data_export_default_time": common.DataExportDefaultTime,
 			"default_collapse_sidebar": common.DefaultCollapseSidebar,
-			"payment_enabled":          common.PaymentEnabled,
+			"enable_online_topup":      constant.PayAddress != "" && constant.EpayId != "" && constant.EpayKey != "",
 			"mj_notify_enabled":        constant.MjNotifyEnabled,
 			"chats":                    constant.Chats,
 		},
@@ -207,7 +205,7 @@ func SendPasswordResetEmail(c *gin.Context) {
 	}
 	code := common.GenerateVerificationCode(0)
 	common.RegisterVerificationCodeWithKey(email, code, common.PasswordResetPurpose)
-	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", common.ServerAddress, email, code)
+	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", constant.ServerAddress, email, code)
 	subject := fmt.Sprintf("%s密码重置", common.SystemName)
 	content := fmt.Sprintf("<p>您好，你正在进行%s密码重置。</p>"+
 		"<p>点击 <a href='%s'>此处</a> 进行密码重置。</p>"+
--- a/controller/option.go
+++ b/controller/option.go
@@ -50,14 +50,6 @@ func UpdateOption(c *gin.Context) {
 			})
 			return
 		}
-	case "LinuxDoOAuthEnabled":
-		if option.Value == "true" && common.LinuxDoClientId == "" {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "无法启用 LINUX DO OAuth，请先填入 LINUX DO Client Id 以及 LINUX DO Client Secret！",
-			})
-			return
-		}
 	case "EmailDomainRestrictionEnabled":
 		if option.Value == "true" && len(common.EmailDomainWhitelist) == 0 {
 			c.JSON(http.StatusOK, gin.H{
--- a/controller/relay.go
+++ b/controller/relay.go
@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"log"
 	"net/http"
@@ -38,6 +39,15 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	return err
 }

+func wsHandler(c *gin.Context, ws *websocket.Conn, relayMode int) *dto.OpenAIErrorWithStatusCode {
+	var err *dto.OpenAIErrorWithStatusCode
+	switch relayMode {
+	default:
+		err = relay.TextHelper(c)
+	}
+	return err
+}
+
 func Playground(c *gin.Context) {
 	var openaiErr *dto.OpenAIErrorWithStatusCode

@@ -134,6 +144,67 @@ func Relay(c *gin.Context) {
 	}
 }

+var upgrader = websocket.Upgrader{
+	Subprotocols: []string{"realtime"}, // WS 握手支持的协议，如果有使用 Sec-WebSocket-Protocol，则必须在此声明对应的 Protocol TODO add other protocol
+	CheckOrigin: func(r *http.Request) bool {
+		return true // 允许跨域
+	},
+}
+
+func WssRelay(c *gin.Context) {
+	// 将 HTTP 连接升级为 WebSocket 连接
+
+	ws, err := upgrader.Upgrade(c.Writer, c.Request, nil)
+	defer ws.Close()
+
+	if err != nil {
+		openaiErr := service.OpenAIErrorWrapper(err, "get_channel_failed", http.StatusInternalServerError)
+		service.WssError(c, ws, openaiErr.Error)
+		return
+	}
+
+	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
+	requestId := c.GetString(common.RequestIdKey)
+	group := c.GetString("group")
+	//wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01
+	originalModel := c.GetString("original_model")
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
+		if err != nil {
+			common.LogError(c, err.Error())
+			openaiErr = service.OpenAIErrorWrapperLocal(err, "get_channel_failed", http.StatusInternalServerError)
+			break
+		}
+
+		openaiErr = wssRequest(c, ws, relayMode, channel)
+
+		if openaiErr == nil {
+			return // 成功处理请求，直接返回
+		}
+
+		go processChannelError(c, channel.Id, channel.Type, channel.Name, channel.GetAutoBan(), openaiErr)
+
+		if !shouldRetry(c, openaiErr, common.RetryTimes-i) {
+			break
+		}
+	}
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c, retryLogStr)
+	}
+
+	if openaiErr != nil {
+		if openaiErr.StatusCode == http.StatusTooManyRequests {
+			openaiErr.Error.Message = "当前分组上游负载已饱和，请稍后再试"
+		}
+		openaiErr.Error.Message = common.MessageWithRequestId(openaiErr.Error.Message, requestId)
+		service.WssError(c, ws, openaiErr.Error)
+	}
+}
+
 func relayRequest(c *gin.Context, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
 	addUsedChannel(c, channel.Id)
 	requestBody, _ := common.GetRequestBody(c)
@@ -141,6 +212,13 @@ func relayRequest(c *gin.Context, relayMode int, channel *model.Channel) *dto.Op
 	return relayHandler(c, relayMode)
 }

+func wssRequest(c *gin.Context, ws *websocket.Conn, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
+	addUsedChannel(c, channel.Id)
+	requestBody, _ := common.GetRequestBody(c)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return relay.WssHelper(c, ws)
+}
+
 func addUsedChannel(c *gin.Context, channelId int) {
 	useChannel := c.GetStringSlice("use_channel")
 	useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
--- a/controller/stripe.go
+++ b/controller/stripe.go
@@ -1,99 +0,0 @@
-package controller
-
-import (
-	"github.com/gin-gonic/gin"
-	"github.com/stripe/stripe-go/v79"
-	"github.com/stripe/stripe-go/v79/webhook"
-	"io"
-	"log"
-	"net/http"
-	"one-api/common"
-	"one-api/model"
-	"strconv"
-	"strings"
-)
-
-func StripeWebhook(c *gin.Context) {
-	payload, err := io.ReadAll(c.Request.Body)
-	if err != nil {
-		log.Printf("解析Stripe Webhook参数失败: %v\n", err)
-		c.AbortWithStatus(http.StatusServiceUnavailable)
-		return
-	}
-
-	signature := c.GetHeader("Stripe-Signature")
-	endpointSecret := common.StripeWebhookSecret
-	event, err := webhook.ConstructEventWithOptions(payload, signature, endpointSecret, webhook.ConstructEventOptions{
-		IgnoreAPIVersionMismatch: true,
-	})
-
-	if err != nil {
-		log.Printf("Stripe Webhook验签失败: %v\n", err)
-		c.AbortWithStatus(http.StatusBadRequest)
-		return
-	}
-
-	switch event.Type {
-	case stripe.EventTypeCheckoutSessionCompleted:
-		sessionCompleted(event)
-	case stripe.EventTypeCheckoutSessionExpired:
-		sessionExpired(event)
-	default:
-		log.Printf("不支持的Stripe Webhook事件类型: %s\n", event.Type)
-	}
-
-	c.Status(http.StatusOK)
-}
-
-func sessionCompleted(event stripe.Event) {
-	customerId := event.GetObjectValue("customer")
-	referenceId := event.GetObjectValue("client_reference_id")
-	status := event.GetObjectValue("status")
-	if "complete" != status {
-		log.Println("错误的Stripe Checkout完成状态:", status, ",", referenceId)
-		return
-	}
-
-	err := model.Recharge(referenceId, customerId)
-	if err != nil {
-		log.Println(err.Error(), referenceId)
-		return
-	}
-
-	total, _ := strconv.ParseFloat(event.GetObjectValue("amount_total"), 64)
-	currency := strings.ToUpper(event.GetObjectValue("currency"))
-	log.Printf("收到款项：%s, %.2f(%s)", referenceId, total/100, currency)
-}
-
-func sessionExpired(event stripe.Event) {
-	referenceId := event.GetObjectValue("client_reference_id")
-	status := event.GetObjectValue("status")
-	if "expired" != status {
-		log.Println("错误的Stripe Checkout过期状态:", status, ",", referenceId)
-		return
-	}
-
-	if "" == referenceId {
-		log.Println("未提供支付单号")
-		return
-	}
-
-	topUp := model.GetTopUpByTradeNo(referenceId)
-	if topUp == nil {
-		log.Println("充值订单不存在", referenceId)
-		return
-	}
-
-	if topUp.Status != common.TopUpStatusPending {
-		log.Println("充值订单状态错误", referenceId)
-	}
-
-	topUp.Status = common.TopUpStatusExpired
-	err := topUp.Update()
-	if err != nil {
-		log.Println("过期充值订单失败", referenceId, ", err:", err.Error())
-		return
-	}
-
-	log.Println("充值订单已过期", referenceId)
-}
--- a/controller/topup.go
+++ b/controller/topup.go
@@ -1,20 +1,22 @@
 package controller

-import "C"
 import (
 	"fmt"
+	"github.com/Calcium-Ion/go-epay/epay"
 	"github.com/gin-gonic/gin"
-	"github.com/stripe/stripe-go/v79"
-	"github.com/stripe/stripe-go/v79/checkout/session"
+	"github.com/samber/lo"
 	"log"
+	"net/url"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/model"
+	"one-api/service"
 	"strconv"
-	"strings"
+	"sync"
 	"time"
 )

-type PayRequest struct {
+type EpayRequest struct {
 	Amount        int    `json:"amount"`
 	PaymentMethod string `json:"payment_method"`
 	TopUpCode     string `json:"top_up_code"`
@@ -25,114 +27,201 @@ type AmountRequest struct {
 	TopUpCode string `json:"top_up_code"`
 }

-func genStripeLink(referenceId string, customerId string, email string, amount int64) (string, error) {
-	if !strings.HasPrefix(common.StripeApiSecret, "sk_") {
-		return "", fmt.Errorf("无效的Stripe API密钥")
+func GetEpayClient() *epay.Client {
+	if constant.PayAddress == "" || constant.EpayId == "" || constant.EpayKey == "" {
+		return nil
 	}
-
-	stripe.Key = common.StripeApiSecret
-
-	params := &stripe.CheckoutSessionParams{
-		ClientReferenceID: stripe.String(referenceId),
-		SuccessURL:        stripe.String(common.ServerAddress + "/log"),
-		CancelURL:         stripe.String(common.ServerAddress + "/topup"),
-		LineItems: []*stripe.CheckoutSessionLineItemParams{
-			{
-				Price:    stripe.String(common.StripePriceId),
-				Quantity: stripe.Int64(amount),
-			},
-		},
-		Mode: stripe.String(string(stripe.CheckoutSessionModePayment)),
-	}
-
-	if "" == customerId {
-		if "" != email {
-			params.CustomerEmail = stripe.String(email)
-		}
-
-		params.CustomerCreation = stripe.String(string(stripe.CheckoutSessionCustomerCreationAlways))
-	} else {
-		params.Customer = stripe.String(customerId)
-	}
-
-	result, err := session.New(params)
+	withUrl, err := epay.NewClient(&epay.Config{
+		PartnerID: constant.EpayId,
+		Key:       constant.EpayKey,
+	}, constant.PayAddress)
 	if err != nil {
-		return "", err
+		return nil
 	}
-
-	return result.URL, nil
+	return withUrl
 }

-func GetPayAmount(count float64) float64 {
-	return count * common.StripeUnitPrice
-}
-
-func GetChargedAmount(count float64, user model.User) float64 {
-	topUpGroupRatio := common.GetTopupGroupRatio(user.Group)
-	if topUpGroupRatio == 0 {
-		topUpGroupRatio = 1
+func getPayMoney(amount float64, group string) float64 {
+	if !common.DisplayInCurrencyEnabled {
+		amount = amount / common.QuotaPerUnit
 	}
-
-	return count * topUpGroupRatio
+	// 别问为什么用float64，问就是这么点钱没必要
+	topupGroupRatio := common.GetTopupGroupRatio(group)
+	if topupGroupRatio == 0 {
+		topupGroupRatio = 1
+	}
+	payMoney := amount * constant.Price * topupGroupRatio
+	return payMoney
 }

-func RequestPayLink(c *gin.Context) {
-	var req PayRequest
+func getMinTopup() int {
+	minTopup := constant.MinTopUp
+	if !common.DisplayInCurrencyEnabled {
+		minTopup = minTopup * int(common.QuotaPerUnit)
+	}
+	return minTopup
+}
+
+func RequestEpay(c *gin.Context) {
+	var req EpayRequest
 	err := c.ShouldBindJSON(&req)
 	if err != nil {
-		c.JSON(200, gin.H{"message": err.Error(), "data": 10})
+		c.JSON(200, gin.H{"message": "error", "data": "参数错误"})
 		return
 	}
-	if !common.PaymentEnabled {
-		c.JSON(200, gin.H{"message": "error", "data": "管理员未开启在线支付"})
-		return
-	}
-	if req.PaymentMethod != "stripe" {
-		c.JSON(200, gin.H{"message": "error", "data": "不支持的支付渠道"})
-		return
-	}
-	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
-	}
-	if req.Amount > 10000 {
-		c.JSON(200, gin.H{"message": "充值数量不能大于 10000", "data": 10})
+	if req.Amount < getMinTopup() {
+		c.JSON(200, gin.H{"message": "error", "data": fmt.Sprintf("充值数量不能小于 %d", getMinTopup())})
 		return
 	}

 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	chargedMoney := GetChargedAmount(float64(req.Amount), *user)
-
-	reference := fmt.Sprintf("new-api-ref-%d-%d-%s", user.Id, time.Now().UnixMilli(), common.RandomString(4))
-	referenceId := "ref_" + common.Sha1(reference)
-
-	payLink, err := genStripeLink(referenceId, user.StripeCustomer, user.Email, int64(req.Amount))
+	group, err := model.CacheGetUserGroup(id)
 	if err != nil {
-		log.Println("获取Stripe Checkout支付链接失败", err)
-		c.JSON(200, gin.H{"message": "error", "data": "拉起支付失败"})
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
+	if payMoney < 0.01 {
+		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
 		return
 	}

+	var payType epay.PurchaseType
+	if req.PaymentMethod == "zfb" {
+		payType = epay.Alipay
+	}
+	if req.PaymentMethod == "wx" {
+		req.PaymentMethod = "wxpay"
+		payType = epay.WechatPay
+	}
+	callBackAddress := service.GetCallbackAddress()
+	returnUrl, _ := url.Parse(constant.ServerAddress + "/log")
+	notifyUrl, _ := url.Parse(callBackAddress + "/api/user/epay/notify")
+	tradeNo := fmt.Sprintf("%s%d", common.GetRandomString(6), time.Now().Unix())
+	tradeNo = fmt.Sprintf("USR%dNO%s", id, tradeNo)
+	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"})
+		return
+	}
+	uri, params, err := client.Purchase(&epay.PurchaseArgs{
+		Type:           payType,
+		ServiceTradeNo: tradeNo,
+		Name:           fmt.Sprintf("TUC%d", req.Amount),
+		Money:          strconv.FormatFloat(payMoney, 'f', 2, 64),
+		Device:         epay.PC,
+		NotifyUrl:      notifyUrl,
+		ReturnUrl:      returnUrl,
+	})
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "拉起支付失败"})
+		return
+	}
+	amount := req.Amount
+	if !common.DisplayInCurrencyEnabled {
+		amount = amount / int(common.QuotaPerUnit)
+	}
 	topUp := &model.TopUp{
 		UserId:     id,
-		Amount:     req.Amount,
-		Money:      chargedMoney,
-		TradeNo:    referenceId,
+		Amount:     amount,
+		Money:      payMoney,
+		TradeNo:    tradeNo,
 		CreateTime: time.Now().Unix(),
-		Status:     common.TopUpStatusPending,
+		Status:     "pending",
 	}
 	err = topUp.Insert()
 	if err != nil {
 		c.JSON(200, gin.H{"message": "error", "data": "创建订单失败"})
 		return
 	}
-	c.JSON(200, gin.H{
-		"message": "success",
-		"data": gin.H{
-			"payLink": payLink,
-		},
-	})
+	c.JSON(200, gin.H{"message": "success", "data": params, "url": uri})
+}
+
+// tradeNo lock
+var orderLocks sync.Map
+var createLock sync.Mutex
+
+// LockOrder 尝试对给定订单号加锁
+func LockOrder(tradeNo string) {
+	lock, ok := orderLocks.Load(tradeNo)
+	if !ok {
+		createLock.Lock()
+		defer createLock.Unlock()
+		lock, ok = orderLocks.Load(tradeNo)
+		if !ok {
+			lock = new(sync.Mutex)
+			orderLocks.Store(tradeNo, lock)
+		}
+	}
+	lock.(*sync.Mutex).Lock()
+}
+
+// UnlockOrder 释放给定订单号的锁
+func UnlockOrder(tradeNo string) {
+	lock, ok := orderLocks.Load(tradeNo)
+	if ok {
+		lock.(*sync.Mutex).Unlock()
+	}
+}
+
+func EpayNotify(c *gin.Context) {
+	params := lo.Reduce(lo.Keys(c.Request.URL.Query()), func(r map[string]string, t string, i int) map[string]string {
+		r[t] = c.Request.URL.Query().Get(t)
+		return r
+	}, map[string]string{})
+	client := GetEpayClient()
+	if client == nil {
+		log.Println("易支付回调失败 未找到配置信息")
+		_, err := c.Writer.Write([]byte("fail"))
+		if err != nil {
+			log.Println("易支付回调写入失败")
+			return
+		}
+	}
+	verifyInfo, err := client.Verify(params)
+	if err == nil && verifyInfo.VerifyStatus {
+		_, err := c.Writer.Write([]byte("success"))
+		if err != nil {
+			log.Println("易支付回调写入失败")
+		}
+	} else {
+		_, err := c.Writer.Write([]byte("fail"))
+		if err != nil {
+			log.Println("易支付回调写入失败")
+		}
+		log.Println("易支付回调签名验证失败")
+		return
+	}
+
+	if verifyInfo.TradeStatus == epay.StatusTradeSuccess {
+		log.Println(verifyInfo)
+		LockOrder(verifyInfo.ServiceTradeNo)
+		defer UnlockOrder(verifyInfo.ServiceTradeNo)
+		topUp := model.GetTopUpByTradeNo(verifyInfo.ServiceTradeNo)
+		if topUp == nil {
+			log.Printf("易支付回调未找到订单: %v", verifyInfo)
+			return
+		}
+		if topUp.Status == "pending" {
+			topUp.Status = "success"
+			err := topUp.Update()
+			if err != nil {
+				log.Printf("易支付回调更新订单失败: %v", topUp)
+				return
+			}
+			//user, _ := model.GetUserById(topUp.UserId, false)
+			//user.Quota += topUp.Amount * 500000
+			err = model.IncreaseUserQuota(topUp.UserId, topUp.Amount*int(common.QuotaPerUnit))
+			if err != nil {
+				log.Printf("易支付回调更新用户失败: %v", topUp)
+				return
+			}
+			log.Printf("易支付回调更新用户成功 %v", topUp)
+			model.RecordLog(topUp.UserId, model.LogTypeTopup, fmt.Sprintf("使用在线充值成功，充值金额: %v，支付金额：%f", common.LogQuota(topUp.Amount*int(common.QuotaPerUnit)), topUp.Money))
+		}
+	} else {
+		log.Printf("易支付异常回调: %v", verifyInfo)
+	}
 }

 func RequestAmount(c *gin.Context) {
@@ -142,23 +231,21 @@ func RequestAmount(c *gin.Context) {
 		c.JSON(200, gin.H{"message": "error", "data": "参数错误"})
 		return
 	}
-	if !common.PaymentEnabled {
-		c.JSON(200, gin.H{"message": "error", "data": "管理员未开启在线支付"})
-		return
-	}
-	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)})
+
+	if req.Amount < getMinTopup() {
+		c.JSON(200, gin.H{"message": "error", "data": fmt.Sprintf("充值数量不能小于 %d", getMinTopup())})
 		return
 	}
 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	payMoney := GetPayAmount(float64(req.Amount))
-	chargedMoney := GetChargedAmount(float64(req.Amount), *user)
-	c.JSON(200, gin.H{
-		"message": "success",
-		"data": gin.H{
-			"payAmount":     strconv.FormatFloat(payMoney, 'f', 2, 64),
-			"chargedAmount": strconv.FormatFloat(chargedMoney, 'f', 2, 64),
-		},
-	})
+	group, err := model.CacheGetUserGroup(id)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
+	if payMoney <= 0.01 {
+		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
+		return
+	}
+	c.JSON(200, gin.H{"message": "success", "data": strconv.FormatFloat(payMoney, 'f', 2, 64)})
 }
--- a/controller/user.go
+++ b/controller/user.go
@@ -69,7 +69,6 @@ func setupLogin(user *model.User, c *gin.Context) {
 	session.Set("role", user.Role)
 	session.Set("status", user.Status)
 	session.Set("group", user.Group)
-	session.Set("linuxdo_enable", user.LinuxDoId == "" || user.LinuxDoLevel >= common.LinuxDoMinLevel)
 	err := session.Save()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
@@ -575,7 +574,7 @@ func UpdateSelf(c *gin.Context) {
 	return
 }

-func HardDeleteUser(c *gin.Context) {
+func DeleteUser(c *gin.Context) {
 	id, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
@@ -584,7 +583,7 @@ func HardDeleteUser(c *gin.Context) {
 		})
 		return
 	}
-	originUser, err := model.GetUserByIdUnscoped(id, false)
+	originUser, err := model.GetUserById(id, false)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -608,23 +607,9 @@ func HardDeleteUser(c *gin.Context) {
 		})
 		return
 	}
-
-	c.JSON(http.StatusOK, gin.H{
-		"success": true,
-		"message": "",
-	})
-	return
 }

 func DeleteSelf(c *gin.Context) {
-	if !common.UserSelfDeletionEnabled {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": "当前设置不允许用户自我删除账号",
-		})
-		return
-	}
-
 	id := c.GetInt("id")
 	user, _ := model.GetUserById(id, false)

--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -2,17 +2,18 @@ version: '3.4'

 services:
  new-api:
-    image: pengzhile/new-api:latest
+    image: calciumion/new-api:latest
+    # build: .
    container_name: new-api
    restart: always
    command: --log-dir /app/logs
    ports:
      - "3000:3000"
    volumes:
-      - ./data/new-api:/data
+      - ./data:/data
      - ./logs:/app/logs
    environment:
-      - SQL_DSN=newapi:123456@tcp(db:3306)/new-api  # 修改此行，或注释掉以使用 SQLite 作为数据库
+      - SQL_DSN=root:123456@tcp(host.docker.internal:3306)/new-api  # 修改此行，或注释掉以使用 SQLite 作为数据库
      - REDIS_CONN_STRING=redis://redis
      - SESSION_SECRET=random_string  # 修改为随机字符串
      - TZ=Asia/Shanghai
@@ -22,22 +23,13 @@ services:

    depends_on:
      - redis
-      - db
+    healthcheck:
+      test: [ "CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $2}'" ]
+      interval: 30s
+      timeout: 10s
+      retries: 3

  redis:
-    image: redis:7.4
+    image: redis:latest
    container_name: redis
    restart: always
-
-  db:
-    image: mysql:8.2
-    container_name: mysql
-    restart: always
-    volumes:
-      - ./data/mysql:/var/lib/mysql  # 挂载目录，持久化存储
-    environment:
-      TZ: Asia/Shanghai   # 设置时区
-      MYSQL_ROOT_PASSWORD: 'OneAPI@justsong' # 设置 root 用户的密码
-      MYSQL_USER: newapi   # 创建专用用户
-      MYSQL_PASSWORD: '123456'    # 设置专用用户密码
-      MYSQL_DATABASE: new-api   # 自动创建数据库
--- a/dto/openai_request.go
+++ b/dto/openai_request.go
@@ -2,16 +2,16 @@ package dto

 import "encoding/json"

+type ResponseFormat struct {
+	Type string `json:"type,omitempty"`
+}
+
 type GeneralOpenAIRequest struct {
 	Model               string         `json:"model,omitempty"`
-	ReasoningEffort     string         `json:"reasoning_effort,omitempty"`
 	Messages            []Message      `json:"messages,omitempty"`
 	Prompt              any            `json:"prompt,omitempty"`
-	BestOf              int            `json:"best_of,omitempty"`
-	Echo                bool           `json:"echo,omitempty"`
 	Stream              bool           `json:"stream,omitempty"`
 	StreamOptions       *StreamOptions `json:"stream_options,omitempty"`
-	Suffix              string         `json:"suffix,omitempty"`
 	MaxTokens           uint           `json:"max_tokens,omitempty"`
 	MaxCompletionTokens uint           `json:"max_completion_tokens,omitempty"`
 	Temperature         float64        `json:"temperature,omitempty"`
@@ -26,23 +26,16 @@ type GeneralOpenAIRequest struct {
 	FrequencyPenalty    float64        `json:"frequency_penalty,omitempty"`
 	PresencePenalty     float64        `json:"presence_penalty,omitempty"`
 	ResponseFormat      any            `json:"response_format,omitempty"`
+	EncodingFormat      any            `json:"encoding_format,omitempty"`
 	Seed                float64        `json:"seed,omitempty"`
 	Tools               []ToolCall     `json:"tools,omitempty"`
 	ToolChoice          any            `json:"tool_choice,omitempty"`
 	User                string         `json:"user,omitempty"`
-	LogitBias           any            `json:"logit_bias,omitempty"`
-	LogProbs            any            `json:"logprobs,omitempty"`
+	LogProbs            bool           `json:"logprobs,omitempty"`
 	TopLogProbs         int            `json:"top_logprobs,omitempty"`
 	Dimensions          int            `json:"dimensions,omitempty"`
-	ParallelToolCalls   bool           `json:"parallel_tool_calls,omitempty"`
-	EncodingFormat      any            `json:"encoding_format,omitempty"`
-
-	Thinking *Thinking `json:"thinking,omitempty"`
-}
-
-type Thinking struct {
-	Type         string `json:"type"`
-	BudgetTokens int    `json:"budget_tokens"`
+	Modalities          any            `json:"modalities,omitempty"`
+	Audio               any            `json:"audio,omitempty"`
 }

 type OpenAITools struct {
@@ -84,18 +77,18 @@ func (r GeneralOpenAIRequest) ParseInput() []string {
 }

 type Message struct {
-	Role             string          `json:"role"`
-	Content          json.RawMessage `json:"content"`
-	ReasoningContent *string         `json:"reasoning_content,omitempty"`
-	Name             *string         `json:"name,omitempty"`
-	ToolCalls        any             `json:"tool_calls,omitempty"`
-	ToolCallId       string          `json:"tool_call_id,omitempty"`
+	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       string `json:"type"`
+	Text       string `json:"text"`
+	ImageUrl   any    `json:"image_url,omitempty"`
+	InputAudio any    `json:"input_audio,omitempty"`
 }

 type MessageImageUrl struct {
@@ -103,9 +96,15 @@ type MessageImageUrl struct {
 	Detail string `json:"detail"`
 }

+type MessageInputAudio struct {
+	Data   string `json:"data"` //base64
+	Format string `json:"format"`
+}
+
 const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeText       = "text"
+	ContentTypeImageURL   = "image_url"
+	ContentTypeInputAudio = "input_audio"
 )

 func (m Message) StringContent() string {
@@ -178,11 +177,19 @@ func (m Message) ParseContent() []MediaMessage {
 						},
 					})
 				}
-
+			case ContentTypeInputAudio:
+				if subObj, ok := contentMap["input_audio"].(map[string]any); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeInputAudio,
+						InputAudio: MessageInputAudio{
+							Data:   subObj["data"].(string),
+							Format: subObj["format"].(string),
+						},
+					})
+				}
 			}
 		}
 		return contentList
 	}
-
 	return nil
 }
--- a/dto/openai_response.go
+++ b/dto/openai_response.go
@@ -42,9 +42,9 @@ type OpenAITextResponse struct {
 }

 type OpenAIEmbeddingResponseItem struct {
-	Object    string `json:"object"`
-	Index     int    `json:"index"`
-	Embedding any    `json:"embedding"`
+	Object    string    `json:"object"`
+	Index     int       `json:"index"`
+	Embedding []float64 `json:"embedding"`
 }

 type OpenAIEmbeddingResponse struct {
@@ -62,10 +62,9 @@ type ChatCompletionsStreamResponseChoice struct {
 }

 type ChatCompletionsStreamResponseChoiceDelta struct {
-	Content          *string    `json:"content,omitempty"`
-	ReasoningContent *string    `json:"reasoning_content,omitempty"`
-	Role             string     `json:"role,omitempty"`
-	ToolCalls        []ToolCall `json:"tool_calls,omitempty"`
+	Content   *string    `json:"content,omitempty"`
+	Role      string     `json:"role,omitempty"`
+	ToolCalls []ToolCall `json:"tool_calls,omitempty"`
 }

 func (c *ChatCompletionsStreamResponseChoiceDelta) SetContentString(s string) {
@@ -129,7 +128,9 @@ type CompletionsStreamResponse struct {
 }

 type Usage struct {
-	PromptTokens     int `json:"prompt_tokens"`
-	CompletionTokens int `json:"completion_tokens"`
-	TotalTokens      int `json:"total_tokens"`
+	PromptTokens           int                `json:"prompt_tokens"`
+	CompletionTokens       int                `json:"completion_tokens"`
+	TotalTokens            int                `json:"total_tokens"`
+	PromptTokensDetails    InputTokenDetails  `json:"prompt_tokens_details"`
+	CompletionTokenDetails OutputTokenDetails `json:"completion_tokens_details"`
 }
--- a/dto/realtime.go
+++ b/dto/realtime.go
@@ -0,0 +1,98 @@
+package dto
+
+const (
+	RealtimeEventTypeError              = "error"
+	RealtimeEventTypeSessionUpdate      = "session.update"
+	RealtimeEventTypeConversationCreate = "conversation.item.create"
+	RealtimeEventTypeResponseCreate     = "response.create"
+	RealtimeEventInputAudioBufferAppend = "input_audio_buffer.append"
+)
+
+const (
+	RealtimeEventTypeResponseDone                   = "response.done"
+	RealtimeEventTypeSessionUpdated                 = "session.updated"
+	RealtimeEventTypeSessionCreated                 = "session.created"
+	RealtimeEventResponseAudioDelta                 = "response.audio.delta"
+	RealtimeEventResponseAudioTranscriptionDelta    = "response.audio_transcript.delta"
+	RealtimeEventResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"
+	RealtimeEventResponseFunctionCallArgumentsDone  = "response.function_call_arguments.done"
+	RealtimeEventConversationItemCreated            = "conversation.item.created"
+)
+
+type RealtimeEvent struct {
+	EventId string `json:"event_id"`
+	Type    string `json:"type"`
+	//PreviousItemId string `json:"previous_item_id"`
+	Session  *RealtimeSession  `json:"session,omitempty"`
+	Item     *RealtimeItem     `json:"item,omitempty"`
+	Error    *OpenAIError      `json:"error,omitempty"`
+	Response *RealtimeResponse `json:"response,omitempty"`
+	Delta    string            `json:"delta,omitempty"`
+	Audio    string            `json:"audio,omitempty"`
+}
+
+type RealtimeResponse struct {
+	Usage *RealtimeUsage `json:"usage"`
+}
+
+type RealtimeUsage struct {
+	TotalTokens        int                `json:"total_tokens"`
+	InputTokens        int                `json:"input_tokens"`
+	OutputTokens       int                `json:"output_tokens"`
+	InputTokenDetails  InputTokenDetails  `json:"input_token_details"`
+	OutputTokenDetails OutputTokenDetails `json:"output_token_details"`
+}
+
+type InputTokenDetails struct {
+	CachedTokens int `json:"cached_tokens"`
+	TextTokens   int `json:"text_tokens"`
+	AudioTokens  int `json:"audio_tokens"`
+	ImageTokens  int `json:"image_tokens"`
+}
+
+type OutputTokenDetails struct {
+	TextTokens  int `json:"text_tokens"`
+	AudioTokens int `json:"audio_tokens"`
+}
+
+type RealtimeSession struct {
+	Modalities              []string                `json:"modalities"`
+	Instructions            string                  `json:"instructions"`
+	Voice                   string                  `json:"voice"`
+	InputAudioFormat        string                  `json:"input_audio_format"`
+	OutputAudioFormat       string                  `json:"output_audio_format"`
+	InputAudioTranscription InputAudioTranscription `json:"input_audio_transcription"`
+	TurnDetection           interface{}             `json:"turn_detection"`
+	Tools                   []RealTimeTool          `json:"tools"`
+	ToolChoice              string                  `json:"tool_choice"`
+	Temperature             float64                 `json:"temperature"`
+	//MaxResponseOutputTokens int                     `json:"max_response_output_tokens"`
+}
+
+type InputAudioTranscription struct {
+	Model string `json:"model"`
+}
+
+type RealTimeTool struct {
+	Type        string `json:"type"`
+	Name        string `json:"name"`
+	Description string `json:"description"`
+	Parameters  any    `json:"parameters"`
+}
+
+type RealtimeItem struct {
+	Id        string            `json:"id"`
+	Type      string            `json:"type"`
+	Status    string            `json:"status"`
+	Role      string            `json:"role"`
+	Content   []RealtimeContent `json:"content"`
+	Name      *string           `json:"name,omitempty"`
+	ToolCalls any               `json:"tool_calls,omitempty"`
+	CallId    string            `json:"call_id,omitempty"`
+}
+type RealtimeContent struct {
+	Type       string `json:"type"`
+	Text       string `json:"text,omitempty"`
+	Audio      string `json:"audio,omitempty"` // Base64-encoded audio bytes.
+	Transcript string `json:"transcript,omitempty"`
+}
--- a/go.mod
+++ b/go.mod
@@ -3,13 +3,16 @@ module one-api
 // +heroku goVersion go1.18
 go 1.21

+toolchain go1.22.4
+
 require (
+	github.com/Calcium-Ion/go-epay v0.0.2
 	github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0
 	github.com/aws/aws-sdk-go-v2 v1.26.1
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
 	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
-	github.com/gin-contrib/cors v1.6.0
+	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
 	github.com/gin-contrib/static v0.0.1
@@ -24,10 +27,8 @@ require (
 	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
-	github.com/stripe/stripe-go/v79 v79.12.0
-	golang.org/x/crypto v0.31.0
-	golang.org/x/image v0.18.0
-	golang.org/x/net v0.33.0
+	golang.org/x/crypto v0.26.0
+	golang.org/x/image v0.15.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
 	gorm.io/driver/sqlite v1.4.3
@@ -40,10 +41,9 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
-	github.com/bytedance/sonic v1.11.2 // indirect
+	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d // indirect
-	github.com/chenzhuoyu/iasm v0.9.1 // indirect
+	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
@@ -64,24 +64,26 @@ require (
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/cpuid/v2 v2.2.7 // indirect
+	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-sqlite3 v2.0.3+incompatible // indirect
+	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
-	github.com/pelletier/go-toml/v2 v2.1.1 // indirect
+	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
 	github.com/stretchr/testify v1.9.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
-	github.com/ugorji/go/codec v1.2.12 // indirect
+	github.com/ugorji/go/codec v1.2.11 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
-	golang.org/x/arch v0.7.0 // indirect
+	golang.org/x/arch v0.3.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/sync v0.10.0 // indirect
-	golang.org/x/sys v0.28.0 // indirect
-	golang.org/x/text v0.21.0 // indirect
+	golang.org/x/net v0.28.0 // indirect
+	golang.org/x/sync v0.8.0 // indirect
+	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/text v0.17.0 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
--- a/go.sum
+++ b/go.sum
@@ -1,3 +1,5 @@
+github.com/Calcium-Ion/go-epay v0.0.2 h1:3knFBuaBFpHzsGeGQU/QxUqZSHh5s0+jGo0P62pJzWc=
+github.com/Calcium-Ion/go-epay v0.0.2/go.mod h1:cxo/ZOg8ClvE3VAnCmEzbuyAZINSq7kFEN9oHj5WQ2U=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0 h1:onfun1RA+KcxaMk1lfrRnwCd1UUuOjJM/lri5eM1qMs=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0/go.mod h1:4yg+jNTYlDEzBjhGS96v+zjyA3lfXlFd5CiTLIkPBLI=
 github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6 h1:HblK3eJHq54yET63qPCTJnks3loDse5xRmmqHgHzwoI=
@@ -19,18 +21,13 @@ github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC
 github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b h1:LTGVFpNmNHhj0vhOlfgWueFJ32eK9blaIlHR2ciXOT0=
 github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaUH4+NXIBF0aMdKKAnHTzqH+iMU4KUjAbL23Q=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
-github.com/bytedance/sonic v1.10.0-rc/go.mod h1:ElCzW+ufi8qKqNW0FY314xriJhyJhuoJ3gFZdAHF7NM=
-github.com/bytedance/sonic v1.11.2 h1:ywfwo0a/3j9HR8wsYGWsIWl2mvRsI950HyoxiBERw5A=
-github.com/bytedance/sonic v1.11.2/go.mod h1:iZcSUejdk5aukTND/Eu/ivjQuEL0Cu9/rf50Hi0u/g4=
+github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
+github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
+github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
-github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d h1:77cEq6EriyTZ0g/qfRdp61a3Uu/AWrgIq2s0ClJV1g0=
-github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d/go.mod h1:8EPpVsBuRksnlj1mLy4AWzRNQYxauNi62uWcE3to6eA=
-github.com/chenzhuoyu/iasm v0.9.0/go.mod h1:Xjy2NpN3h7aUqeqM+woSuuvxmIe6+DDsiNLIrkAmYog=
-github.com/chenzhuoyu/iasm v0.9.1 h1:tUHQJXo3NhBqw6s33wkGn9SP3bvrWLdlVIJ3hQBL7P0=
-github.com/chenzhuoyu/iasm v0.9.1/go.mod h1:Xjy2NpN3h7aUqeqM+woSuuvxmIe6+DDsiNLIrkAmYog=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -43,8 +40,8 @@ github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWo
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
-github.com/gin-contrib/cors v1.6.0 h1:0Z7D/bVhE6ja07lI8CTjTonp6SB07o8bNuFyRbsBUQg=
-github.com/gin-contrib/cors v1.6.0/go.mod h1:cI+h6iOAyxKRtUtC6iF/Si1KSFvGm/gK+kshxlCi8ro=
+github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
+github.com/gin-contrib/cors v1.4.0/go.mod h1:bs9pNM0x/UsmHPBWT2xZz9ROh8xYjYkiURUfmBoMlcs=
 github.com/gin-contrib/gzip v0.0.6 h1:NjcunTcGAj5CO1gn4N8jHOSIeRFHIbn51z6K+xaN4d4=
 github.com/gin-contrib/gzip v0.0.6/go.mod h1:QOJlmV2xmayAjkNS2Y8NQsMneuRShOU/kjovCXNuzzk=
 github.com/gin-contrib/sessions v0.0.5 h1:CATtfHmLMQrMNpJRgzjWXD7worTh7g7ritsQfmF+0jE=
@@ -118,9 +115,8 @@ github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/u
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
-github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM=
-github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
-github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
+github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
+github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
@@ -140,6 +136,8 @@ github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D
 github.com/mattn/go-sqlite3 v1.14.15/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
 github.com/mattn/go-sqlite3 v2.0.3+incompatible h1:gXHsfypPkaMZrKbD5209QV9jbUTJKjyR5WD3HYQSd+U=
 github.com/mattn/go-sqlite3 v2.0.3+incompatible/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
+github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
+github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -153,8 +151,8 @@ github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
 github.com/onsi/gomega v1.18.1/go.mod h1:0q+aL8jAiMXy9hbwj2mr5GziHiwhAIQpFmmtT5hitRs=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
-github.com/pelletier/go-toml/v2 v2.1.1 h1:LWAJwfNvjQZCFIDKWYQaM62NcYeYViCmWIwmOStowAI=
-github.com/pelletier/go-toml/v2 v2.1.1/go.mod h1:tJU2Z3ZkXwnxa4DPO899bsyIoywizdUvyaeZurnPPDc=
+github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
+github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
@@ -179,11 +177,9 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
-github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
-github.com/stripe/stripe-go/v79 v79.12.0 h1:HQs/kxNEB3gYA7FnkSFkp0kSOeez0fsmCWev6SxftYs=
-github.com/stripe/stripe-go/v79 v79.12.0/go.mod h1:cuH6X0zC8peY6f1AubHwgJ/fJSn2dh5pfiCr6CjyKVU=
 github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
 github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
 github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
@@ -194,47 +190,45 @@ github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVM
 github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
 github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
 github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
-github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
-github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
+github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
 github.com/yusufpapurcu/wmi v1.2.3 h1:E1ctvB7uKFMOJw3fdOW32DwGE9I7t++CRUEMKvFoFiw=
 github.com/yusufpapurcu/wmi v1.2.3/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
-golang.org/x/arch v0.7.0 h1:pskyeJh/3AmoQ8CPE95vxHLqp1G1GfGNXTmcl9NEKTc=
-golang.org/x/arch v0.7.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
+golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
+golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
-golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
+golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
+golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
-golang.org/x/image v0.18.0 h1:jGzIakQa/ZXI1I0Fxvaa9W7yP25TqT6cHIHn+6CqvSQ=
-golang.org/x/image v0.18.0/go.mod h1:4yyo5vMFQjVjUcVk4jEQcU9MGy/rulF5WvUILseCM2E=
+golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
+golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.0.0-20210520170846-37e1c6afe023/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
-golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
+golang.org/x/net v0.28.0 h1:a9JDOJc5GMUJ0+UDqmLT86WiEy7iWyIhz8gz8E4e5hE=
+golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
-golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220110181412-a018aaa089fe/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
-golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
+golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
-golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
+golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
@@ -266,5 +260,4 @@ gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
 gorm.io/gorm v1.24.0/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
 gorm.io/gorm v1.25.0 h1:+KtYtb2roDz14EQe4bla8CbQlmb9dN3VejSai3lprfU=
 gorm.io/gorm v1.25.0/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=
-nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=
--- a/2
+++ b/2
@@ -7,7 +7,7 @@ all: build-frontend start-backend

 build-frontend:
 	@echo "Building frontend..."
-	@cd $(FRONTEND_DIR) && yarn install --network-timeout 1000000 && DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) yarn build
+	@cd $(FRONTEND_DIR) && npm install && DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) npm run build

 start-backend:
 	@echo "Starting backend dev server..."
--- a/middleware/auth.go
+++ b/middleware/auth.go
@@ -27,7 +27,6 @@ func authHelper(c *gin.Context, minRole int) {
 	role := session.Get("role")
 	id := session.Get("id")
 	status := session.Get("status")
-	linuxDoEnable := session.Get("linuxdo_enable")
 	useAccessToken := false
 	if username == nil {
 		// Check access token
@@ -55,7 +54,6 @@ func authHelper(c *gin.Context, minRole int) {
 			role = user.Role
 			id = user.Id
 			status = user.Status
-			linuxDoEnable = user.LinuxDoId == "" || user.LinuxDoLevel >= common.LinuxDoMinLevel
 			useAccessToken = true
 		} else {
 			c.JSON(http.StatusOK, gin.H{
@@ -104,14 +102,6 @@ func authHelper(c *gin.Context, minRole int) {
 		c.Abort()
 		return
 	}
-	if nil != linuxDoEnable && !linuxDoEnable.(bool) {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": "用户 LINUX DO 信任等级不足",
-		})
-		c.Abort()
-		return
-	}
 	if role.(int) < minRole {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -165,8 +155,27 @@ func RootAuth() func(c *gin.Context) {
 	}
 }

+func WssAuth(c *gin.Context) {
+
+}
+
 func TokenAuth() func(c *gin.Context) {
 	return func(c *gin.Context) {
+		// 先检测是否为ws
+		if c.Request.Header.Get("Sec-WebSocket-Protocol") != "" {
+			// Sec-WebSocket-Protocol: realtime, openai-insecure-api-key.sk-xxx, openai-beta.realtime-v1
+			// read sk from Sec-WebSocket-Protocol
+			key := c.Request.Header.Get("Sec-WebSocket-Protocol")
+			parts := strings.Split(key, ",")
+			for _, part := range parts {
+				part = strings.TrimSpace(part)
+				if strings.HasPrefix(part, "openai-insecure-api-key") {
+					key = strings.TrimPrefix(part, "openai-insecure-api-key.")
+					break
+				}
+			}
+			c.Request.Header.Set("Authorization", "Bearer "+key)
+		}
 		key := c.Request.Header.Get("Authorization")
 		parts := make([]string, 0)
 		key = strings.TrimPrefix(key, "Bearer ")
@@ -201,15 +210,6 @@ func TokenAuth() func(c *gin.Context) {
 			abortWithOpenAiMessage(c, http.StatusForbidden, "用户已被封禁")
 			return
 		}
-		linuxDoEnabled, err := model.CacheIsLinuxDoEnabled(token.UserId)
-		if err != nil {
-			abortWithOpenAiMessage(c, http.StatusInternalServerError, err.Error())
-			return
-		}
-		if !linuxDoEnabled {
-			abortWithOpenAiMessage(c, http.StatusForbidden, "用户 LINUX DO 信任等级不足")
-			return
-		}
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
 		c.Set("token_name", token.Name)
--- a/middleware/distributor.go
+++ b/middleware/distributor.go
@@ -170,6 +170,10 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
 		return nil, false, errors.New("无效的请求, " + err.Error())
 	}
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/realtime") {
+		//wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01
+		modelRequest.Model = c.Query("model")
+	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
 		if modelRequest.Model == "" {
 			modelRequest.Model = "text-moderation-stable"
--- a/model/cache.go
+++ b/model/cache.go
@@ -205,30 +205,6 @@ func CacheIsUserEnabled(userId int) (bool, error) {
 	return userEnabled, err
 }

-func CacheIsLinuxDoEnabled(userId int) (bool, error) {
-	if !common.RedisEnabled {
-		return IsLinuxDoEnabled(userId)
-	}
-	enabled, err := common.RedisGet(fmt.Sprintf("linuxdo_enabled:%d", userId))
-	if err == nil {
-		return enabled == "1", nil
-	}
-
-	linuxDoEnabled, err := IsLinuxDoEnabled(userId)
-	if err != nil {
-		return false, err
-	}
-	enabled = "0"
-	if linuxDoEnabled {
-		enabled = "1"
-	}
-	err = common.RedisSet(fmt.Sprintf("linuxdo_enabled:%d", userId), enabled, time.Duration(UserId2StatusCacheSeconds)*time.Second)
-	if err != nil {
-		common.SysError("Redis set linuxdo enabled error: " + err.Error())
-	}
-	return linuxDoEnabled, err
-}
-
 var group2model2channels map[string]map[string][]*Channel
 var channelsIDM map[int]*Channel
 var channelSyncLock sync.RWMutex
@@ -293,8 +269,9 @@ func SyncChannelCache(frequency int) {
 func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Channel, error) {
 	if strings.HasPrefix(model, "gpt-4-gizmo") {
 		model = "gpt-4-gizmo-*"
-	} else if strings.HasPrefix(model, "g-") {
-		model = "g-*"
+	}
+	if strings.HasPrefix(model, "gpt-4o-gizmo") {
+		model = "gpt-4o-gizmo-*"
 	}

 	// if memory cache is disabled, get channel directly from database
--- a/model/log.go
+++ b/model/log.go
@@ -247,25 +247,7 @@ func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	return token
 }

-func DeleteOldLog(ctx context.Context, targetTimestamp int64, limit int) (int64, error) {
-	var total int64 = 0
-
-	for {
-		if nil != ctx.Err() {
-			return total, ctx.Err()
-		}
-
-		result := LOG_DB.Where("created_at < ?", targetTimestamp).Limit(limit).Delete(&Log{})
-		if nil != result.Error {
-			return total, result.Error
-		}
-
-		total += result.RowsAffected
-
-		if result.RowsAffected < int64(limit) {
-			break
-		}
-	}
-
-	return total, nil
+func DeleteOldLog(targetTimestamp int64) (int64, error) {
+	result := LOG_DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
+	return result.RowsAffected, result.Error
 }
--- a/model/option.go
+++ b/model/option.go
@@ -31,12 +31,10 @@ 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["LinuxDoOAuthEnabled"] = strconv.FormatBool(common.LinuxDoOAuthEnabled)
 	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["UserSelfDeletionEnabled"] = strconv.FormatBool(common.UserSelfDeletionEnabled)
 	common.OptionMap["AutomaticDisableChannelEnabled"] = strconv.FormatBool(common.AutomaticDisableChannelEnabled)
 	common.OptionMap["AutomaticEnableChannelEnabled"] = strconv.FormatBool(common.AutomaticEnableChannelEnabled)
 	common.OptionMap["LogConsumeEnabled"] = strconv.FormatBool(common.LogConsumeEnabled)
@@ -62,20 +60,18 @@ func InitOptionMap() {
 	common.OptionMap["SystemName"] = common.SystemName
 	common.OptionMap["Logo"] = common.Logo
 	common.OptionMap["ServerAddress"] = ""
-	common.OptionMap["OutProxyUrl"] = ""
-	common.OptionMap["StripeApiSecret"] = common.StripeApiSecret
-	common.OptionMap["StripeWebhookSecret"] = common.StripeWebhookSecret
-	common.OptionMap["StripePriceId"] = common.StripePriceId
-	common.OptionMap["PaymentEnabled"] = strconv.FormatBool(common.PaymentEnabled)
-	common.OptionMap["StripeUnitPrice"] = strconv.FormatFloat(common.StripeUnitPrice, 'f', -1, 64)
-	common.OptionMap["MinTopUp"] = strconv.Itoa(common.MinTopUp)
+	common.OptionMap["WorkerUrl"] = constant.WorkerUrl
+	common.OptionMap["WorkerValidKey"] = constant.WorkerValidKey
+	common.OptionMap["PayAddress"] = ""
+	common.OptionMap["CustomCallbackAddress"] = ""
+	common.OptionMap["EpayId"] = ""
+	common.OptionMap["EpayKey"] = ""
+	common.OptionMap["Price"] = strconv.FormatFloat(constant.Price, 'f', -1, 64)
+	common.OptionMap["MinTopUp"] = strconv.Itoa(constant.MinTopUp)
 	common.OptionMap["TopupGroupRatio"] = common.TopupGroupRatio2JSONString()
 	common.OptionMap["Chats"] = constant.Chats2JsonString()
 	common.OptionMap["GitHubClientId"] = ""
 	common.OptionMap["GitHubClientSecret"] = ""
-	common.OptionMap["LinuxDoClientId"] = ""
-	common.OptionMap["LinuxDoClientSecret"] = ""
-	common.OptionMap["LinuxDoMinLevel"] = strconv.Itoa(common.LinuxDoMinLevel)
 	common.OptionMap["TelegramBotToken"] = ""
 	common.OptionMap["TelegramBotName"] = ""
 	common.OptionMap["WeChatServerAddress"] = ""
@@ -179,8 +175,6 @@ func updateOptionMap(key string, value string) (err error) {
 			common.EmailVerificationEnabled = boolValue
 		case "GitHubOAuthEnabled":
 			common.GitHubOAuthEnabled = boolValue
-		case "LinuxDoOAuthEnabled":
-			common.LinuxDoOAuthEnabled = boolValue
 		case "WeChatAuthEnabled":
 			common.WeChatAuthEnabled = boolValue
 		case "TelegramOAuthEnabled":
@@ -189,8 +183,6 @@ func updateOptionMap(key string, value string) (err error) {
 			common.TurnstileCheckEnabled = boolValue
 		case "RegisterEnabled":
 			common.RegisterEnabled = boolValue
-		case "UserSelfDeletionEnabled":
-			common.UserSelfDeletionEnabled = boolValue
 		case "EmailDomainRestrictionEnabled":
 			common.EmailDomainRestrictionEnabled = boolValue
 		case "EmailAliasRestrictionEnabled":
@@ -250,35 +242,31 @@ func updateOptionMap(key string, value string) (err error) {
 	case "SMTPToken":
 		common.SMTPToken = value
 	case "ServerAddress":
-		common.ServerAddress = value
-	case "OutProxyUrl":
-		common.OutProxyUrl = value
+		constant.ServerAddress = value
+	case "WorkerUrl":
+		constant.WorkerUrl = value
+	case "WorkerValidKey":
+		constant.WorkerValidKey = value
+	case "PayAddress":
+		constant.PayAddress = value
 	case "Chats":
 		err = constant.UpdateChatsByJsonString(value)
-	case "StripeApiSecret":
-		common.StripeApiSecret = value
-	case "StripeWebhookSecret":
-		common.StripeWebhookSecret = value
-	case "StripePriceId":
-		common.StripePriceId = value
-	case "PaymentEnabled":
-		common.PaymentEnabled, _ = strconv.ParseBool(value)
-	case "StripeUnitPrice":
-		common.StripeUnitPrice, _ = strconv.ParseFloat(value, 64)
+	case "CustomCallbackAddress":
+		constant.CustomCallbackAddress = value
+	case "EpayId":
+		constant.EpayId = value
+	case "EpayKey":
+		constant.EpayKey = value
+	case "Price":
+		constant.Price, _ = strconv.ParseFloat(value, 64)
 	case "MinTopUp":
-		common.MinTopUp, _ = strconv.Atoi(value)
+		constant.MinTopUp, _ = strconv.Atoi(value)
 	case "TopupGroupRatio":
 		err = common.UpdateTopupGroupRatioByJSONString(value)
 	case "GitHubClientId":
 		common.GitHubClientId = value
 	case "GitHubClientSecret":
 		common.GitHubClientSecret = value
-	case "LinuxDoClientId":
-		common.LinuxDoClientId = value
-	case "LinuxDoClientSecret":
-		common.LinuxDoClientSecret = value
-	case "LinuxDoMinLevel":
-		common.LinuxDoMinLevel, _ = strconv.Atoi(value)
 	case "Footer":
 		common.Footer = value
 	case "SystemName":
--- a/model/token.go
+++ b/model/token.go
@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"gorm.io/gorm"
 	"one-api/common"
+	"one-api/constant"
 	relaycommon "one-api/relay/common"
 	"strconv"
 	"strings"
@@ -324,7 +325,7 @@ func PostConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, userQuota int, quot
 						prompt = "您的额度已用尽"
 					}
 					if email != "" {
-						topUpLink := fmt.Sprintf("%s/topup", common.ServerAddress)
+						topUpLink := fmt.Sprintf("%s/topup", constant.ServerAddress)
 						err = common.SendEmail(prompt, email,
 							fmt.Sprintf("%s，当前剩余额度为 %d，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='%s'>%s</a>", prompt, userQuota, topUpLink, topUpLink))
 						if err != nil {
--- a/model/topup.go
+++ b/model/topup.go
@@ -1,21 +1,13 @@
 package model

-import (
-	"errors"
-	"fmt"
-	"gorm.io/gorm"
-	"one-api/common"
-)
-
 type TopUp struct {
-	Id           int     `json:"id"`
-	UserId       int     `json:"user_id" gorm:"index"`
-	Amount       int     `json:"amount"`
-	Money        float64 `json:"money"`
-	TradeNo      string  `json:"trade_no" gorm:"unique"`
-	CreateTime   int64   `json:"create_time"`
-	CompleteTime int64   `json:"complete_time"`
-	Status       string  `json:"status"`
+	Id         int     `json:"id"`
+	UserId     int     `json:"user_id" gorm:"index"`
+	Amount     int     `json:"amount"`
+	Money      float64 `json:"money"`
+	TradeNo    string  `json:"trade_no"`
+	CreateTime int64   `json:"create_time"`
+	Status     string  `json:"status"`
 }

 func (topUp *TopUp) Insert() error {
@@ -49,51 +41,3 @@ func GetTopUpByTradeNo(tradeNo string) *TopUp {
 	}
 	return topUp
 }
-
-func Recharge(referenceId string, customerId string) (err error) {
-	if referenceId == "" {
-		return errors.New("未提供支付单号")
-	}
-
-	var quota float64
-	topUp := &TopUp{}
-
-	refCol := "`trade_no`"
-	if common.UsingPostgreSQL {
-		refCol = `"trade_no"`
-	}
-
-	err = DB.Transaction(func(tx *gorm.DB) error {
-		err := tx.Set("gorm:query_option", "FOR UPDATE").Where(refCol+" = ?", referenceId).First(topUp).Error
-		if err != nil {
-			return errors.New("充值订单不存在")
-		}
-
-		if topUp.Status != common.TopUpStatusPending {
-			return errors.New("充值订单状态错误")
-		}
-
-		topUp.CompleteTime = common.GetTimestamp()
-		topUp.Status = common.TopUpStatusSuccess
-		err = tx.Save(topUp).Error
-		if err != nil {
-			return err
-		}
-
-		quota = topUp.Money * common.QuotaPerUnit
-		err = tx.Model(&User{}).Where("id = ?", topUp.UserId).Updates(map[string]interface{}{"stripe_customer": customerId, "quota": gorm.Expr("quota + ?", quota)}).Error
-		if err != nil {
-			return err
-		}
-
-		return nil
-	})
-
-	if err != nil {
-		return errors.New("充值失败，" + err.Error())
-	}
-
-	RecordLog(topUp.UserId, LogTypeTopup, fmt.Sprintf("使用在线充值成功，充值金额: %v，支付金额：%d", common.LogQuotaF(quota), topUp.Amount))
-
-	return nil
-}
--- a/model/user.go
+++ b/model/user.go
@@ -22,8 +22,6 @@ type User struct {
 	Status           int            `json:"status" gorm:"type:int;default:1"` // enabled, disabled
 	Email            string         `json:"email" gorm:"index" validate:"max=50"`
 	GitHubId         string         `json:"github_id" gorm:"column:github_id;index"`
-	LinuxDoId        string         `json:"linuxdo_id" gorm:"column:linuxdo_id;index"`
-	LinuxDoLevel     int            `json:"linuxdo_level" gorm:"column:linuxdo_level;type:int;default:0"`
 	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!
@@ -37,7 +35,6 @@ type User struct {
 	AffQuota         int            `json:"aff_quota" gorm:"type:int;default:0;column:aff_quota"`           // 邀请剩余额度
 	AffHistoryQuota  int            `json:"aff_history_quota" gorm:"type:int;default:0;column:aff_history"` // 邀请历史额度
 	InviterId        int            `json:"inviter_id" gorm:"type:int;column:inviter_id;index"`
-	StripeCustomer   string         `json:"stripe_customer" gorm:"column:stripe_customer;index"`
 	DeletedAt        gorm.DeletedAt `gorm:"index"`
 }

@@ -78,7 +75,7 @@ func CheckUserExistOrDeleted(username string, email string) (bool, error) {

 func GetMaxUserId() int {
 	var user User
-	DB.Unscoped().Last(&user)
+	DB.Last(&user)
 	return user.Id
 }

@@ -91,18 +88,13 @@ func SearchUsers(keyword string, group string) ([]*User, error) {
 	var users []*User
 	var err error

-	groupCol := "`group`"
-	if common.UsingPostgreSQL {
-		groupCol = `"group"`
-	}
-
 	// 尝试将关键字转换为整数ID
 	keywordInt, err := strconv.Atoi(keyword)
 	if err == nil {
 		// 如果转换成功，按照ID和可选的组别搜索用户
-		query := DB.Unscoped().Omit("password").Where("id = ?", keywordInt)
+		query := DB.Unscoped().Omit("password").Where("`id` = ?", keywordInt)
 		if group != "" {
-			query = query.Where(groupCol+" = ?", group) // 使用反引号包围group
+			query = query.Where("`group` = ?", group) // 使用反引号包围group
 		}
 		err = query.Find(&users).Error
 		if err != nil || len(users) > 0 {
@@ -113,9 +105,9 @@ func SearchUsers(keyword string, group string) ([]*User, error) {
 	err = nil

 	query := DB.Unscoped().Omit("password")
-	likeCondition := "username LIKE ? OR email LIKE ? OR display_name LIKE ?"
+	likeCondition := "`username` LIKE ? OR `email` LIKE ? OR `display_name` LIKE ?"
 	if group != "" {
-		query = query.Where("("+likeCondition+") AND "+groupCol+" = ?", "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
+		query = query.Where("("+likeCondition+") AND `group` = ?", "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
 	} else {
 		query = query.Where(likeCondition, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%")
 	}
@@ -138,20 +130,6 @@ func GetUserById(id int, selectAll bool) (*User, error) {
 	return &user, err
 }

-func GetUserByIdUnscoped(id int, selectAll bool) (*User, error) {
-	if id == 0 {
-		return nil, errors.New("id 为空！")
-	}
-	user := User{Id: id}
-	var err error = nil
-	if selectAll {
-		err = DB.Unscoped().First(&user, "id = ?", id).Error
-	} else {
-		err = DB.Unscoped().Omit("password").First(&user, "id = ?", id).Error
-	}
-	return &user, err
-}
-
 func GetUserIdByAffCode(affCode string) (int, error) {
 	if affCode == "" {
 		return 0, errors.New("affCode 为空！")
@@ -365,14 +343,6 @@ func (user *User) FillUserByGitHubId() error {
 	return nil
 }

-func (user *User) FillUserByLinuxDoId() error {
-	if user.LinuxDoId == "" {
-		return errors.New("LINUX DO id 为空！")
-	}
-	DB.Where(User{LinuxDoId: user.LinuxDoId}).First(user)
-	return nil
-}
-
 func (user *User) FillUserByWeChatId() error {
 	if user.WeChatId == "" {
 		return errors.New("WeChat id 为空！")
@@ -404,14 +374,6 @@ func IsGitHubIdAlreadyTaken(githubId string) bool {
 	return DB.Unscoped().Where("github_id = ?", githubId).Find(&User{}).RowsAffected == 1
 }

-func IsLinuxDoIdAlreadyTaken(linuxdoId string) bool {
-	return DB.Unscoped().Where("linuxdo_id = ?", linuxdoId).Find(&User{}).RowsAffected == 1
-}
-
-func IsUsernameAlreadyTaken(username string) bool {
-	return DB.Unscoped().Where("username = ?", username).Find(&User{}).RowsAffected == 1
-}
-
 func IsTelegramIdAlreadyTaken(telegramId string) bool {
 	return DB.Unscoped().Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
 }
@@ -453,18 +415,6 @@ func IsUserEnabled(userId int) (bool, error) {
 	return user.Status == common.UserStatusEnabled, nil
 }

-func IsLinuxDoEnabled(userId int) (bool, error) {
-	if userId == 0 {
-		return false, errors.New("user id is empty")
-	}
-	var user User
-	err := DB.Where("id = ?", userId).Select("linuxdo_id, linuxdo_level").Find(&user).Error
-	if err != nil {
-		return false, err
-	}
-	return user.LinuxDoId == "" || user.LinuxDoLevel >= common.LinuxDoMinLevel, nil
-}
-
 func ValidateAccessToken(token string) (user *User) {
 	if token == "" {
 		return nil
--- a/relay/channel/adapter.go
+++ b/relay/channel/adapter.go
@@ -12,13 +12,13 @@ type Adaptor interface {
 	// Init IsStream bool
 	Init(info *relaycommon.RelayInfo)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
-	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
+	SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
 	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
 	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
 	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (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)
+	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string
 	GetChannelName() string
 }
--- a/relay/channel/ali/adaptor.go
+++ b/relay/channel/ali/adaptor.go
@@ -32,14 +32,14 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fullRequestURL, nil
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	if info.IsStream {
-		req.Header.Set("X-DashScope-SSE", "enable")
+		req.Set("X-DashScope-SSE", "enable")
 	}
 	if c.GetString("plugin") != "" {
-		req.Header.Set("X-DashScope-Plugin", c.GetString("plugin"))
+		req.Set("X-DashScope-Plugin", c.GetString("plugin"))
 	}
 	return nil
 }
@@ -72,11 +72,11 @@ func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInf
 	return nil, errors.New("not implemented")
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeImagesGenerations:
 		err, usage = aliImageHandler(c, resp, info)
--- a/relay/channel/ali/dto.go
+++ b/relay/channel/ali/dto.go
@@ -36,8 +36,8 @@ type AliEmbeddingRequest struct {
 }

 type AliEmbedding struct {
-	Embedding any `json:"embedding"`
-	TextIndex int `json:"text_index"`
+	Embedding []float64 `json:"embedding"`
+	TextIndex int       `json:"text_index"`
 }

 type AliEmbeddingResponse struct {
--- a/relay/channel/ali/image.go
+++ b/relay/channel/ali/image.go
@@ -105,7 +105,7 @@ func responseAli2OpenAIImage(c *gin.Context, response *AliResponse, info *relayc
 	for _, data := range response.Output.Results {
 		var b64Json string
 		if responseFormat == "b64_json" {
-			_, b64, err := common.GetImageFromUrl(data.Url)
+			_, b64, err := service.GetImageFromUrl(data.Url)
 			if err != nil {
 				common.LogError(c, "get_image_data_failed: "+err.Error())
 				continue
--- a/relay/channel/api_request.go
+++ b/relay/channel/api_request.go
@@ -4,6 +4,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"net/http"
 	"one-api/relay/common"
@@ -11,14 +12,16 @@ import (
 	"one-api/service"
 )

-func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Request) {
+func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Header) {
 	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
 		// multipart/form-data
+	} else if info.RelayMode == constant.RelayModeRealtime {
+		// websocket
 	} else {
-		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		req.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+		req.Set("Accept", c.Request.Header.Get("Accept"))
 		if info.IsStream && c.Request.Header.Get("Accept") == "" {
-			req.Header.Set("Accept", "text/event-stream")
+			req.Set("Accept", "text/event-stream")
 		}
 	}
 }
@@ -32,7 +35,7 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	if err != nil {
 		return nil, fmt.Errorf("new request failed: %w", err)
 	}
-	err = a.SetupRequestHeader(c, req, info)
+	err = a.SetupRequestHeader(c, &req.Header, info)
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
@@ -55,7 +58,7 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	// set form data
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))

-	err = a.SetupRequestHeader(c, req, info)
+	err = a.SetupRequestHeader(c, &req.Header, info)
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
@@ -66,6 +69,27 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	return resp, nil
 }

+func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*websocket.Conn, error) {
+	fullRequestURL, err := a.GetRequestURL(info)
+	if err != nil {
+		return nil, fmt.Errorf("get request url failed: %w", err)
+	}
+	targetHeader := http.Header{}
+	err = a.SetupRequestHeader(c, &targetHeader, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	targetHeader.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	targetConn, _, err := websocket.DefaultDialer.Dial(fullRequestURL, targetHeader)
+	if err != nil {
+		return nil, fmt.Errorf("dial failed to %s: %w", fullRequestURL, err)
+	}
+	// send request body
+	//all, err := io.ReadAll(requestBody)
+	//err = service.WssString(c, targetConn, string(all))
+	return targetConn, nil
+}
+
 func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
--- a/relay/channel/aws/adaptor.go
+++ b/relay/channel/aws/adaptor.go
@@ -37,7 +37,7 @@ 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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	return nil
 }

@@ -48,7 +48,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re

 	var claudeReq *claude.ClaudeRequest
 	var err error
-	claudeReq, err = claude.RequestOpenAI2ClaudeMessage(c, *request)
+	claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)

 	c.Set("request_model", request.Model)
 	c.Set("converted_request", claudeReq)
@@ -59,11 +59,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return nil, nil
 }

-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
 	} else {
--- a/relay/channel/baidu/adaptor.go
+++ b/relay/channel/baidu/adaptor.go
@@ -98,9 +98,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fullRequestURL, nil
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }

@@ -122,11 +122,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = baiduStreamHandler(c, resp)
 	} else {
--- a/relay/channel/baidu/dto.go
+++ b/relay/channel/baidu/dto.go
@@ -50,9 +50,9 @@ type BaiduEmbeddingRequest struct {
 }

 type BaiduEmbeddingData struct {
-	Object    string `json:"object"`
-	Embedding any    `json:"embedding"`
-	Index     int    `json:"index"`
+	Object    string    `json:"object"`
+	Embedding []float64 `json:"embedding"`
+	Index     int       `json:"index"`
 }

 type BaiduEmbeddingResponse struct {
--- a/relay/channel/claude/adaptor.go
+++ b/relay/channel/claude/adaptor.go
@@ -47,21 +47,14 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-api-key", info.ApiKey)
-
+	req.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)
-
-	anthropicBeta := c.Request.Header.Get("anthropic-beta")
-	if "" != anthropicBeta {
-		req.Header.Set("anthropic-beta", anthropicBeta)
-	}
-
+	req.Set("anthropic-version", anthropicVersion)
 	return nil
 }

@@ -70,9 +63,9 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		return nil, errors.New("request is nil")
 	}
 	if a.RequestMode == RequestModeCompletion {
-		return RequestOpenAI2ClaudeComplete(c, *request), nil
+		return RequestOpenAI2ClaudeComplete(*request), nil
 	} else {
-		return RequestOpenAI2ClaudeMessage(c, *request)
+		return RequestOpenAI2ClaudeMessage(*request)
 	}
 }

@@ -80,11 +73,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = ClaudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
--- a/relay/channel/claude/constants.go
+++ b/relay/channel/claude/constants.go
@@ -11,8 +11,6 @@ var ModelList = []string{
 	"claude-3-5-haiku-20241022",
 	"claude-3-5-sonnet-20240620",
 	"claude-3-5-sonnet-20241022",
-	"claude-3-7-sonnet-20250219",
-	"claude-3-7-sonnet-20250219-thinking",
 }

 var ChannelName = "claude"
--- a/relay/channel/claude/dto.go
+++ b/relay/channel/claude/dto.go
@@ -1,7 +1,5 @@
 package claude

-import "one-api/dto"
-
 type ClaudeMetadata struct {
 	UserId string `json:"user_id"`
 }
@@ -13,9 +11,6 @@ type ClaudeMediaMessage struct {
 	Usage       *ClaudeUsage         `json:"usage,omitempty"`
 	StopReason  *string              `json:"stop_reason,omitempty"`
 	PartialJson string               `json:"partial_json,omitempty"`
-	Thinking    string               `json:"thinking,omitempty"`
-	Signature   string               `json:"signature,omitempty"`
-	Delta       string               `json:"delta,omitempty"`
 	// tool_calls
 	Id        string `json:"id,omitempty"`
 	Name      string `json:"name,omitempty"`
@@ -36,13 +31,9 @@ type ClaudeMessage struct {
 }

 type Tool struct {
-	Name            string                 `json:"name"`
-	Description     any                    `json:"description,omitempty"`
-	InputSchema     map[string]interface{} `json:"input_schema,omitempty"`
-	Type            any                    `json:"type,omitempty"`
-	DisplayHeightPx int                    `json:"display_height_px,omitempty"`
-	DisplayWidthPx  int                    `json:"display_width_px,omitempty"`
-	DisplayNumber   int                    `json:"display_number,omitempty"`
+	Name        string                 `json:"name"`
+	Description string                 `json:"description,omitempty"`
+	InputSchema map[string]interface{} `json:"input_schema"`
 }

 type InputSchema struct {
@@ -63,10 +54,9 @@ type ClaudeRequest struct {
 	TopP              float64         `json:"top_p,omitempty"`
 	TopK              int             `json:"top_k,omitempty"`
 	//ClaudeMetadata    `json:"metadata,omitempty"`
-	Stream     bool          `json:"stream,omitempty"`
-	Tools      []Tool        `json:"tools,omitempty"`
-	ToolChoice any           `json:"tool_choice,omitempty"`
-	Thinking   *dto.Thinking `json:"thinking,omitempty"`
+	Stream     bool   `json:"stream,omitempty"`
+	Tools      []Tool `json:"tools,omitempty"`
+	ToolChoice any    `json:"tool_choice,omitempty"`
 }

 type ClaudeError struct {
--- a/relay/channel/claude/relay-claude.go
+++ b/relay/channel/claude/relay-claude.go
@@ -28,7 +28,7 @@ func stopReasonClaude2OpenAI(reason string) string {
 	}
 }

-func RequestOpenAI2ClaudeComplete(c *gin.Context, textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
+func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {

 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
@@ -59,68 +59,27 @@ func RequestOpenAI2ClaudeComplete(c *gin.Context, textRequest dto.GeneralOpenAIR
 	return &claudeRequest
 }

-func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
+func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
 	claudeTools := make([]Tool, 0, len(textRequest.Tools))

-	if strings.HasSuffix(textRequest.Model, "-thinking") {
-		textRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
-
-		if textRequest.MaxTokens == 0 {
-			textRequest.MaxTokens = 8192
-		} else if textRequest.MaxTokens < 2048 {
-			textRequest.MaxTokens = 2048
-		} else if textRequest.MaxTokens > 64000 {
-			c.Request.Header.Set("anthropic-beta", "output-128k-2025-02-19")
-		}
-
-		textRequest.TopP = 0
-		textRequest.TopK = 0
-		textRequest.Temperature = 0
-		textRequest.Thinking = &dto.Thinking{
-			Type:         "enabled",
-			BudgetTokens: int(float64(textRequest.MaxTokens) * 0.5),
-		}
-	}
-
 	for _, tool := range textRequest.Tools {
-		claudeTool := Tool{
-			Name:        tool.Function.Name,
-			Description: tool.Function.Description,
-			Type:        tool.Type,
-		}
-
-		if "function" != tool.Type {
-			claudeTool.Description = nil
-		}
-
 		if params, ok := tool.Function.Parameters.(map[string]any); ok {
-			if "function" == tool.Type {
-				claudeTool.Type = nil
-
-				claudeTool.InputSchema = make(map[string]interface{})
-				claudeTool.InputSchema["type"] = params["type"].(string)
-				claudeTool.InputSchema["properties"] = params["properties"]
-				claudeTool.InputSchema["required"] = params["required"]
-				for s, a := range params {
-					if s == "type" || s == "properties" || s == "required" {
-						continue
-					}
-					claudeTool.InputSchema[s] = a
-				}
-			} else {
-				if val, ok := params["display_height_px"]; ok {
-					claudeTool.DisplayHeightPx = int(val.(float64))
-				}
-				if val, ok := params["display_width_px"]; ok {
-					claudeTool.DisplayWidthPx = int(val.(float64))
-				}
-				if val, ok := params["display_number"]; ok {
-					claudeTool.DisplayNumber = int(val.(float64))
-				}
+			claudeTool := Tool{
+				Name:        tool.Function.Name,
+				Description: tool.Function.Description,
 			}
+			claudeTool.InputSchema = make(map[string]interface{})
+			claudeTool.InputSchema["type"] = params["type"].(string)
+			claudeTool.InputSchema["properties"] = params["properties"]
+			claudeTool.InputSchema["required"] = params["required"]
+			for s, a := range params {
+				if s == "type" || s == "properties" || s == "required" {
+					continue
+				}
+				claudeTool.InputSchema[s] = a
+			}
+			claudeTools = append(claudeTools, claudeTool)
 		}
-
-		claudeTools = append(claudeTools, claudeTool)
 	}

 	claudeRequest := ClaudeRequest{
@@ -132,8 +91,6 @@ func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRe
 		TopK:          textRequest.TopK,
 		Stream:        textRequest.Stream,
 		Tools:         claudeTools,
-		ToolChoice:    textRequest.ToolChoice,
-		Thinking:      textRequest.Thinking,
 	}
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
@@ -268,11 +225,11 @@ func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRe
 						// 判断是否是url
 						if strings.HasPrefix(imageUrl.Url, "http") {
 							// 是url，获取图片的类型和base64编码的数据
-							mimeType, data, _ := common.GetImageFromUrl(imageUrl.Url)
+							mimeType, data, _ := service.GetImageFromUrl(imageUrl.Url)
 							claudeMediaMessage.Source.MediaType = mimeType
 							claudeMediaMessage.Source.Data = data
 						} else {
-							_, format, base64String, err := common.DecodeBase64ImageData(imageUrl.Url)
+							_, format, base64String, err := service.DecodeBase64ImageData(imageUrl.Url)
 							if err != nil {
 								return nil, err
 							}
@@ -355,19 +312,12 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 			if claudeResponse.Delta != nil {
 				choice.Index = claudeResponse.Index
 				choice.Delta.SetContentString(claudeResponse.Delta.Text)
-				switch claudeResponse.Delta.Type {
-				case "input_json_delta":
+				if claudeResponse.Delta.Type == "input_json_delta" {
 					tools = append(tools, dto.ToolCall{
 						Function: dto.FunctionCall{
 							Arguments: claudeResponse.Delta.PartialJson,
 						},
 					})
-				case "signature_delta":
-					reasoningContent := "\n"
-					choice.Delta.ReasoningContent = &reasoningContent
-				case "thinking_delta":
-					reasoningContent := claudeResponse.Delta.Thinking
-					choice.Delta.ReasoningContent = &reasoningContent
 				}
 			}
 		} else if claudeResponse.Type == "message_delta" {
@@ -405,8 +355,6 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	if len(claudeResponse.Content) > 0 {
 		responseText = claudeResponse.Content[0].Text
 	}
-
-	reasoningContent := ""
 	tools := make([]dto.ToolCall, 0)
 	if reqMode == RequestModeCompletion {
 		content, _ := json.Marshal(strings.TrimPrefix(claudeResponse.Completion, " "))
@@ -423,8 +371,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	} else {
 		fullTextResponse.Id = claudeResponse.Id
 		for _, message := range claudeResponse.Content {
-			switch message.Type {
-			case "tool_use":
+			if message.Type == "tool_use" {
 				args, _ := json.Marshal(message.Input)
 				tools = append(tools, dto.ToolCall{
 					ID:   message.Id,
@@ -434,10 +381,6 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 						Arguments: string(args),
 					},
 				})
-			case "thinking":
-				reasoningContent = message.Thinking
-			case "text":
-				responseText = message.Text
 			}
 		}
 	}
@@ -452,7 +395,6 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	if len(tools) > 0 {
 		choice.Message.ToolCalls = tools
 	}
-	choice.Message.ReasoningContent = &reasoningContent
 	fullTextResponse.Model = claudeResponse.Model
 	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
@@ -567,7 +509,7 @@ func ClaudeHandler(c *gin.Context, resp *http.Response, requestMode int, info *r
 		}, nil
 	}
 	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err := service.CountTokenText(claudeResponse.Completion, info.OriginModelName)
+	completionTokens, err := service.CountTextToken(claudeResponse.Completion, info.OriginModelName)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}
--- a/relay/channel/cloudflare/adaptor.go
+++ b/relay/channel/cloudflare/adaptor.go
@@ -30,9 +30,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }

@@ -48,7 +48,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	}
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

@@ -78,7 +78,7 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 	return nil, errors.New("not implemented")
 }

-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		fallthrough
--- a/relay/channel/cloudflare/relay_cloudflare.go
+++ b/relay/channel/cloudflare/relay_cloudflare.go
@@ -149,7 +149,7 @@ func cfSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayIn

 	usage := &dto.Usage{}
 	usage.PromptTokens = info.PromptTokens
-	usage.CompletionTokens, _ = service.CountTokenText(cfResp.Result.Text, info.UpstreamModelName)
+	usage.CompletionTokens, _ = service.CountTextToken(cfResp.Result.Text, info.UpstreamModelName)
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens

 	return nil, usage
--- a/relay/channel/cohere/adaptor.go
+++ b/relay/channel/cohere/adaptor.go
@@ -36,9 +36,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }

@@ -46,7 +46,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return requestOpenAI2Cohere(*request), nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

@@ -54,7 +54,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return requestConvertRerank2Cohere(request), nil
 }

-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = cohereRerankHandler(c, resp, info)
 	} else {
--- a/relay/channel/dify/adaptor.go
+++ b/relay/channel/dify/adaptor.go
@@ -31,9 +31,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/v1/chat-messages", info.BaseUrl), nil
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }

@@ -48,11 +48,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = difyStreamHandler(c, resp, info)
 	} else {
--- a/relay/channel/dify/relay-dify.go
+++ b/relay/channel/dify/relay-dify.go
@@ -108,7 +108,7 @@ func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Re
 	}
 	if usage.TotalTokens == 0 {
 		usage.PromptTokens = info.PromptTokens
-		usage.CompletionTokens, _ = service.CountTokenText("gpt-3.5-turbo", responseText)
+		usage.CompletionTokens, _ = service.CountTextToken("gpt-3.5-turbo", responseText)
 		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	}
 	return nil, usage
--- a/relay/channel/gemini/adaptor.go
+++ b/relay/channel/gemini/adaptor.go
@@ -47,9 +47,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-goog-api-key", info.ApiKey)
+	req.Set("x-goog-api-key", info.ApiKey)
 	return nil
 }

@@ -64,11 +64,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = GeminiChatStreamHandler(c, resp, info)
 	} else {
--- a/relay/channel/gemini/relay-gemini.go
+++ b/relay/channel/gemini/relay-gemini.go
@@ -86,7 +86,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				// 判断是否是url
 				if strings.HasPrefix(part.ImageUrl.(dto.MessageImageUrl).Url, "http") {
 					// 是url，获取图片的类型和base64编码的数据
-					mimeType, data, _ := common.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
+					mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
 					parts = append(parts, GeminiPart{
 						InlineData: &GeminiInlineData{
 							MimeType: mimeType,
@@ -94,7 +94,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 						},
 					})
 				} else {
-					_, format, base64String, err := common.DecodeBase64ImageData(part.ImageUrl.(dto.MessageImageUrl).Url)
+					_, format, base64String, err := service.DecodeBase64ImageData(part.ImageUrl.(dto.MessageImageUrl).Url)
 					if err != nil {
 						continue
 					}
--- a/relay/channel/jina/adaptor.go
+++ b/relay/channel/jina/adaptor.go
@@ -37,9 +37,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return "", errors.New("invalid relay mode")
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }

@@ -47,7 +47,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return request, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

@@ -55,7 +55,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }

-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = jinaRerankHandler(c, resp)
 	} else if info.RelayMode == constant.RelayModeEmbeddings {
--- a/relay/channel/mistral/adaptor.go
+++ b/relay/channel/mistral/adaptor.go
@@ -0,0 +1,72 @@
+package mistral
+
+import (
+	"errors"
+	"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"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	mistralReq := requestOpenAI2Mistral(*request)
+	//common.LogJson(c, "body", mistralReq)
+	return mistralReq, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = openai.OaiStreamHandler(c, resp, info)
+	} 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/mistral/constants.go
+++ b/relay/channel/mistral/constants.go
@@ -0,0 +1,12 @@
+package mistral
+
+var ModelList = []string{
+	"open-mistral-7b",
+	"open-mixtral-8x7b",
+	"mistral-small-latest",
+	"mistral-medium-latest",
+	"mistral-large-latest",
+	"mistral-embed",
+}
+
+var ChannelName = "mistral"
--- a/relay/channel/mistral/text.go
+++ b/relay/channel/mistral/text.go
@@ -0,0 +1,40 @@
+package mistral
+
+import (
+	"encoding/json"
+	"one-api/dto"
+)
+
+func requestOpenAI2Mistral(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIRequest {
+	messages := make([]dto.Message, 0, len(request.Messages))
+	for _, message := range request.Messages {
+		if !message.IsStringContent() {
+			mediaMessages := message.ParseContent()
+			for j, mediaMessage := range mediaMessages {
+				if mediaMessage.Type == dto.ContentTypeImageURL {
+					imageUrl := mediaMessage.ImageUrl.(dto.MessageImageUrl)
+					mediaMessage.ImageUrl = imageUrl.Url
+					mediaMessages[j] = mediaMessage
+				}
+			}
+			messageRaw, _ := json.Marshal(mediaMessages)
+			message.Content = messageRaw
+		}
+		messages = append(messages, dto.Message{
+			Role:       message.Role,
+			Content:    message.Content,
+			ToolCalls:  message.ToolCalls,
+			ToolCallId: message.ToolCallId,
+		})
+	}
+	return &dto.GeneralOpenAIRequest{
+		Model:       request.Model,
+		Stream:      request.Stream,
+		Messages:    messages,
+		Temperature: request.Temperature,
+		TopP:        request.TopP,
+		MaxTokens:   request.MaxTokens,
+		Tools:       request.Tools,
+		ToolChoice:  request.ToolChoice,
+	}
+}
--- a/relay/channel/ollama/adaptor.go
+++ b/relay/channel/ollama/adaptor.go
@@ -31,13 +31,13 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	switch info.RelayMode {
 	case relayconstant.RelayModeEmbeddings:
-		return info.BaseUrl + "/api/embeddings", nil
+		return info.BaseUrl + "/api/embed", nil
 	default:
 		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 	}
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	return nil
 }
@@ -58,11 +58,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
--- a/relay/channel/ollama/dto.go
+++ b/relay/channel/ollama/dto.go
@@ -35,7 +35,7 @@ type OllamaEmbeddingRequest struct {
 }

 type OllamaEmbeddingResponse struct {
-	Embedding any `json:"embedding,omitempty"`
 	Error     string    `json:"error,omitempty"`
 	Model     string    `json:"model"`
+	Embedding [][]float64 `json:"embeddings,omitempty"`
 }
--- a/relay/channel/ollama/relay-ollama.go
+++ b/relay/channel/ollama/relay-ollama.go
@@ -73,9 +73,10 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 	if ollamaEmbeddingResponse.Error != "" {
 		return service.OpenAIErrorWrapper(err, "ollama_error", resp.StatusCode), nil
 	}
+	flattenedEmbeddings := flattenEmbeddings(ollamaEmbeddingResponse.Embedding)
 	data := make([]dto.OpenAIEmbeddingResponseItem, 0, 1)
 	data = append(data, dto.OpenAIEmbeddingResponseItem{
-		Embedding: ollamaEmbeddingResponse.Embedding,
+		Embedding: flattenedEmbeddings,
 		Object:    "embedding",
 	})
 	usage := &dto.Usage{
@@ -120,3 +121,11 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 	}
 	return nil, usage
 }
+
+func flattenEmbeddings(embeddings [][]float64) []float64 {
+flattened := []float64{}
+for _, row := range embeddings {
+	flattened = append(flattened, row...)
+}
+return flattened
+}
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -31,6 +31,13 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }

 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRealtime {
+		// trim https
+		baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
+		baseUrl = strings.TrimPrefix(baseUrl, "http://")
+		baseUrl = "wss://" + baseUrl
+		info.BaseUrl = baseUrl
+	}
 	switch info.ChannelType {
 	case common.ChannelTypeAzure:
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
@@ -40,8 +47,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		model_ := info.UpstreamModelName
 		model_ = strings.Replace(model_, ".", "", -1)
 		// https://github.com/songquanpeng/one-api/issues/67
-
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
+		if info.RelayMode == constant.RelayModeRealtime {
+			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion)
+		}
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
 	case common.ChannelTypeMiniMax:
 		return minimax.GetRequestURL(info)
@@ -54,16 +63,34 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
-	channel.SetupApiRequestHeader(info, c, req)
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, header *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, header)
 	if info.ChannelType == common.ChannelTypeAzure {
-		req.Header.Set("api-key", info.ApiKey)
+		header.Set("api-key", info.ApiKey)
 		return nil
 	}
 	if info.ChannelType == common.ChannelTypeOpenAI && "" != info.Organization {
-		req.Header.Set("OpenAI-Organization", info.Organization)
+		header.Set("OpenAI-Organization", info.Organization)
+	}
+	if info.RelayMode == constant.RelayModeRealtime {
+		swp := c.Request.Header.Get("Sec-WebSocket-Protocol")
+		if swp != "" {
+			items := []string{
+				"realtime",
+				"openai-insecure-api-key." + info.ApiKey,
+				"openai-beta.realtime-v1",
+			}
+			header.Set("Sec-WebSocket-Protocol", strings.Join(items, ","))
+			//req.Header.Set("Sec-WebSocket-Key", c.Request.Header.Get("Sec-WebSocket-Key"))
+			//req.Header.Set("Sec-Websocket-Extensions", c.Request.Header.Get("Sec-Websocket-Extensions"))
+			//req.Header.Set("Sec-Websocket-Version", c.Request.Header.Get("Sec-Websocket-Version"))
+		} else {
+			header.Set("openai-beta", "realtime=v1")
+			header.Set("Authorization", "Bearer "+info.ApiKey)
+		}
+	} else {
+		header.Set("Authorization", "Bearer "+info.ApiKey)
 	}
-	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")
@@ -78,7 +105,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	if info.ChannelType != common.ChannelTypeOpenAI {
 		request.StreamOptions = nil
 	}
-	if "o1" == request.Model || strings.HasPrefix(request.Model, "o1-") {
+	if strings.HasPrefix(request.Model, "o1-") {
 		if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 {
 			request.MaxCompletionTokens = request.MaxTokens
 			request.MaxTokens = 0
@@ -131,16 +158,20 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 	return request, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
 		return channel.DoFormRequest(a, c, info, requestBody)
+	} else if info.RelayMode == constant.RelayModeRealtime {
+		return channel.DoWssRequest(a, c, info, requestBody)
 	} else {
 		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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
+	case constant.RelayModeRealtime:
+		err, usage = OpenaiRealtimeHandler(c, info)
 	case constant.RelayModeAudioSpeech:
 		err, usage = OpenaiTTSHandler(c, resp, info)
 	case constant.RelayModeAudioTranslation:
--- a/relay/channel/openai/constant.go
+++ b/relay/channel/openai/constant.go
@@ -1,24 +1,26 @@
 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", "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", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
+	"gpt-4-32k", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
 	"chatgpt-4o-latest",
-	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06", "gpt-4o-2024-08-06",
+	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"o1-preview", "o1-preview-2024-09-12",
 	"o1-mini", "o1-mini-2024-09-12",
+	"gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01",
+	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01",
 	"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-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",
 	"text-davinci-edit-001",
 	"davinci-002", "babbage-002",
-	"dall-e-2", "dall-e-3",
+	"dall-e-3",
 	"whisper-1",
 	"tts-1", "tts-1-1106", "tts-1-hd", "tts-1-hd-1106",
 }
--- a/relay/channel/openai/relay-openai.go
+++ b/relay/channel/openai/relay-openai.go
@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -231,7 +232,7 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
-			ctkm, _ := service.CountTokenText(string(choice.Message.Content), model)
+			ctkm, _ := service.CountTextToken(string(choice.Message.Content), model)
 			completionTokens += ctkm
 		}
 		simpleResponse.Usage = dto.Usage{
@@ -324,7 +325,7 @@ func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel

 	usage := &dto.Usage{}
 	usage.PromptTokens = info.PromptTokens
-	usage.CompletionTokens, _ = service.CountTokenText(text, info.UpstreamModelName)
+	usage.CompletionTokens, _ = service.CountTextToken(text, info.UpstreamModelName)
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	return nil, usage
 }
@@ -373,3 +374,210 @@ func getTextFromJSON(body []byte) (string, error) {
 	}
 	return whisperResponse.Text, nil
 }
+
+func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.RealtimeUsage) {
+	info.IsStream = true
+	clientConn := info.ClientWs
+	targetConn := info.TargetWs
+
+	clientClosed := make(chan struct{})
+	targetClosed := make(chan struct{})
+	sendChan := make(chan []byte, 100)
+	receiveChan := make(chan []byte, 100)
+	errChan := make(chan error, 2)
+
+	usage := &dto.RealtimeUsage{}
+	localUsage := &dto.RealtimeUsage{}
+	sumUsage := &dto.RealtimeUsage{}
+
+	gopool.Go(func() {
+		for {
+			select {
+			case <-c.Done():
+				return
+			default:
+				_, message, err := clientConn.ReadMessage()
+				if err != nil {
+					if !websocket.IsCloseError(err, websocket.CloseNormalClosure, websocket.CloseGoingAway) {
+						errChan <- fmt.Errorf("error reading from client: %v", err)
+					}
+					close(clientClosed)
+					return
+				}
+
+				realtimeEvent := &dto.RealtimeEvent{}
+				err = json.Unmarshal(message, realtimeEvent)
+				if err != nil {
+					errChan <- fmt.Errorf("error unmarshalling message: %v", err)
+					return
+				}
+
+				if realtimeEvent.Type == dto.RealtimeEventTypeSessionUpdate {
+					if realtimeEvent.Session != nil {
+						if realtimeEvent.Session.Tools != nil {
+							info.RealtimeTools = realtimeEvent.Session.Tools
+						}
+					}
+				}
+
+				textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+				if err != nil {
+					errChan <- fmt.Errorf("error counting text token: %v", err)
+					return
+				}
+				common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+				localUsage.TotalTokens += textToken + audioToken
+				localUsage.InputTokens += textToken + audioToken
+				localUsage.InputTokenDetails.TextTokens += textToken
+				localUsage.InputTokenDetails.AudioTokens += audioToken
+
+				err = service.WssString(c, targetConn, string(message))
+				if err != nil {
+					errChan <- fmt.Errorf("error writing to target: %v", err)
+					return
+				}
+
+				select {
+				case sendChan <- message:
+				default:
+				}
+			}
+		}
+	})
+
+	gopool.Go(func() {
+		for {
+			select {
+			case <-c.Done():
+				return
+			default:
+				_, message, err := targetConn.ReadMessage()
+				if err != nil {
+					if !websocket.IsCloseError(err, websocket.CloseNormalClosure, websocket.CloseGoingAway) {
+						errChan <- fmt.Errorf("error reading from target: %v", err)
+					}
+					close(targetClosed)
+					return
+				}
+				info.SetFirstResponseTime()
+				realtimeEvent := &dto.RealtimeEvent{}
+				err = json.Unmarshal(message, realtimeEvent)
+				if err != nil {
+					errChan <- fmt.Errorf("error unmarshalling message: %v", err)
+					return
+				}
+
+				if realtimeEvent.Type == dto.RealtimeEventTypeResponseDone {
+					realtimeUsage := realtimeEvent.Response.Usage
+					if realtimeUsage != nil {
+						usage.TotalTokens += realtimeUsage.TotalTokens
+						usage.InputTokens += realtimeUsage.InputTokens
+						usage.OutputTokens += realtimeUsage.OutputTokens
+						usage.InputTokenDetails.AudioTokens += realtimeUsage.InputTokenDetails.AudioTokens
+						usage.InputTokenDetails.CachedTokens += realtimeUsage.InputTokenDetails.CachedTokens
+						usage.InputTokenDetails.TextTokens += realtimeUsage.InputTokenDetails.TextTokens
+						usage.OutputTokenDetails.AudioTokens += realtimeUsage.OutputTokenDetails.AudioTokens
+						usage.OutputTokenDetails.TextTokens += realtimeUsage.OutputTokenDetails.TextTokens
+						err := preConsumeUsage(c, info, usage, sumUsage)
+						if err != nil {
+							errChan <- fmt.Errorf("error consume usage: %v", err)
+							return
+						}
+						// 本次计费完成，清除
+						usage = &dto.RealtimeUsage{}
+
+						localUsage = &dto.RealtimeUsage{}
+					} else {
+						textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+						if err != nil {
+							errChan <- fmt.Errorf("error counting text token: %v", err)
+							return
+						}
+						common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+						localUsage.TotalTokens += textToken + audioToken
+						info.IsFirstRequest = false
+						localUsage.InputTokens += textToken + audioToken
+						localUsage.InputTokenDetails.TextTokens += textToken
+						localUsage.InputTokenDetails.AudioTokens += audioToken
+						err = preConsumeUsage(c, info, localUsage, sumUsage)
+						if err != nil {
+							errChan <- fmt.Errorf("error consume usage: %v", err)
+							return
+						}
+						// 本次计费完成，清除
+						localUsage = &dto.RealtimeUsage{}
+						// print now usage
+					}
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming sumUsage: %v", sumUsage))
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming localUsage: %v", localUsage))
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming localUsage: %v", localUsage))
+
+				} else if realtimeEvent.Type == dto.RealtimeEventTypeSessionUpdated || realtimeEvent.Type == dto.RealtimeEventTypeSessionCreated {
+					realtimeSession := realtimeEvent.Session
+					if realtimeSession != nil {
+						// update audio format
+						info.InputAudioFormat = common.GetStringIfEmpty(realtimeSession.InputAudioFormat, info.InputAudioFormat)
+						info.OutputAudioFormat = common.GetStringIfEmpty(realtimeSession.OutputAudioFormat, info.OutputAudioFormat)
+					}
+				} else {
+					textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+					if err != nil {
+						errChan <- fmt.Errorf("error counting text token: %v", err)
+						return
+					}
+					common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+					localUsage.TotalTokens += textToken + audioToken
+					localUsage.OutputTokens += textToken + audioToken
+					localUsage.OutputTokenDetails.TextTokens += textToken
+					localUsage.OutputTokenDetails.AudioTokens += audioToken
+				}
+
+				err = service.WssString(c, clientConn, string(message))
+				if err != nil {
+					errChan <- fmt.Errorf("error writing to client: %v", err)
+					return
+				}
+
+				select {
+				case receiveChan <- message:
+				default:
+				}
+			}
+		}
+	})
+
+	select {
+	case <-clientClosed:
+	case <-targetClosed:
+	case err := <-errChan:
+		//return service.OpenAIErrorWrapper(err, "realtime_error", http.StatusInternalServerError), nil
+		common.LogError(c, "realtime error: "+err.Error())
+	case <-c.Done():
+	}
+
+	if usage.TotalTokens != 0 {
+		_ = preConsumeUsage(c, info, usage, sumUsage)
+	}
+
+	if localUsage.TotalTokens != 0 {
+		_ = preConsumeUsage(c, info, localUsage, sumUsage)
+	}
+
+	// check usage total tokens, if 0, use local usage
+
+	return nil, sumUsage
+}
+
+func preConsumeUsage(ctx *gin.Context, info *relaycommon.RelayInfo, usage *dto.RealtimeUsage, totalUsage *dto.RealtimeUsage) error {
+	totalUsage.TotalTokens += usage.TotalTokens
+	totalUsage.InputTokens += usage.InputTokens
+	totalUsage.OutputTokens += usage.OutputTokens
+	totalUsage.InputTokenDetails.CachedTokens += usage.InputTokenDetails.CachedTokens
+	totalUsage.InputTokenDetails.TextTokens += usage.InputTokenDetails.TextTokens
+	totalUsage.InputTokenDetails.AudioTokens += usage.InputTokenDetails.AudioTokens
+	totalUsage.OutputTokenDetails.TextTokens += usage.OutputTokenDetails.TextTokens
+	totalUsage.OutputTokenDetails.AudioTokens += usage.OutputTokenDetails.AudioTokens
+	// clear usage
+	err := service.PreWssConsumeQuota(ctx, info, usage)
+	return err
+}
--- a/relay/channel/palm/adaptor.go
+++ b/relay/channel/palm/adaptor.go
@@ -32,9 +32,9 @@ 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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-goog-api-key", info.ApiKey)
+	req.Set("x-goog-api-key", info.ApiKey)
 	return nil
 }

@@ -49,11 +49,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
 		err, responseText = palmStreamHandler(c, resp)
--- a/relay/channel/palm/relay-palm.go
+++ b/relay/channel/palm/relay-palm.go
@@ -156,7 +156,7 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	completionTokens, _ := service.CountTokenText(palmResponse.Candidates[0].Content, model)
+	completionTokens, _ := service.CountTextToken(palmResponse.Candidates[0].Content, model)
 	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,
--- a/relay/channel/perplexity/adaptor.go
+++ b/relay/channel/perplexity/adaptor.go
@@ -32,9 +32,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/chat/completions", info.BaseUrl), nil
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }

@@ -52,11 +52,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
--- a/relay/channel/siliconflow/adaptor.go
+++ b/relay/channel/siliconflow/adaptor.go
@@ -40,9 +40,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return "", errors.New("invalid relay mode")
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }

@@ -50,7 +50,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return request, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

@@ -58,7 +58,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }

-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeRerank:
 		err, usage = siliconflowRerankHandler(c, resp)
--- a/relay/channel/tencent/adaptor.go
+++ b/relay/channel/tencent/adaptor.go
@@ -43,12 +43,12 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/", info.BaseUrl), nil
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", a.Sign)
-	req.Header.Set("X-TC-Action", a.Action)
-	req.Header.Set("X-TC-Version", a.Version)
-	req.Header.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
+	req.Set("Authorization", a.Sign)
+	req.Set("X-TC-Action", a.Action)
+	req.Set("X-TC-Version", a.Version)
+	req.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
 	return nil
 }

@@ -73,11 +73,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
 		err, responseText = tencentStreamHandler(c, resp)
--- a/relay/channel/vertex/adaptor.go
+++ b/relay/channel/vertex/adaptor.go
@@ -107,13 +107,13 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return "", errors.New("unsupported request mode")
 }

-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	accessToken, err := getAccessToken(a, info)
 	if err != nil {
 		return err
 	}
-	req.Header.Set("Authorization", "Bearer "+accessToken)
+	req.Set("Authorization", "Bearer "+accessToken)
 	return nil
 }

@@ -122,7 +122,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		return nil, errors.New("request is nil")
 	}
 	if a.RequestMode == RequestModeClaude {
-		claudeReq, err := claude.RequestOpenAI2ClaudeMessage(c, *request)
+		claudeReq, err := claude.RequestOpenAI2ClaudeMessage(*request)
 		if err != nil {
 			return nil, err
 		}
@@ -148,11 +148,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		switch a.RequestMode {
 		case RequestModeClaude:
--- a/relay/channel/xunfei/adaptor.go
+++ b/relay/channel/xunfei/adaptor.go
@@ -33,7 +33,7 @@ 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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	return nil
 }
@@ -50,14 +50,14 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	splits := strings.Split(info.ApiKey, "|")
 	if len(splits) != 3 {
 		return nil, service.OpenAIErrorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
--- a/relay/channel/zhipu/adaptor.go
+++ b/relay/channel/zhipu/adaptor.go
@@ -35,10 +35,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	token := getZhipuToken(info.ApiKey)
-	req.Header.Set("Authorization", token)
+	req.Set("Authorization", token)
 	return nil
 }

@@ -56,11 +56,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = zhipuStreamHandler(c, resp)
 	} else {
--- a/relay/channel/zhipu_4v/adaptor.go
+++ b/relay/channel/zhipu_4v/adaptor.go
@@ -32,10 +32,10 @@ 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 {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	token := getZhipuToken(info.ApiKey)
-	req.Header.Set("Authorization", token)
+	req.Set("Authorization", token)
 	return nil
 }

@@ -53,11 +53,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }

-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, 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) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
--- a/relay/common/relay_info.go
+++ b/relay/common/relay_info.go
@@ -2,7 +2,9 @@ package common

 import (
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"one-api/common"
+	"one-api/dto"
 	"one-api/relay/constant"
 	"strings"
 	"time"
@@ -21,6 +23,7 @@ type RelayInfo struct {
 	ApiType              int
 	IsStream             bool
 	IsPlayground         bool
+	UsePrice             bool
 	RelayMode            int
 	UpstreamModelName    string
 	OriginModelName      string
@@ -32,6 +35,22 @@ type RelayInfo struct {
 	BaseUrl              string
 	SupportStreamOptions bool
 	ShouldIncludeUsage   bool
+	ClientWs             *websocket.Conn
+	TargetWs             *websocket.Conn
+	InputAudioFormat     string
+	OutputAudioFormat    string
+	RealtimeTools        []dto.RealTimeTool
+	IsFirstRequest       bool
+	AudioUsage           bool
+}
+
+func GenRelayInfoWs(c *gin.Context, ws *websocket.Conn) *RelayInfo {
+	info := GenRelayInfo(c)
+	info.ClientWs = ws
+	info.InputAudioFormat = "pcm16"
+	info.OutputAudioFormat = "pcm16"
+	info.IsFirstRequest = true
+	return info
 }

 func GenRelayInfo(c *gin.Context) *RelayInfo {
--- a/relay/constant/api_type.go
+++ b/relay/constant/api_type.go
@@ -25,6 +25,7 @@ const (
 	APITypeCloudflare
 	APITypeSiliconFlow
 	APITypeVertexAi
+	APITypeMistral

 	APITypeDummy // this one is only for count, do not add any channel after this
 )
@@ -72,6 +73,8 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeSiliconFlow
 	case common.ChannelTypeVertexAi:
 		apiType = APITypeVertexAi
+	case common.ChannelTypeMistral:
+		apiType = APITypeMistral
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false
--- a/relay/constant/relay_mode.go
+++ b/relay/constant/relay_mode.go
@@ -38,6 +38,8 @@ const (
 	RelayModeSunoSubmit

 	RelayModeRerank
+
+	RelayModeRealtime
 )

 func Path2RelayMode(path string) int {
@@ -64,6 +66,8 @@ func Path2RelayMode(path string) int {
 		relayMode = RelayModeAudioTranslation
 	} else if strings.HasPrefix(path, "/v1/rerank") {
 		relayMode = RelayModeRerank
+	} else if strings.HasPrefix(path, "/v1/realtime") {
+		relayMode = RelayModeRealtime
 	}
 	return relayMode
 }
--- a/relay/relay-audio.go
+++ b/relay/relay-audio.go
@@ -46,7 +46,7 @@ func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 	return audioRequest, nil
 }

-func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
+func AudioHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	relayInfo := relaycommon.GenRelayInfo(c)
 	audioRequest, err := getAndValidAudioRequest(c, relayInfo)

@@ -58,7 +58,7 @@ func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	promptTokens := 0
 	preConsumedTokens := common.PreConsumedQuota
 	if relayInfo.RelayMode == relayconstant.RelayModeAudioSpeech {
-		promptTokens, err = service.CountAudioToken(audioRequest.Input, audioRequest.Model)
+		promptTokens, err = service.CountTTSToken(audioRequest.Input, audioRequest.Model)
 		if err != nil {
 			return service.OpenAIErrorWrapper(err, "count_audio_token_failed", http.StatusInternalServerError)
 		}
@@ -92,6 +92,11 @@ func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 			return service.OpenAIErrorWrapperLocal(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
 	}
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()

 	// map model name
 	modelMapping := c.GetString("model_mapping")
@@ -122,19 +127,20 @@ func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}
-
 	statusCodeMappingStr := c.GetString("status_code_mapping")
+
+	var httpResp *http.Response
 	if resp != nil {
-		if resp.StatusCode != http.StatusOK {
-			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
-			openaiErr := service.RelayErrorHandler(resp)
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp)
 			// reset status code 重置状态码
 			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 			return openaiErr
 		}
 	}

-	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
 	if openaiErr != nil {
 		returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
 		// reset status code 重置状态码
@@ -142,7 +148,7 @@ func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return openaiErr
 	}

-	postConsumeQuota(c, relayInfo, audioRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, 0, false, "")
+	postConsumeQuota(c, relayInfo, audioRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, 0, false, "")

 	return nil
 }
--- a/relay/relay-image.go
+++ b/relay/relay-image.go
@@ -149,22 +149,24 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	requestBody = bytes.NewBuffer(jsonData)

 	statusCodeMappingStr := c.GetString("status_code_mapping")
+
 	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}
-
+	var httpResp *http.Response
 	if resp != nil {
-		relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
-		if resp.StatusCode != http.StatusOK {
-			openaiErr := service.RelayErrorHandler(resp)
+		httpResp = resp.(*http.Response)
+		relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(httpResp.Header.Get("Content-Type"), "text/event-stream")
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr := service.RelayErrorHandler(httpResp)
 			// reset status code 重置状态码
 			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 			return openaiErr
 		}
 	}

-	_, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	_, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
 	if openaiErr != nil {
 		// reset status code 重置状态码
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
--- a/relay/relay-mj.go
+++ b/relay/relay-mj.go
@@ -31,7 +31,7 @@ func RelayMidjourneyImage(c *gin.Context) {
 		})
 		return
 	}
-	resp, err := common.ProxiedHttpGet(midjourneyTask.ImageUrl, common.OutProxyUrl)
+	resp, err := http.Get(midjourneyTask.ImageUrl)
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{
 			"error": "http_get_image_failed",
@@ -112,7 +112,7 @@ func coverMidjourneyTaskDto(c *gin.Context, originTask *model.Midjourney) (midjo
 	midjourneyTask.FinishTime = originTask.FinishTime
 	midjourneyTask.ImageUrl = ""
 	if originTask.ImageUrl != "" && constant.MjForwardUrlEnabled {
-		midjourneyTask.ImageUrl = common.ServerAddress + "/mj/image/" + originTask.MjId
+		midjourneyTask.ImageUrl = constant.ServerAddress + "/mj/image/" + originTask.MjId
 		if originTask.Status != "SUCCESS" {
 			midjourneyTask.ImageUrl += "?rand=" + strconv.FormatInt(time.Now().UnixNano(), 10)
 		}
--- a/relay/relay-text.go
+++ b/relay/relay-text.go
@@ -64,7 +64,7 @@ func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo)
 	return textRequest, nil
 }

-func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
+func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {

 	relayInfo := relaycommon.GenRelayInfo(c)

@@ -131,7 +131,11 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	if openaiErr != nil {
 		return openaiErr
 	}
-
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
 	includeUsage := false
 	// 判断用户是否需要返回使用情况
 	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
@@ -180,30 +184,35 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	}

 	statusCodeMappingStr := c.GetString("status_code_mapping")
+	var httpResp *http.Response
 	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}

 	if resp != nil {
-		relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
-		if resp.StatusCode != http.StatusOK {
-			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
-			openaiErr := service.RelayErrorHandler(resp)
+		httpResp = resp.(*http.Response)
+		relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(httpResp.Header.Get("Content-Type"), "text/event-stream")
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp)
 			// reset status code 重置状态码
 			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 			return openaiErr
 		}
 	}

-	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
 	if openaiErr != nil {
-		returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
 		// reset status code 重置状态码
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, textRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+
+	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
+		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	} else {
+		postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	}
 	return nil
 }

@@ -215,15 +224,6 @@ func getPromptTokens(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.Re
 		promptTokens, err = service.CountTokenChatRequest(*textRequest, textRequest.Model)
 	case relayconstant.RelayModeCompletions:
 		promptTokens, err = service.CountTokenInput(textRequest.Prompt, textRequest.Model)
-		prompts := textRequest.Prompt
-		switch v := prompts.(type) {
-		case string:
-			prompts = v + textRequest.Suffix
-		case []string:
-			prompts = append(v, textRequest.Suffix)
-		}
-
-		promptTokens, err = service.CountTokenInput(prompts, textRequest.Model)
 	case relayconstant.RelayModeModerations:
 		promptTokens, err = service.CountTokenInput(textRequest.Input, textRequest.Model)
 	case relayconstant.RelayModeEmbeddings:
@@ -372,8 +372,9 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 	if strings.HasPrefix(logModel, "gpt-4-gizmo") {
 		logModel = "gpt-4-gizmo-*"
 		logContent += fmt.Sprintf("，模型 %s", modelName)
-	} else if strings.HasPrefix(logModel, "g-") {
-		logModel = "g-*"
+	}
+	if strings.HasPrefix(logModel, "gpt-4o-gizmo") {
+		logModel = "gpt-4o-gizmo-*"
 		logContent += fmt.Sprintf("，模型 %s", modelName)
 	}
 	if extraContent != "" {
--- a/relay/relay_adaptor.go
+++ b/relay/relay_adaptor.go
@@ -12,6 +12,7 @@ import (
 	"one-api/relay/channel/dify"
 	"one-api/relay/channel/gemini"
 	"one-api/relay/channel/jina"
+	"one-api/relay/channel/mistral"
 	"one-api/relay/channel/ollama"
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
@@ -68,6 +69,8 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &siliconflow.Adaptor{}
 	case constant.APITypeVertexAi:
 		return &vertex.Adaptor{}
+	case constant.APITypeMistral:
+		return &mistral.Adaptor{}
 	}
 	return nil
 }
--- a/relay/relay_rerank.go
+++ b/relay/relay_rerank.go
@@ -23,7 +23,7 @@ func getRerankPromptToken(rerankRequest dto.RerankRequest) int {
 	return token
 }

-func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
+func RerankHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	relayInfo := relaycommon.GenRelayInfo(c)

 	var rerankRequest *dto.RerankRequest
@@ -79,6 +79,12 @@ func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	if openaiErr != nil {
 		return openaiErr
 	}
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
+
 	adaptor := GetAdaptor(relayInfo.ApiType)
 	if adaptor == nil {
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
@@ -99,23 +105,24 @@ func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}
+
+	var httpResp *http.Response
 	if resp != nil {
-		if resp.StatusCode != http.StatusOK {
-			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
-			openaiErr := service.RelayErrorHandler(resp)
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp)
 			// reset status code 重置状态码
 			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 			return openaiErr
 		}
 	}

-	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
 	if openaiErr != nil {
-		returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
 		// reset status code 重置状态码
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
+	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
 	return nil
 }
--- a/relay/websocket.go
+++ b/relay/websocket.go
@@ -0,0 +1,159 @@
+package relay
+
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+)
+
+//func getAndValidateWssRequest(c *gin.Context, ws *websocket.Conn) (*dto.RealtimeEvent, error) {
+//	_, p, err := ws.ReadMessage()
+//	if err != nil {
+//		return nil, err
+//	}
+//	realtimeEvent := &dto.RealtimeEvent{}
+//	err = json.Unmarshal(p, realtimeEvent)
+//	if err != nil {
+//		return nil, err
+//	}
+//	// save the original request
+//	if realtimeEvent.Session == nil {
+//		return nil, errors.New("session object is nil")
+//	}
+//	c.Set("first_wss_request", p)
+//	return realtimeEvent, nil
+//}
+
+func WssHelper(c *gin.Context, ws *websocket.Conn) (openaiErr *dto.OpenAIErrorWithStatusCode) {
+	relayInfo := relaycommon.GenRelayInfoWs(c, ws)
+
+	// get & validate textRequest 获取并验证文本请求
+	//realtimeEvent, err := getAndValidateWssRequest(c, ws)
+	//if err != nil {
+	//	common.LogError(c, fmt.Sprintf("getAndValidateWssRequest failed: %s", err.Error()))
+	//	return service.OpenAIErrorWrapperLocal(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.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+		}
+		if modelMap[relayInfo.OriginModelName] != "" {
+			relayInfo.UpstreamModelName = modelMap[relayInfo.OriginModelName]
+			// set upstream model name
+			//isModelMapped = true
+		}
+	}
+	//relayInfo.UpstreamModelName = textRequest.Model
+	modelPrice, getModelPriceSuccess := common.GetModelPrice(relayInfo.UpstreamModelName, false)
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+
+	var preConsumedQuota int
+	var ratio float64
+	var modelRatio float64
+	//err := service.SensitiveWordsCheck(textRequest)
+
+	//if constant.ShouldCheckPromptSensitive() {
+	//	err = checkRequestSensitive(textRequest, relayInfo)
+	//	if err != nil {
+	//		return service.OpenAIErrorWrapperLocal(err, "sensitive_words_detected", http.StatusBadRequest)
+	//	}
+	//}
+
+	//promptTokens, err := getWssPromptTokens(realtimeEvent, relayInfo)
+	//// count messages token error 计算promptTokens错误
+	//if err != nil {
+	//	return service.OpenAIErrorWrapper(err, "count_token_messages_failed", http.StatusInternalServerError)
+	//}
+	//
+	if !getModelPriceSuccess {
+		preConsumedTokens := common.PreConsumedQuota
+		//if realtimeEvent.Session.MaxResponseOutputTokens != 0 {
+		//	preConsumedTokens = promptTokens + int(realtimeEvent.Session.MaxResponseOutputTokens)
+		//}
+		modelRatio = common.GetModelRatio(relayInfo.UpstreamModelName)
+		ratio = modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+		relayInfo.UsePrice = true
+	}
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
+
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo)
+	//var requestBody io.Reader
+	//firstWssRequest, _ := c.Get("first_wss_request")
+	//requestBody = bytes.NewBuffer(firstWssRequest.([]byte))
+
+	statusCodeMappingStr := c.GetString("status_code_mapping")
+	resp, err := adaptor.DoRequest(c, relayInfo, nil)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+	}
+
+	if resp != nil {
+		relayInfo.TargetWs = resp.(*websocket.Conn)
+		defer relayInfo.TargetWs.Close()
+	}
+
+	usage, openaiErr := adaptor.DoResponse(c, nil, relayInfo)
+	if openaiErr != nil {
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
+	service.PostWssConsumeQuota(c, relayInfo, relayInfo.UpstreamModelName, usage.(*dto.RealtimeUsage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	return nil
+}
+
+//func getWssPromptTokens(textRequest *dto.RealtimeEvent, info *relaycommon.RelayInfo) (int, error) {
+//	var promptTokens int
+//	var err error
+//	switch info.RelayMode {
+//	default:
+//		promptTokens, err = service.CountTokenRealtime(*textRequest, info.UpstreamModelName)
+//	}
+//	info.PromptTokens = promptTokens
+//	return promptTokens, err
+//}
+
+//func checkWssRequestSensitive(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) error {
+//	var err error
+//	switch info.RelayMode {
+//	case relayconstant.RelayModeChatCompletions:
+//		err = service.CheckSensitiveMessages(textRequest.Messages)
+//	case relayconstant.RelayModeCompletions:
+//		err = service.CheckSensitiveInput(textRequest.Prompt)
+//	case relayconstant.RelayModeModerations:
+//		err = service.CheckSensitiveInput(textRequest.Input)
+//	case relayconstant.RelayModeEmbeddings:
+//		err = service.CheckSensitiveInput(textRequest.Input)
+//	}
+//	return err
+//}
--- a/router/api-router.go
+++ b/router/api-router.go
@@ -18,14 +18,13 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/status/test", middleware.AdminAuth(), controller.TestStatus)
 		apiRouter.GET("/notice", controller.GetNotice)
 		apiRouter.GET("/about", controller.GetAbout)
-		apiRouter.GET("/midjourney", controller.GetMidjourney)
+		//apiRouter.GET("/midjourney", controller.GetMidjourney)
 		apiRouter.GET("/home_page_content", controller.GetHomePageContent)
 		apiRouter.GET("/pricing", middleware.TryUserAuth(), controller.GetPricing)
 		apiRouter.GET("/verification", middleware.CriticalRateLimit(), middleware.TurnstileCheck(), controller.SendEmailVerification)
 		apiRouter.GET("/reset_password", middleware.CriticalRateLimit(), middleware.TurnstileCheck(), controller.SendPasswordResetEmail)
 		apiRouter.POST("/user/reset", middleware.CriticalRateLimit(), controller.ResetPassword)
 		apiRouter.GET("/oauth/github", middleware.CriticalRateLimit(), controller.GitHubOAuth)
-		apiRouter.GET("/oauth/linuxdo", middleware.CriticalRateLimit(), controller.LinuxDoOAuth)
 		apiRouter.GET("/oauth/state", middleware.CriticalRateLimit(), controller.GenerateOAuthCode)
 		apiRouter.GET("/oauth/wechat", middleware.CriticalRateLimit(), controller.WeChatAuth)
 		apiRouter.GET("/oauth/wechat/bind", middleware.CriticalRateLimit(), middleware.UserAuth(), controller.WeChatBind)
@@ -33,14 +32,13 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/oauth/telegram/login", middleware.CriticalRateLimit(), controller.TelegramLogin)
 		apiRouter.GET("/oauth/telegram/bind", middleware.CriticalRateLimit(), middleware.UserAuth(), controller.TelegramBind)

-		apiRouter.POST("/stripe/webhook", controller.StripeWebhook)
-
 		userRoute := apiRouter.Group("/user")
 		{
 			userRoute.POST("/register", middleware.CriticalRateLimit(), middleware.TurnstileCheck(), controller.Register)
 			userRoute.POST("/login", middleware.CriticalRateLimit(), middleware.TurnstileCheck(), controller.Login)
 			//userRoute.POST("/tokenlog", middleware.CriticalRateLimit(), controller.TokenLog)
 			userRoute.GET("/logout", controller.Logout)
+			userRoute.GET("/epay/notify", controller.EpayNotify)
 			userRoute.GET("/groups", controller.GetUserGroups)

 			selfRoute := userRoute.Group("/")
@@ -53,8 +51,8 @@ func SetApiRouter(router *gin.Engine) {
 				selfRoute.DELETE("/self", controller.DeleteSelf)
 				selfRoute.GET("/token", controller.GenerateAccessToken)
 				selfRoute.GET("/aff", controller.GetAffCode)
-				selfRoute.POST("/topup", middleware.CriticalRateLimit(), controller.TopUp)
-				selfRoute.POST("/pay", middleware.CriticalRateLimit(), controller.RequestPayLink)
+				selfRoute.POST("/topup", controller.TopUp)
+				selfRoute.POST("/pay", controller.RequestEpay)
 				selfRoute.POST("/amount", controller.RequestAmount)
 				selfRoute.POST("/aff_transfer", controller.TransferAffQuota)
 			}
@@ -68,7 +66,7 @@ func SetApiRouter(router *gin.Engine) {
 				adminRoute.POST("/", controller.CreateUser)
 				adminRoute.POST("/manage", controller.ManageUser)
 				adminRoute.PUT("/", controller.UpdateUser)
-				adminRoute.DELETE("/:id", controller.HardDeleteUser)
+				adminRoute.DELETE("/:id", controller.DeleteUser)
 			}
 		}
 		optionRoute := apiRouter.Group("/option")
--- a/router/relay-router.go
+++ b/router/relay-router.go
@@ -22,32 +22,41 @@ func SetRelayRouter(router *gin.Engine) {
 		playgroundRouter.POST("/chat/completions", controller.Playground)
 	}
 	relayV1Router := router.Group("/v1")
-	relayV1Router.Use(middleware.TokenAuth(), middleware.Distribute())
+	relayV1Router.Use(middleware.TokenAuth())
 	{
-		relayV1Router.POST("/completions", controller.Relay)
-		relayV1Router.POST("/chat/completions", controller.Relay)
-		relayV1Router.POST("/edits", controller.Relay)
-		relayV1Router.POST("/images/generations", controller.Relay)
-		relayV1Router.POST("/images/edits", controller.RelayNotImplemented)
-		relayV1Router.POST("/images/variations", controller.RelayNotImplemented)
-		relayV1Router.POST("/embeddings", controller.Relay)
-		relayV1Router.POST("/engines/:model/embeddings", controller.Relay)
-		relayV1Router.POST("/audio/transcriptions", controller.Relay)
-		relayV1Router.POST("/audio/translations", controller.Relay)
-		relayV1Router.POST("/audio/speech", controller.Relay)
-		relayV1Router.GET("/files", controller.RelayNotImplemented)
-		relayV1Router.POST("/files", controller.RelayNotImplemented)
-		relayV1Router.DELETE("/files/:id", controller.RelayNotImplemented)
-		relayV1Router.GET("/files/:id", controller.RelayNotImplemented)
-		relayV1Router.GET("/files/:id/content", controller.RelayNotImplemented)
-		relayV1Router.POST("/fine-tunes", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes/:id", controller.RelayNotImplemented)
-		relayV1Router.POST("/fine-tunes/:id/cancel", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
-		relayV1Router.DELETE("/models/:model", controller.RelayNotImplemented)
-		relayV1Router.POST("/moderations", controller.Relay)
-		relayV1Router.POST("/rerank", controller.Relay)
+		// WebSocket 路由
+		wsRouter := relayV1Router.Group("")
+		wsRouter.Use(middleware.Distribute())
+		wsRouter.GET("/realtime", controller.WssRelay)
+	}
+	{
+		//http router
+		httpRouter := relayV1Router.Group("")
+		httpRouter.Use(middleware.Distribute())
+		httpRouter.POST("/completions", controller.Relay)
+		httpRouter.POST("/chat/completions", controller.Relay)
+		httpRouter.POST("/edits", controller.Relay)
+		httpRouter.POST("/images/generations", controller.Relay)
+		httpRouter.POST("/images/edits", controller.RelayNotImplemented)
+		httpRouter.POST("/images/variations", controller.RelayNotImplemented)
+		httpRouter.POST("/embeddings", controller.Relay)
+		httpRouter.POST("/engines/:model/embeddings", controller.Relay)
+		httpRouter.POST("/audio/transcriptions", controller.Relay)
+		httpRouter.POST("/audio/translations", controller.Relay)
+		httpRouter.POST("/audio/speech", controller.Relay)
+		httpRouter.GET("/files", controller.RelayNotImplemented)
+		httpRouter.POST("/files", controller.RelayNotImplemented)
+		httpRouter.DELETE("/files/:id", controller.RelayNotImplemented)
+		httpRouter.GET("/files/:id", controller.RelayNotImplemented)
+		httpRouter.GET("/files/:id/content", controller.RelayNotImplemented)
+		httpRouter.POST("/fine-tunes", controller.RelayNotImplemented)
+		httpRouter.GET("/fine-tunes", controller.RelayNotImplemented)
+		httpRouter.GET("/fine-tunes/:id", controller.RelayNotImplemented)
+		httpRouter.POST("/fine-tunes/:id/cancel", controller.RelayNotImplemented)
+		httpRouter.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
+		httpRouter.DELETE("/models/:model", controller.RelayNotImplemented)
+		httpRouter.POST("/moderations", controller.Relay)
+		httpRouter.POST("/rerank", controller.Relay)
 	}

 	relayMjRouter := router.Group("/mj")
--- a/service/audio.go
+++ b/service/audio.go
@@ -0,0 +1,31 @@
+package service
+
+import (
+	"encoding/base64"
+	"fmt"
+)
+
+func parseAudio(audioBase64 string, format string) (duration float64, err error) {
+	audioData, err := base64.StdEncoding.DecodeString(audioBase64)
+	if err != nil {
+		return 0, fmt.Errorf("base64 decode error: %v", err)
+	}
+
+	var samplesCount int
+	var sampleRate int
+
+	switch format {
+	case "pcm16":
+		samplesCount = len(audioData) / 2 // 16位 = 2字节每样本
+		sampleRate = 24000                // 24kHz
+	case "g711_ulaw", "g711_alaw":
+		samplesCount = len(audioData) // 8位 = 1字节每样本
+		sampleRate = 8000             // 8kHz
+	default:
+		samplesCount = len(audioData) // 8位 = 1字节每样本
+		sampleRate = 8000             // 8kHz
+	}
+
+	duration = float64(samplesCount) / float64(sampleRate)
+	return duration, nil
+}
--- a/service/epay.go
+++ b/service/epay.go
@@ -0,0 +1,12 @@
+package service
+
+import (
+	"one-api/constant"
+)
+
+func GetCallbackAddress() string {
+	if constant.CustomCallbackAddress == "" {
+		return constant.ServerAddress
+	}
+	return constant.CustomCallbackAddress
+}
--- a/service/image.go
+++ b/service/image.go
@@ -1,4 +1,4 @@
-package common
+package service

 import (
 	"bytes"
@@ -8,6 +8,7 @@ import (
 	"golang.org/x/image/webp"
 	"image"
 	"io"
+	"one-api/common"
 	"strings"
 )

@@ -30,24 +31,9 @@ func DecodeBase64ImageData(base64String string) (image.Config, string, string, e
 	return config, format, base64String, err
 }

-func IsImageUrl(url string) (bool, error) {
-	resp, err := ProxiedHttpHead(url, OutProxyUrl)
-	if err != nil {
-		return false, err
-	}
-	if !strings.HasPrefix(resp.Header.Get("Content-Type"), "image/") {
-		return false, nil
-	}
-	return true, nil
-}
-
 // GetImageFromUrl 获取图片的类型和base64编码的数据
 func GetImageFromUrl(url string) (mimeType string, data string, err error) {
-	isImage, err := IsImageUrl(url)
-	if !isImage {
-		return
-	}
-	resp, err := ProxiedHttpGet(url, OutProxyUrl)
+	resp, err := DoImageRequest(url)
 	if err != nil {
 		return
 	}
@@ -66,9 +52,9 @@ func GetImageFromUrl(url string) (mimeType string, data string, err error) {
 }

 func DecodeUrlImageData(imageUrl string) (image.Config, string, error) {
-	response, err := ProxiedHttpGet(imageUrl, OutProxyUrl)
+	response, err := DoImageRequest(imageUrl)
 	if err != nil {
-		SysLog(fmt.Sprintf("fail to get image from url: %s", err.Error()))
+		common.SysLog(fmt.Sprintf("fail to get image from url: %s", err.Error()))
 		return image.Config{}, "", err
 	}
 	defer response.Body.Close()
@@ -80,7 +66,7 @@ func DecodeUrlImageData(imageUrl string) (image.Config, string, error) {

 	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))
+		common.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)))
@@ -106,11 +92,11 @@ func getImageConfig(reader io.Reader) (image.Config, string, error) {
 	config, format, err := image.DecodeConfig(reader)
 	if err != nil {
 		err = errors.New(fmt.Sprintf("fail to decode image config(gif, jpg, png): %s", err.Error()))
-		SysLog(err.Error())
+		common.SysLog(err.Error())
 		config, err = webp.DecodeConfig(reader)
 		if err != nil {
 			err = errors.New(fmt.Sprintf("fail to decode image config(webp): %s", err.Error()))
-			SysLog(err.Error())
+			common.SysLog(err.Error())
 		}
 		format = "webp"
 	}
--- a/service/log.go
+++ b/service/log.go
@@ -2,6 +2,7 @@ package service

 import (
 	"github.com/gin-gonic/gin"
+	"one-api/dto"
 	relaycommon "one-api/relay/common"
 )

@@ -17,3 +18,27 @@ func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, m
 	other["admin_info"] = adminInfo
 	return other
 }
+
+func GenerateWssOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice float64) map[string]interface{} {
+	info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, modelPrice)
+	info["ws"] = true
+	info["audio_input"] = usage.InputTokenDetails.AudioTokens
+	info["audio_output"] = usage.OutputTokenDetails.AudioTokens
+	info["text_input"] = usage.InputTokenDetails.TextTokens
+	info["text_output"] = usage.OutputTokenDetails.TextTokens
+	info["audio_ratio"] = audioRatio
+	info["audio_completion_ratio"] = audioCompletionRatio
+	return info
+}
+
+func GenerateAudioOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice float64) map[string]interface{} {
+	info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, modelPrice)
+	info["audio"] = true
+	info["audio_input"] = usage.PromptTokensDetails.AudioTokens
+	info["audio_output"] = usage.CompletionTokenDetails.AudioTokens
+	info["text_input"] = usage.PromptTokensDetails.TextTokens
+	info["text_output"] = usage.CompletionTokenDetails.TextTokens
+	info["audio_ratio"] = audioRatio
+	info["audio_completion_ratio"] = audioCompletionRatio
+	return info
+}
--- a/service/quota.go
+++ b/service/quota.go
@@ -0,0 +1,201 @@
+package service
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"math"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/model"
+	relaycommon "one-api/relay/common"
+	"time"
+)
+
+func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage) error {
+	if relayInfo.UsePrice {
+		return nil
+	}
+	userQuota, err := model.GetUserQuota(relayInfo.UserId)
+	if err != nil {
+		return err
+	}
+	modelName := relayInfo.UpstreamModelName
+	textInputTokens := usage.InputTokenDetails.TextTokens
+	textOutTokens := usage.OutputTokenDetails.TextTokens
+	audioInputTokens := usage.InputTokenDetails.AudioTokens
+	audioOutTokens := usage.OutputTokenDetails.AudioTokens
+
+	completionRatio := common.GetCompletionRatio(modelName)
+	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+	modelRatio := common.GetModelRatio(modelName)
+
+	ratio := groupRatio * modelRatio
+
+	quota := textInputTokens + int(math.Round(float64(textOutTokens)*completionRatio))
+	quota += int(math.Round(float64(audioInputTokens)*audioRatio)) + int(math.Round(float64(audioOutTokens)*audioRatio*audioCompletionRatio))
+
+	quota = int(math.Round(float64(quota) * ratio))
+	if ratio != 0 && quota <= 0 {
+		quota = 1
+	}
+
+	if userQuota < quota {
+		return errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
+	}
+
+	err = model.PostConsumeTokenQuota(relayInfo, 0, quota, 0, false)
+	if err != nil {
+		return err
+	}
+	common.LogInfo(ctx, "realtime streaming consume quota success, quota: "+fmt.Sprintf("%d", quota))
+	err = model.CacheUpdateUserQuota(relayInfo.UserId)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
+	usage *dto.RealtimeUsage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
+	groupRatio float64,
+	modelPrice float64, usePrice bool, extraContent string) {
+
+	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
+	textInputTokens := usage.InputTokenDetails.TextTokens
+	textOutTokens := usage.OutputTokenDetails.TextTokens
+
+	audioInputTokens := usage.InputTokenDetails.AudioTokens
+	audioOutTokens := usage.OutputTokenDetails.AudioTokens
+
+	tokenName := ctx.GetString("token_name")
+	completionRatio := common.GetCompletionRatio(modelName)
+	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
+
+	quota := 0
+	if !usePrice {
+		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
+		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
+		quota = int(math.Round(float64(quota) * ratio))
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	totalTokens := usage.TotalTokens
+	var logContent string
+	if !usePrice {
+		logContent = fmt.Sprintf("模型倍率 %.2f，补全倍率 %.2f，音频倍率 %.2f，音频补全倍率 %.2f，分组倍率 %.2f", modelRatio, completionRatio, audioRatio, audioCompletionRatio, 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, modelName, preConsumedQuota))
+	} else {
+		//if sensitiveResp != nil {
+		//	logContent += fmt.Sprintf("，敏感词：%s", strings.Join(sensitiveResp.SensitiveWords, ", "))
+		//}
+		//quotaDelta := quota - preConsumedQuota
+		//if quotaDelta != 0 {
+		//	err := model.PostConsumeTokenQuota(relayInfo, 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 := modelName
+	if extraContent != "" {
+		logContent += ", " + extraContent
+	}
+	other := GenerateWssOtherInfo(ctx, relayInfo, usage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice)
+	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, usage.InputTokens, usage.OutputTokens, logModel,
+		tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
+}
+
+func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
+	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
+	groupRatio float64,
+	modelPrice float64, usePrice bool, extraContent string) {
+
+	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
+	textInputTokens := usage.PromptTokensDetails.TextTokens
+	textOutTokens := usage.CompletionTokenDetails.TextTokens
+
+	audioInputTokens := usage.PromptTokensDetails.AudioTokens
+	audioOutTokens := usage.CompletionTokenDetails.AudioTokens
+
+	tokenName := ctx.GetString("token_name")
+	completionRatio := common.GetCompletionRatio(relayInfo.UpstreamModelName)
+	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName)
+
+	quota := 0
+	if !usePrice {
+		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
+		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
+		quota = int(math.Round(float64(quota) * ratio))
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	totalTokens := usage.TotalTokens
+	var logContent string
+	if !usePrice {
+		logContent = fmt.Sprintf("模型倍率 %.2f，补全倍率 %.2f，音频倍率 %.2f，音频补全倍率 %.2f，分组倍率 %.2f", modelRatio, completionRatio, audioRatio, audioCompletionRatio, 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, relayInfo.UpstreamModelName, preConsumedQuota))
+	} else {
+		quotaDelta := quota - preConsumedQuota
+		if quotaDelta != 0 {
+			err := model.PostConsumeTokenQuota(relayInfo, 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 := relayInfo.UpstreamModelName
+	if extraContent != "" {
+		logContent += ", " + extraContent
+	}
+	other := GenerateAudioOtherInfo(ctx, relayInfo, usage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice)
+	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, usage.PromptTokens, usage.CompletionTokens, logModel,
+		tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
+}
--- a/service/relay.go
+++ b/service/relay.go
@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
@@ -42,11 +43,47 @@ func Done(c *gin.Context) {
 	_ = StringData(c, "[DONE]")
 }

+func WssString(c *gin.Context, ws *websocket.Conn, str string) error {
+	if ws == nil {
+		common.LogError(c, "websocket connection is nil")
+		return errors.New("websocket connection is nil")
+	}
+	//common.LogInfo(c, fmt.Sprintf("sending message: %s", str))
+	return ws.WriteMessage(1, []byte(str))
+}
+
+func WssObject(c *gin.Context, ws *websocket.Conn, object interface{}) error {
+	jsonData, err := json.Marshal(object)
+	if err != nil {
+		return fmt.Errorf("error marshalling object: %w", err)
+	}
+	if ws == nil {
+		common.LogError(c, "websocket connection is nil")
+		return errors.New("websocket connection is nil")
+	}
+	//common.LogInfo(c, fmt.Sprintf("sending message: %s", jsonData))
+	return ws.WriteMessage(1, jsonData)
+}
+
+func WssError(c *gin.Context, ws *websocket.Conn, openaiError dto.OpenAIError) {
+	errorObj := &dto.RealtimeEvent{
+		Type:    "error",
+		EventId: GetLocalRealtimeID(c),
+		Error:   &openaiError,
+	}
+	_ = WssObject(c, ws, errorObj)
+}
+
 func GetResponseID(c *gin.Context) string {
-	logID := c.GetString("X-Oneapi-Request-Id")
+	logID := c.GetString(common.RequestIdKey)
 	return fmt.Sprintf("chatcmpl-%s", logID)
 }

+func GetLocalRealtimeID(c *gin.Context) string {
+	logID := c.GetString(common.RequestIdKey)
+	return fmt.Sprintf("evt_%s", logID)
+}
+
 func GenerateStopResponse(id string, createAt int64, model string, finishReason string) *dto.ChatCompletionsStreamResponse {
 	return &dto.ChatCompletionsStreamResponse{
 		Id:                id,
--- a/service/token_counter.go
+++ b/service/token_counter.go
@@ -11,6 +11,7 @@ import (
 	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"strings"
 	"unicode/utf8"
 )
@@ -18,6 +19,7 @@ import (
 // tokenEncoderMap won't grow after initialization
 var tokenEncoderMap = map[string]*tiktoken.Tiktoken{}
 var defaultTokenEncoder *tiktoken.Tiktoken
+var cl200kTokenEncoder *tiktoken.Tiktoken

 func InitTokenEncoders() {
 	common.SysLog("initializing token encoders")
@@ -30,22 +32,19 @@ func InitTokenEncoders() {
 	if err != nil {
 		common.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
 	}
-
-	gpt4oTokenEncoder, err := tiktoken.EncodingForModel("gpt-4o")
+	cl200kTokenEncoder, err = tiktoken.EncodingForModel("gpt-4o")
 	if err != nil {
 		common.FatalLog(fmt.Sprintf("failed to get gpt-4o token encoder: %s", err.Error()))
 	}
 	for model, _ := range common.GetDefaultModelRatioMap() {
 		if strings.HasPrefix(model, "gpt-3.5") {
 			tokenEncoderMap[model] = gpt35TokenEncoder
-		} else if strings.HasPrefix(model, "gpt-4o") {
-			tokenEncoderMap[model] = gpt4oTokenEncoder
-		} else if strings.HasPrefix(model, "chatgpt-4o") {
-			tokenEncoderMap[model] = gpt4oTokenEncoder
-		} else if "o1" == model || strings.HasPrefix(model, "o1") {
-			tokenEncoderMap[model] = gpt4oTokenEncoder
 		} else if strings.HasPrefix(model, "gpt-4") {
-			tokenEncoderMap[model] = gpt4TokenEncoder
+			if strings.HasPrefix(model, "gpt-4o") {
+				tokenEncoderMap[model] = cl200kTokenEncoder
+			} else {
+				tokenEncoderMap[model] = gpt4TokenEncoder
+			}
 		} else {
 			tokenEncoderMap[model] = nil
 		}
@@ -53,6 +52,13 @@ func InitTokenEncoders() {
 	common.SysLog("token encoders initialized")
 }

+func getModelDefaultTokenEncoder(model string) *tiktoken.Tiktoken {
+	if strings.HasPrefix(model, "gpt-4o") || strings.HasPrefix(model, "chatgpt-4o") {
+		return cl200kTokenEncoder
+	}
+	return defaultTokenEncoder
+}
+
 func getTokenEncoder(model string) *tiktoken.Tiktoken {
 	tokenEncoder, ok := tokenEncoderMap[model]
 	if ok && tokenEncoder != nil {
@@ -63,12 +69,13 @@ func getTokenEncoder(model string) *tiktoken.Tiktoken {
 		tokenEncoder, err := tiktoken.EncodingForModel(model)
 		if err != nil {
 			common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
-			tokenEncoder = defaultTokenEncoder
+			tokenEncoder = getModelDefaultTokenEncoder(model)
 		}
 		tokenEncoderMap[model] = tokenEncoder
 		return tokenEncoder
 	}
-	return defaultTokenEncoder
+	// 如果model不在tokenEncoderMap中，直接返回默认的tokenEncoder
+	return getModelDefaultTokenEncoder(model)
 }

 func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
@@ -105,11 +112,10 @@ func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (in
 	var err error
 	var format string
 	if strings.HasPrefix(imageUrl.Url, "http") {
-		common.SysLog(fmt.Sprintf("downloading image: %s", imageUrl.Url))
-		config, format, err = common.DecodeUrlImageData(imageUrl.Url)
+		config, format, err = DecodeUrlImageData(imageUrl.Url)
 	} else {
 		common.SysLog(fmt.Sprintf("decoding image"))
-		config, format, _, err = common.DecodeBase64ImageData(imageUrl.Url)
+		config, format, _, err = DecodeBase64ImageData(imageUrl.Url)
 	}
 	if err != nil {
 		return 0, err
@@ -186,6 +192,72 @@ func CountTokenChatRequest(request dto.GeneralOpenAIRequest, model string) (int,
 	return tkm, nil
 }

+func CountTokenRealtime(info *relaycommon.RelayInfo, request dto.RealtimeEvent, model string) (int, int, error) {
+	audioToken := 0
+	textToken := 0
+	switch request.Type {
+	case dto.RealtimeEventTypeSessionUpdate:
+		if request.Session != nil {
+			msgTokens, err := CountTextToken(request.Session.Instructions, model)
+			if err != nil {
+				return 0, 0, err
+			}
+			textToken += msgTokens
+		}
+	case dto.RealtimeEventResponseAudioDelta:
+		// count audio token
+		atk, err := CountAudioTokenOutput(request.Delta, info.OutputAudioFormat)
+		if err != nil {
+			return 0, 0, fmt.Errorf("error counting audio token: %v", err)
+		}
+		audioToken += atk
+	case dto.RealtimeEventResponseAudioTranscriptionDelta, dto.RealtimeEventResponseFunctionCallArgumentsDelta:
+		// count text token
+		tkm, err := CountTextToken(request.Delta, model)
+		if err != nil {
+			return 0, 0, fmt.Errorf("error counting text token: %v", err)
+		}
+		textToken += tkm
+	case dto.RealtimeEventInputAudioBufferAppend:
+		// count audio token
+		atk, err := CountAudioTokenInput(request.Audio, info.InputAudioFormat)
+		if err != nil {
+			return 0, 0, fmt.Errorf("error counting audio token: %v", err)
+		}
+		audioToken += atk
+	case dto.RealtimeEventConversationItemCreated:
+		if request.Item != nil {
+			switch request.Item.Type {
+			case "message":
+				for _, content := range request.Item.Content {
+					if content.Type == "input_text" {
+						tokens, err := CountTextToken(content.Text, model)
+						if err != nil {
+							return 0, 0, err
+						}
+						textToken += tokens
+					}
+				}
+			}
+		}
+	case dto.RealtimeEventTypeResponseDone:
+		// count tools token
+		if !info.IsFirstRequest {
+			if info.RealtimeTools != nil && len(info.RealtimeTools) > 0 {
+				for _, tool := range info.RealtimeTools {
+					toolTokens, err := CountTokenInput(tool, model)
+					if err != nil {
+						return 0, 0, err
+					}
+					textToken += 8
+					textToken += toolTokens
+				}
+			}
+		}
+	}
+	return textToken, audioToken, nil
+}
+
 func CountTokenMessages(messages []dto.Message, model string, stream bool) (int, error) {
 	//recover when panic
 	tokenEncoder := getTokenEncoder(model)
@@ -218,7 +290,7 @@ func CountTokenMessages(messages []dto.Message, model string, stream bool) (int,
 			} else {
 				arrayContent := message.ParseContent()
 				for _, m := range arrayContent {
-					if m.Type == "image_url" {
+					if m.Type == dto.ContentTypeImageURL {
 						imageUrl := m.ImageUrl.(dto.MessageImageUrl)
 						imageTokenNum, err := getImageToken(&imageUrl, model, stream)
 						if err != nil {
@@ -226,6 +298,9 @@ func CountTokenMessages(messages []dto.Message, model string, stream bool) (int,
 						}
 						tokenNum += imageTokenNum
 						log.Printf("image token num: %d", imageTokenNum)
+					} else if m.Type == dto.ContentTypeInputAudio {
+						// TODO: 音频token数量计算
+						tokenNum += 100
 					} else {
 						tokenNum += getTokenNum(tokenEncoder, m.Text)
 					}
@@ -240,13 +315,13 @@ func CountTokenMessages(messages []dto.Message, model string, stream bool) (int,
 func CountTokenInput(input any, model string) (int, error) {
 	switch v := input.(type) {
 	case string:
-		return CountTokenText(v, model)
+		return CountTextToken(v, model)
 	case []string:
 		text := ""
 		for _, s := range v {
 			text += s
 		}
-		return CountTokenText(text, model)
+		return CountTextToken(text, model)
 	}
 	return CountTokenInput(fmt.Sprintf("%v", input), model)
 }
@@ -268,16 +343,44 @@ func CountTokenStreamChoices(messages []dto.ChatCompletionsStreamResponseChoice,
 	return tokens
 }

-func CountAudioToken(text string, model string) (int, error) {
+func CountTTSToken(text string, model string) (int, error) {
 	if strings.HasPrefix(model, "tts") {
 		return utf8.RuneCountInString(text), nil
 	} else {
-		return CountTokenText(text, model)
+		return CountTextToken(text, model)
 	}
 }

-// CountTokenText 统计文本的token数量，仅当文本包含敏感词，返回错误，同时返回token数量
-func CountTokenText(text string, model string) (int, error) {
+func CountAudioTokenInput(audioBase64 string, audioFormat string) (int, error) {
+	if audioBase64 == "" {
+		return 0, nil
+	}
+	duration, err := parseAudio(audioBase64, audioFormat)
+	if err != nil {
+		return 0, err
+	}
+	return int(duration / 60 * 100 / 0.06), nil
+}
+
+func CountAudioTokenOutput(audioBase64 string, audioFormat string) (int, error) {
+	if audioBase64 == "" {
+		return 0, nil
+	}
+	duration, err := parseAudio(audioBase64, audioFormat)
+	if err != nil {
+		return 0, err
+	}
+	return int(duration / 60 * 200 / 0.24), nil
+}
+
+//func CountAudioToken(sec float64, audioType string) {
+//	if audioType == "input" {
+//
+//	}
+//}
+
+// CountTextToken 统计文本的token数量，仅当文本包含敏感词，返回错误，同时返回token数量
+func CountTextToken(text string, model string) (int, error) {
 	var err error
 	tokenEncoder := getTokenEncoder(model)
 	return getTokenNum(tokenEncoder, text), err
--- a/service/usage_helpr.go
+++ b/service/usage_helpr.go
@@ -19,7 +19,7 @@ import (
 func ResponseText2Usage(responseText string, modeName string, promptTokens int) (*dto.Usage, error) {
 	usage := &dto.Usage{}
 	usage.PromptTokens = promptTokens
-	ctkm, err := CountTokenText(responseText, modeName)
+	ctkm, err := CountTextToken(responseText, modeName)
 	usage.CompletionTokens = ctkm
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	return usage, err
--- a/service/worker.go
+++ b/service/worker.go
@@ -0,0 +1,26 @@
+package service
+
+import (
+	"bytes"
+	"fmt"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"strings"
+)
+
+func DoImageRequest(originUrl string) (resp *http.Response, err error) {
+	if constant.EnableWorker() {
+		common.SysLog(fmt.Sprintf("downloading image from worker: %s", originUrl))
+		workerUrl := constant.WorkerUrl
+		if !strings.HasSuffix(workerUrl, "/") {
+			workerUrl += "/"
+		}
+		// post request to worker
+		data := []byte(`{"url":"` + originUrl + `","key":"` + constant.WorkerValidKey + `"}`)
+		return http.Post(constant.WorkerUrl, "application/json", bytes.NewBuffer(data))
+	} else {
+		common.SysLog(fmt.Sprintf("downloading image from origin: %s", originUrl))
+		return http.Get(originUrl)
+	}
+}
--- a/web/.gitignore
+++ b/web/.gitignore
@@ -10,7 +10,6 @@

 # production
 /build
-/dist

 # misc
 .DS_Store
@@ -22,4 +21,6 @@
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
-.idea/
+.idea
+package-lock.json
+yarn.lock
--- a/web/.prettierrc.mjs
+++ b/web/.prettierrc.mjs
@@ -1 +1 @@
-module.exports = require('@so1ve/prettier-config');
+module.exports = require("@so1ve/prettier-config");
--- a/web/package.json
+++ b/web/package.json
@@ -55,7 +55,7 @@
    "@vitejs/plugin-react": "^4.2.1",
    "prettier": "^3.0.0",
    "typescript": "4.4.2",
-    "vite": "^5.4.14"
+    "vite": "^5.2.0"
  },
  "prettier": {
    "singleQuote": true,
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
CalciumIon	97fdcd8e8f	feat: 完善audio计费	2024-11-07 16:12:09 +08:00
Calcium-Ion	be652fa3c2	Merge pull request #555 from utopeadia/main Continue fixing Ollama embedding return issue	2024-11-06 21:13:06 +08:00
CalciumIon	cbf0688b80	feat: update model ratio	2024-11-06 19:33:50 +08:00
HowieWood	2ffa4268fc	Continue fixing Ollama embedding return issue	2024-11-06 01:21:02 +00:00
Calcium-Ion	3037dfab5b	Merge pull request #552 from utopeadia/main Modify ollama embed return fields	2024-11-05 22:05:45 +08:00
CalciumIon	b40c2e1071	feat: 美化日志页面 (cherry picked from commit 90daa38d5bea7b158ebed9990f042f6bf8567eb3)	2024-11-05 20:45:01 +08:00
Xyfacai	afc1e92ed0	fix: log table unknown ws prop error	2024-11-05 20:20:19 +08:00
1808837298@qq.com	ee04dbd9dd	feat: 日志详情完善 (cherry picked from commit ec79110c99e9b4c076c5f7b8285e535b9c5052db)	2024-11-05 20:19:58 +08:00
HowieWood	5253a0e7b2	Modify ollama embed return fields	2024-11-05 20:12:51 +08:00
CalciumIon	e5588fc1ee	Update README.md	2024-11-05 19:48:03 +08:00
Calcium-Ion	a859ff5985	Merge pull request #551 from Calcium-Ion/realtime feat: support openai realtime api	2024-11-05 19:45:43 +08:00
CalciumIon	0a80231e18	chore: 删除无用日志	2024-11-05 19:41:38 +08:00
CalciumIon	7b1ff41e4c	fix: mistral adaptor	2024-11-05 19:32:51 +08:00
1808837298@qq.com	4e0c522cd0	fix: realtime计费 (cherry picked from commit fdfea8726c6d86d3844af1ac18d7b3df908f26a7)	2024-11-05 19:29:06 +08:00
1808837298@qq.com	f08f7ae940	fix: channel test (cherry picked from commit 052bdab1c45b3a4ba5f079afc763f54e751b1cd7)	2024-11-05 19:28:58 +08:00
Xyfacai	be64408a25	fix(realtime): 修复ws 握手失败、计费问题 (cherry picked from commit 618dffc43fd5a5f4065944db87761f9ee18e44d3)	2024-11-05 19:28:46 +08:00
Xyfacai	d596699250	refactor: realtime log (cherry picked from commit fd24dc467bfc360008b313220e607f0176ee7aa3)	2024-11-05 19:28:09 +08:00
Xyfacai	f0907bf60a	fix: 部分情况缺少返回预扣 (cherry picked from commit 96373455521a38095706bd81c57f9a18557d9c2e)	2024-11-05 19:28:08 +08:00
1808837298@qq.com	e5c05d77b7	feat: realtime pre consume (cherry picked from commit 273d154e1640bae26b7caedddf1685e9ff21ab74)	2024-11-05 19:28:06 +08:00
1808837298@qq.com	24b3ed50d7	feat: realtime pre consume (cherry picked from commit d87917f8f6eb9d2e144a9f840d6d91767ea2eb69)	2024-11-05 19:28:03 +08:00
1808837298@qq.com	8de79382f0	feat: azure realtime (cherry picked from commit 75ff3d98f06103dc2df1f8817bd3fcbf433e0f20)	2024-11-05 19:27:55 +08:00
1808837298@qq.com	74f9006b40	feat: realtime (cherry picked from commit d4966246e68dbdcdab45ec5c5141362834d74425)	2024-11-05 19:27:47 +08:00
1808837298@qq.com	33af069fae	feat: realtime (cherry picked from commit a5529df3e1a4c08a120e8c05203a7d885b0fe8d8)	2024-11-05 19:24:14 +08:00
1808837298@qq.com	e3c85572d4	Update dto (cherry picked from commit 030187ff75c64c40017cda2fa98ef2b3c01f0bd5)	2024-11-05 19:23:56 +08:00
CalciumIon	4b48e490fa	feat: 添加Mistral渠道 (close #546 )	2024-11-05 17:11:33 +08:00
CalciumIon	3e2ae29ba0	fix: 修复聊天环境变量替换不完全 (close #542 )	2024-11-05 16:02:10 +08:00
CalciumIon	fe0ed128c6	chore: update model ratio	2024-11-05 15:58:22 +08:00
Calcium-Ion	3785e9d754	Merge pull request #549 from HynoR/main chore: 更新最新haiku模型倍率	2024-11-05 14:58:55 +08:00
HynoR	902a66b60f	Sync Latest Claude Model	2024-11-05 10:17:11 +08:00
Calcium-Ion	aaf3f09eec	Merge pull request #548 from utopeadia/main ollama /api/embeddings is deprecated, use /api/embed.	2024-11-04 22:21:52 +08:00
HowieWood	e523555844	/api/embeddings is deprecated, use /api/embed. /api/embeddings is deprecated, use /api/embed.	2024-11-04 22:03:41 +08:00
CalciumIon	139a104b26	feat: support gpt-4o-audio-preview	2024-11-04 15:27:12 +08:00