Merge branch 'main' into customer-function

common/blacklist/main.go

@@ -0,0 +1,29 @@
+package blacklist
+
+import (
+	"fmt"
+	"sync"
+)
+
+var blackList sync.Map
+
+func init() {
+	blackList = sync.Map{}
+}
+
+func userId2Key(id int) string {
+	return fmt.Sprintf("userid_%d", id)
+}
+
+func BanUser(id int) {
+	blackList.Store(userId2Key(id), true)
+}
+
+func UnbanUser(id int) {
+	blackList.Delete(userId2Key(id))
+}
+
+func IsUserBanned(id int) bool {
+	_, ok := blackList.Load(userId2Key(id))
+	return ok
+}

common/config/config.go

@@ -1,7 +1,7 @@
 package config
 
 import (
-	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/env"
 	"os"
 	"strconv"
 	"sync"
@@ -52,6 +52,7 @@ var EmailDomainWhitelist = []string{
 }
 
 var DebugEnabled = os.Getenv("DEBUG") == "true"
+var DebugSQLEnabled = os.Getenv("DEBUG_SQL") == "true"
 var MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
 
 var LogConsumeEnabled = true
@@ -69,17 +70,20 @@ var WeChatServerAddress = ""
 var WeChatServerToken = ""
 var WeChatAccountQRCodeImageURL = ""
 
+var MessagePusherAddress = ""
+var MessagePusherToken = ""
+
 var TurnstileSiteKey = ""
 var TurnstileSecretKey = ""
 
-var QuotaForNewUser = 0
-var QuotaForInviter = 0
-var QuotaForInvitee = 0
+var QuotaForNewUser int64 = 0
+var QuotaForInviter int64 = 0
+var QuotaForInvitee int64 = 0
 var ChannelDisableThreshold = 5.0
 var AutomaticDisableChannelEnabled = false
 var AutomaticEnableChannelEnabled = false
-var QuotaRemindThreshold = 1000
-var PreConsumedQuota = 500
+var QuotaRemindThreshold int64 = 1000
+var PreConsumedQuota int64 = 500
 var ApproximateTokenEnabled = false
 var RetryTimes = 0
 
@@ -90,28 +94,29 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = helper.GetOrDefaultEnvInt("SYNC_FREQUENCY", 10*60) // unit is second
+var SyncFrequency = env.Int("SYNC_FREQUENCY", 10*60) // unit is second
 
 var BatchUpdateEnabled = false
-var BatchUpdateInterval = helper.GetOrDefaultEnvInt("BATCH_UPDATE_INTERVAL", 5)
+var BatchUpdateInterval = env.Int("BATCH_UPDATE_INTERVAL", 5)
 
-var RelayTimeout = helper.GetOrDefaultEnvInt("RELAY_TIMEOUT", 0) // unit is second
+var RelayTimeout = env.Int("RELAY_TIMEOUT", 0) // unit is second
 
-var GeminiSafetySetting = helper.GetOrDefaultEnvString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+var GeminiSafetySetting = env.String("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
-var Theme = helper.GetOrDefaultEnvString("THEME", "default")
+var Theme = env.String("THEME", "default")
 var ValidThemes = map[string]bool{
 	"default": true,
 	"berry":   true,
+	"air":     true,
 }
 
 // All duration's unit is seconds
 // Shouldn't larger then RateLimitKeyExpirationDuration
 var (
-	GlobalApiRateLimitNum            = helper.GetOrDefaultEnvInt("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitNum            = env.Int("GLOBAL_API_RATE_LIMIT", 180)
 	GlobalApiRateLimitDuration int64 = 3 * 60
 
-	GlobalWebRateLimitNum            = helper.GetOrDefaultEnvInt("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitNum            = env.Int("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration int64 = 3 * 60
 
 	UploadRateLimitNum            = 10
@@ -125,3 +130,9 @@ var (
 )
 
 var RateLimitKeyExpirationDuration = 20 * time.Minute
+
+var EnableMetric = env.Bool("ENABLE_METRIC", false)
+var MetricQueueSize = env.Int("METRIC_QUEUE_SIZE", 10)
+var MetricSuccessRateThreshold = env.Float64("METRIC_SUCCESS_RATE_THRESHOLD", 0.8)
+var MetricSuccessChanSize = env.Int("METRIC_SUCCESS_CHAN_SIZE", 1024)
+var MetricFailChanSize = env.Int("METRIC_FAIL_CHAN_SIZE", 128)

common/constants.go

@@ -15,6 +15,7 @@ const (
 const (
 	UserStatusEnabled  = 1 // don't use 0, 0 is the default value!
 	UserStatusDisabled = 2 // also don't use 0
+	UserStatusDeleted  = 3
 )
 
 const (
@@ -38,32 +39,40 @@ const (
 )
 
 const (
-	ChannelTypeUnknown        = 0
-	ChannelTypeOpenAI         = 1
-	ChannelTypeAPI2D          = 2
-	ChannelTypeAzure          = 3
-	ChannelTypeCloseAI        = 4
-	ChannelTypeOpenAISB       = 5
-	ChannelTypeOpenAIMax      = 6
-	ChannelTypeOhMyGPT        = 7
-	ChannelTypeCustom         = 8
-	ChannelTypeAILS           = 9
-	ChannelTypeAIProxy        = 10
-	ChannelTypePaLM           = 11
-	ChannelTypeAPI2GPT        = 12
-	ChannelTypeAIGC2D         = 13
-	ChannelTypeAnthropic      = 14
-	ChannelTypeBaidu          = 15
-	ChannelTypeZhipu          = 16
-	ChannelTypeAli            = 17
-	ChannelTypeXunfei         = 18
-	ChannelType360            = 19
-	ChannelTypeOpenRouter     = 20
-	ChannelTypeAIProxyLibrary = 21
-	ChannelTypeFastGPT        = 22
-	ChannelTypeTencent        = 23
-	ChannelTypeGemini         = 24
-	ChannelTypeMoonshot       = 25
+	ChannelTypeUnknown = iota
+	ChannelTypeOpenAI
+	ChannelTypeAPI2D
+	ChannelTypeAzure
+	ChannelTypeCloseAI
+	ChannelTypeOpenAISB
+	ChannelTypeOpenAIMax
+	ChannelTypeOhMyGPT
+	ChannelTypeCustom
+	ChannelTypeAILS
+	ChannelTypeAIProxy
+	ChannelTypePaLM
+	ChannelTypeAPI2GPT
+	ChannelTypeAIGC2D
+	ChannelTypeAnthropic
+	ChannelTypeBaidu
+	ChannelTypeZhipu
+	ChannelTypeAli
+	ChannelTypeXunfei
+	ChannelType360
+	ChannelTypeOpenRouter
+	ChannelTypeAIProxyLibrary
+	ChannelTypeFastGPT
+	ChannelTypeTencent
+	ChannelTypeGemini
+	ChannelTypeMoonshot
+	ChannelTypeBaichuan
+	ChannelTypeMinimax
+	ChannelTypeMistral
+	ChannelTypeGroq
+	ChannelTypeOllama
+	ChannelTypeLingYiWanWu
+
+	ChannelTypeDummy
 )
 
 var ChannelBaseURLs = []string{
@@ -93,6 +102,12 @@ var ChannelBaseURLs = []string{
 	"https://hunyuan.cloud.tencent.com",         // 23
 	"https://generativelanguage.googleapis.com", // 24
 	"https://api.moonshot.cn",                   // 25
+	"https://api.baichuan-ai.com",               // 26
+	"https://api.minimax.chat",                  // 27
+	"https://api.mistral.ai",                    // 28
+	"https://api.groq.com/openai",               // 29
+	"http://localhost:11434",                    // 30
+	"https://api.lingyiwanwu.com",               // 31
 }
 
 const (

common/database.go

@@ -1,9 +1,12 @@
 package common
 
-import "github.com/songquanpeng/one-api/common/helper"
+import (
+	"github.com/songquanpeng/one-api/common/env"
+)
 
 var UsingSQLite = false
 var UsingPostgreSQL = false
+var UsingMySQL = false
 
 var SQLitePath = "one-api.db"
-var SQLiteBusyTimeout = helper.GetOrDefaultEnvInt("SQLITE_BUSY_TIMEOUT", 3000)
+var SQLiteBusyTimeout = env.Int("SQLITE_BUSY_TIMEOUT", 3000)

common/env/helper.go

@@ -0,0 +1,42 @@
+package env
+
+import (
+	"os"
+	"strconv"
+)
+
+func Bool(env string, defaultValue bool) bool {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env) == "true"
+}
+
+func Int(env string, defaultValue int) int {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.Atoi(os.Getenv(env))
+	if err != nil {
+		return defaultValue
+	}
+	return num
+}
+
+func Float64(env string, defaultValue float64) float64 {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.ParseFloat(os.Getenv(env), 64)
+	if err != nil {
+		return defaultValue
+	}
+	return num
+}
+
+func String(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}

common/gin.go

@@ -8,12 +8,24 @@ import (
 	"strings"
 )
 
-func UnmarshalBodyReusable(c *gin.Context, v any) error {
+const KeyRequestBody = "key_request_body"
+
+func GetRequestBody(c *gin.Context) ([]byte, error) {
+	requestBody, _ := c.Get(KeyRequestBody)
+	if requestBody != nil {
+		return requestBody.([]byte), nil
+	}
 	requestBody, err := io.ReadAll(c.Request.Body)
 	if err != nil {
-		return err
+		return nil, err
 	}
-	err = c.Request.Body.Close()
+	_ = c.Request.Body.Close()
+	c.Set(KeyRequestBody, requestBody)
+	return requestBody.([]byte), nil
+}
+
+func UnmarshalBodyReusable(c *gin.Context, v any) error {
+	requestBody, err := GetRequestBody(c)
 	if err != nil {
 		return err
 	}

common/helper/helper.go

@@ -3,12 +3,10 @@ package helper
 import (
 	"fmt"
 	"github.com/google/uuid"
-	"github.com/songquanpeng/one-api/common/logger"
 	"html/template"
 	"log"
 	"math/rand"
 	"net"
-	"os"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -137,6 +135,7 @@ func GetUUID() string {
 }
 
 const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+const keyNumbers = "0123456789"
 
 func init() {
 	rand.Seed(time.Now().UnixNano())
@@ -168,6 +167,15 @@ func GetRandomString(length int) string {
 	return string(key)
 }
 
+func GetRandomNumberString(length int) string {
+	rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyNumbers[rand.Intn(len(keyNumbers))]
+	}
+	return string(key)
+}
+
 func GetTimestamp() int64 {
 	return time.Now().Unix()
 }
@@ -177,6 +185,10 @@ func GetTimeString() string {
 	return fmt.Sprintf("%s%d", now.Format("20060102150405"), now.UnixNano()%1e9)
 }
 
+func GenRequestID() string {
+	return GetTimeString() + GetRandomNumberString(8)
+}
+
 func Max(a int, b int) int {
 	if a >= b {
 		return a
@@ -185,25 +197,6 @@ func Max(a int, b int) int {
 	}
 }
 
-func GetOrDefaultEnvInt(env string, defaultValue int) int {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	num, err := strconv.Atoi(os.Getenv(env))
-	if err != nil {
-		logger.SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
-		return defaultValue
-	}
-	return num
-}
-
-func GetOrDefaultEnvString(env string, defaultValue string) string {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	return os.Getenv(env)
-}
-
 func AssignOrDefault(value string, defaultValue string) string {
 	if len(value) != 0 {
 		return value

common/logger/logger.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
 	"io"
 	"log"
 	"os"
@@ -13,14 +15,12 @@ import (
 )
 
 const (
+	loggerDEBUG = "DEBUG"
 	loggerINFO  = "INFO"
 	loggerWarn  = "WARN"
 	loggerError = "ERR"
 )
 
-const maxLogCount = 1000000
-
-var logCount int
 var setupLogLock sync.Mutex
 var setupLogWorking bool
 
@@ -55,6 +55,12 @@ func SysError(s string) {
 	_, _ = fmt.Fprintf(gin.DefaultErrorWriter, "[SYS] %v | %s \n", t.Format("2006/01/02 - 15:04:05"), s)
 }
 
+func Debug(ctx context.Context, msg string) {
+	if config.DebugEnabled {
+		logHelper(ctx, loggerDEBUG, msg)
+	}
+}
+
 func Info(ctx context.Context, msg string) {
 	logHelper(ctx, loggerINFO, msg)
 }
@@ -67,6 +73,10 @@ func Error(ctx context.Context, msg string) {
 	logHelper(ctx, loggerError, msg)
 }
 
+func Debugf(ctx context.Context, format string, a ...any) {
+	Debug(ctx, fmt.Sprintf(format, a...))
+}
+
 func Infof(ctx context.Context, format string, a ...any) {
 	Info(ctx, fmt.Sprintf(format, a...))
 }
@@ -85,11 +95,12 @@ func logHelper(ctx context.Context, level string, msg string) {
 		writer = gin.DefaultWriter
 	}
 	id := ctx.Value(RequestIdKey)
+	if id == nil {
+		id = helper.GenRequestID()
+	}
 	now := time.Now()
 	_, _ = fmt.Fprintf(writer, "[%s] %v | %s | %s \n", level, now.Format("2006/01/02 - 15:04:05"), id, msg)
-	logCount++ // we don't need accurate count, so no lock here
-	if logCount > maxLogCount && !setupLogWorking {
-		logCount = 0
+	if !setupLogWorking {
 		setupLogWorking = true
 		go func() {
 			SetupLogger()

common/message/email.go

@@ -1,4 +1,4 @@
-package common
+package message
 
 import (
 	"crypto/rand"
@@ -12,6 +12,9 @@ import (
 )
 
 func SendEmail(subject string, receiver string, content string) error {
+	if receiver == "" {
+		return fmt.Errorf("receiver is empty")
+	}
 	if config.SMTPFrom == "" { // for compatibility
 		config.SMTPFrom = config.SMTPAccount
 	}

common/message/main.go

@@ -0,0 +1,22 @@
+package message
+
+import (
+	"fmt"
+	"github.com/songquanpeng/one-api/common/config"
+)
+
+const (
+	ByAll           = "all"
+	ByEmail         = "email"
+	ByMessagePusher = "message_pusher"
+)
+
+func Notify(by string, title string, description string, content string) error {
+	if by == ByEmail {
+		return SendEmail(title, config.RootUserEmail, content)
+	}
+	if by == ByMessagePusher {
+		return SendMessage(title, description, content)
+	}
+	return fmt.Errorf("unknown notify method: %s", by)
+}

common/message/message-pusher.go

@@ -0,0 +1,53 @@
+package message
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"github.com/songquanpeng/one-api/common/config"
+	"net/http"
+)
+
+type request struct {
+	Title       string `json:"title"`
+	Description string `json:"description"`
+	Content     string `json:"content"`
+	URL         string `json:"url"`
+	Channel     string `json:"channel"`
+	Token       string `json:"token"`
+}
+
+type response struct {
+	Success bool   `json:"success"`
+	Message string `json:"message"`
+}
+
+func SendMessage(title string, description string, content string) error {
+	if config.MessagePusherAddress == "" {
+		return errors.New("message pusher address is not set")
+	}
+	req := request{
+		Title:       title,
+		Description: description,
+		Content:     content,
+		Token:       config.MessagePusherToken,
+	}
+	data, err := json.Marshal(req)
+	if err != nil {
+		return err
+	}
+	resp, err := http.Post(config.MessagePusherAddress,
+		"application/json", bytes.NewBuffer(data))
+	if err != nil {
+		return err
+	}
+	var res response
+	err = json.NewDecoder(resp.Body).Decode(&res)
+	if err != nil {
+		return err
+	}
+	if !res.Success {
+		return errors.New(res.Message)
+	}
+	return nil
+}

common/model-ratio.go

@@ -4,32 +4,8 @@ import (
 	"encoding/json"
 	"github.com/songquanpeng/one-api/common/logger"
 	"strings"
-	"time"
 )
 
-var DalleSizeRatios = map[string]map[string]float64{
-	"dall-e-2": {
-		"256x256":   1,
-		"512x512":   1.125,
-		"1024x1024": 1.25,
-	},
-	"dall-e-3": {
-		"1024x1024": 1,
-		"1024x1792": 2,
-		"1792x1024": 2,
-	},
-}
-
-var DalleGenerationImageAmounts = map[string][2]int{
-	"dall-e-2": {1, 10},
-	"dall-e-3": {1, 1}, // OpenAI allows n=1 currently.
-}
-
-var DalleImagePromptLengthLimitations = map[string]int{
-	"dall-e-2": 1000,
-	"dall-e-3": 4000,
-}
-
 const (
 	USD2RMB = 7
 	USD     = 500 // $0.002 = 1 -> $1 = 500
@@ -40,7 +16,6 @@ const (
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
 // https://openai.com/pricing
-// TODO: when a new api is enabled, check the pricing here
 // 1 === $0.002 / 1K tokens
 // 1 === ￥0.014 / 1k tokens
 var ModelRatio = map[string]float64{
@@ -57,7 +32,7 @@ var ModelRatio = map[string]float64{
 	"gpt-4-0125-preview":      5,    // $0.01 / 1K tokens
 	"gpt-4-turbo-preview":     5,    // $0.01 / 1K tokens
 	"gpt-4-vision-preview":    5,    // $0.01 / 1K tokens
-	"gpt-3.5-turbo":           0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo":           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
@@ -89,21 +64,32 @@ var ModelRatio = map[string]float64{
 	"text-search-ada-doc-001": 10,
 	"text-moderation-stable":  0.1,
 	"text-moderation-latest":  0.1,
-	"dall-e-2":                8,     // $0.016 - $0.020 / image
-	"dall-e-3":                20,    // $0.040 - $0.120 / image
-	"claude-instant-1":        0.815, // $1.63 / 1M tokens
-	"claude-2":                5.51,  // $11.02 / 1M tokens
-	"claude-2.0":              5.51,  // $11.02 / 1M tokens
-	"claude-2.1":              5.51,  // $11.02 / 1M tokens
+	"dall-e-2":                8,  // $0.016 - $0.020 / image
+	"dall-e-3":                20, // $0.040 - $0.120 / image
+	// https://www.anthropic.com/api#pricing
+	"claude-instant-1.2":       0.8 / 1000 * USD,
+	"claude-2.0":               8.0 / 1000 * USD,
+	"claude-2.1":               8.0 / 1000 * USD,
+	"claude-3-haiku-20240307":  0.25 / 1000 * USD,
+	"claude-3-sonnet-20240229": 3.0 / 1000 * USD,
+	"claude-3-opus-20240229":   15.0 / 1000 * USD,
 	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
-	"ERNIE-Bot":                 0.8572,     // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":           0.5715,     // ￥0.008 / 1k tokens
-	"ERNIE-Bot-4":               0.12 * RMB, // ￥0.12 / 1k tokens
-	"ERNIE-Bot-8k":              0.024 * RMB,
-	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
-	"PaLM-2":                    1,
-	"gemini-pro":                1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-pro-vision":         1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"ERNIE-Bot":       0.8572,     // ￥0.012 / 1k tokens
+	"ERNIE-Bot-turbo": 0.5715,     // ￥0.008 / 1k tokens
+	"ERNIE-Bot-4":     0.12 * RMB, // ￥0.12 / 1k tokens
+	"ERNIE-Bot-8k":    0.024 * RMB,
+	"Embedding-V1":    0.1429, // ￥0.002 / 1k tokens
+	"bge-large-zh":    0.002 * RMB,
+	"bge-large-en":    0.002 * RMB,
+	"bge-large-8k":    0.002 * RMB,
+	// https://ai.google.dev/pricing
+	"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
+	// https://open.bigmodel.cn/pricing
+	"glm-4":                     0.1 * RMB,
+	"glm-4v":                    0.1 * RMB,
+	"glm-3-turbo":               0.005 * RMB,
 	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
@@ -129,6 +115,66 @@ var ModelRatio = map[string]float64{
 	"moonshot-v1-8k":   0.012 * RMB,
 	"moonshot-v1-32k":  0.024 * RMB,
 	"moonshot-v1-128k": 0.06 * RMB,
+	// https://platform.baichuan-ai.com/price
+	"Baichuan2-Turbo":      0.008 * RMB,
+	"Baichuan2-Turbo-192k": 0.016 * RMB,
+	"Baichuan2-53B":        0.02 * RMB,
+	// https://api.minimax.chat/document/price
+	"abab6-chat":    0.1 * RMB,
+	"abab5.5-chat":  0.015 * RMB,
+	"abab5.5s-chat": 0.005 * RMB,
+	// https://docs.mistral.ai/platform/pricing/
+	"open-mistral-7b":       0.25 / 1000 * USD,
+	"open-mixtral-8x7b":     0.7 / 1000 * USD,
+	"mistral-small-latest":  2.0 / 1000 * USD,
+	"mistral-medium-latest": 2.7 / 1000 * USD,
+	"mistral-large-latest":  8.0 / 1000 * USD,
+	"mistral-embed":         0.1 / 1000 * USD,
+	// https://wow.groq.com/
+	"llama2-70b-4096":    0.7 / 1000 * USD,
+	"llama2-7b-2048":     0.1 / 1000 * USD,
+	"mixtral-8x7b-32768": 0.27 / 1000 * USD,
+	"gemma-7b-it":        0.1 / 1000 * USD,
+	// https://platform.lingyiwanwu.com/docs#-计费单元
+	"yi-34b-chat-0205": 2.5 / 1000000 * RMB,
+	"yi-34b-chat-200k": 12.0 / 1000000 * RMB,
+	"yi-vl-plus":       6.0 / 1000000 * RMB,
+}
+
+var CompletionRatio = map[string]float64{}
+
+var DefaultModelRatio map[string]float64
+var DefaultCompletionRatio map[string]float64
+
+func init() {
+	DefaultModelRatio = make(map[string]float64)
+	for k, v := range ModelRatio {
+		DefaultModelRatio[k] = v
+	}
+	DefaultCompletionRatio = make(map[string]float64)
+	for k, v := range CompletionRatio {
+		DefaultCompletionRatio[k] = v
+	}
+}
+
+func AddNewMissingRatio(oldRatio string) string {
+	newRatio := make(map[string]float64)
+	err := json.Unmarshal([]byte(oldRatio), &newRatio)
+	if err != nil {
+		logger.SysError("error unmarshalling old ratio: " + err.Error())
+		return oldRatio
+	}
+	for k, v := range DefaultModelRatio {
+		if _, ok := newRatio[k]; !ok {
+			newRatio[k] = v
+		}
+	}
+	jsonBytes, err := json.Marshal(newRatio)
+	if err != nil {
+		logger.SysError("error marshalling new ratio: " + err.Error())
+		return oldRatio
+	}
+	return string(jsonBytes)
 }
 
 func ModelRatio2JSONString() string {
@@ -152,6 +198,9 @@ func GetModelRatio(name string) float64 {
 	if strings.Index(name, "gpt-4-gizmo") != -1 {
 		return ModelRatio["gpt-4-gizmo"]
 	}
+	if !ok {
+		ratio, ok = DefaultModelRatio[name]
+	}
 	if !ok {
 		logger.SysError("model ratio not found: " + name)
 		return 30
@@ -159,8 +208,6 @@ func GetModelRatio(name string) float64 {
 	return ratio
 }
 
-var CompletionRatio = map[string]float64{}
-
 func CompletionRatio2JSONString() string {
 	jsonBytes, err := json.Marshal(CompletionRatio)
 	if err != nil {
@@ -178,8 +225,11 @@ func GetCompletionRatio(name string) float64 {
 	if ratio, ok := CompletionRatio[name]; ok {
 		return ratio
 	}
+	if ratio, ok := DefaultCompletionRatio[name]; ok {
+		return ratio
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
-		if strings.HasSuffix(name, "0125") {
+		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
@@ -187,16 +237,7 @@ func GetCompletionRatio(name string) float64 {
 		if strings.HasSuffix(name, "1106") {
 			return 2
 		}
-		if name == "gpt-3.5-turbo" || name == "gpt-3.5-turbo-16k" {
-			// TODO: clear this after 2023-12-11
-			now := time.Now()
-			// https://platform.openai.com/docs/models/continuous-model-upgrades
-			// if after 2023-12-11, use 2
-			if now.After(time.Date(2023, 12, 11, 0, 0, 0, 0, time.UTC)) {
-				return 2
-			}
-		}
-		return 1.333333
+		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") {
 		if strings.HasSuffix(name, "preview") {
@@ -204,11 +245,18 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 2
 	}
-	if strings.HasPrefix(name, "claude-instant-1") {
-		return 3.38
+	if strings.HasPrefix(name, "claude-3") {
+		return 5
 	}
-	if strings.HasPrefix(name, "claude-2") {
-		return 2.965517
+	if strings.HasPrefix(name, "claude-") {
+		return 3
+	}
+	if strings.HasPrefix(name, "mistral-") {
+		return 3
+	}
+	switch name {
+	case "llama2-70b-4096":
+		return 0.8 / 0.7
 	}
 	return 1
 }

common/random.go

@@ -0,0 +1,8 @@
+package common
+
+import "math/rand"
+
+// RandRange returns a random number between min and max (max is not included)
+func RandRange(min, max int) int {
+	return min + rand.Intn(max-min)
+}

common/utils.go

@@ -5,7 +5,7 @@ import (
 	"github.com/songquanpeng/one-api/common/config"
 )
 
-func LogQuota(quota int) string {
+func LogQuota(quota int64) string {
 	if config.DisplayInCurrencyEnabled {
 		return fmt.Sprintf("＄%.6f 额度", float64(quota)/config.QuotaPerUnit)
 	} else {