fix: 模型价格

feat: 自定义渠道功能变更

common/constants.go

@@ -208,6 +208,7 @@ const (
 	ChannelTypeLingYiWanWu    = 31
 	ChannelTypeAws            = 33
 	ChannelTypeCohere         = 34
+	ChannelTypeMiniMax        = 35
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
 )
@@ -248,4 +249,5 @@ var ChannelBaseURLs = []string{
 	"",                                          //32
 	"",                                          //33
 	"https://api.cohere.ai",                     //34
+	"https://api.minimax.chat",                  //35
 }

common/model-ratio.go

@@ -5,6 +5,13 @@ import (
 	"strings"
 )
 
+// from songquanpeng/one-api
+const (
+	USD2RMB = 7.3 // 暂定 1 USD = 7.3 RMB
+	USD     = 500 // $0.002 = 1 -> $1 = 500
+	RMB     = USD / USD2RMB
+)
+
 // modelRatio
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
@@ -33,79 +40,100 @@ var DefaultModelRatio = map[string]float64{
 	"gpt-4-turbo-2024-04-09":    5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":             0.25, // $0.0015 / 1K tokens
 	//"gpt-3.5-turbo-0301":           0.75, //deprecated
-	"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-sonnet-20240229":     1.5,    // $3 / 1M tokens
-	"claude-3-opus-20240229":       7.5,    // $15 / 1M tokens
-	"ERNIE-Bot":                    0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":              0.5715, // ￥0.008 / 1k tokens
-	"ERNIE-Bot-4":                  8.572,  // ￥0.12 / 1k tokens
-	"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
-	"gemini-1.0-pro-vision-001":    1,
-	"gemini-1.0-pro-001":           1,
-	"gemini-1.5-pro-latest":        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":                       7.143,  // ￥0.1 / 1k tokens
-	"glm-3-turbo":                  0.3572,
-	"qwen-turbo":                   0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus":                    10,     // ￥0.14 / 1k tokens
-	"text-embedding-v1":            0.05,   // ￥0.0007 / 1k tokens
-	"SparkDesk-v1.1":               1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v2.1":               1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.1":               1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.5":               1.2858, // ￥0.018 / 1k tokens
-	"360GPT_S2_V9":                 0.8572, // ¥0.012 / 1k tokens
-	"embedding-bert-512-v1":        0.0715, // ¥0.001 / 1k tokens
-	"embedding_s1_v1":              0.0715, // ¥0.001 / 1k tokens
-	"semantic_similarity_s1_v1":    0.0715, // ¥0.001 / 1k tokens
-	"hunyuan":                      7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
+	"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-sonnet-20240229":       1.5,    // $3 / 1M tokens
+	"claude-3-opus-20240229":         7.5,    // $15 / 1M tokens
+	"ERNIE-Bot":                      0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
+	"ERNIE-Bot-turbo":                0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
+	"ERNIE-Bot-4":                    8.572,  // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
+	"ERNIE-4.0-8K":                   8.572,  // ￥0.12 / 1k tokens
+	"ERNIE-3.5-8K":                   0.8572, // ￥0.012 / 1k tokens
+	"ERNIE-Speed-8K":                 0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Speed-128K":               0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Lite-8K":                  0.2143, // ￥0.003 / 1k tokens
+	"ERNIE-Tiny-8K":                  0.0715, // ￥0.001 / 1k tokens
+	"ERNIE-Character-8K":             0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Functions-8K":             0.2858, // ￥0.004 / 1k tokens
+	"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
+	"gemini-1.0-pro-vision-001":      1,
+	"gemini-1.0-pro-001":             1,
+	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-flash-latest":        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":                         7.143,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":                    0.3572,
+	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
+	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
+	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
+	"SparkDesk-v1.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v2.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5":                 1.2858, // ￥0.018 / 1k tokens
+	"360GPT_S2_V9":                   0.8572, // ¥0.012 / 1k tokens
+	"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":      0.018,
-	"yi-34b-chat-200k":      0.0864,
-	"yi-vl-plus":            0.0432,
+	"yi-34b-chat-0205":      0.18,
+	"yi-34b-chat-200k":      0.864,
+	"yi-vl-plus":            0.432,
+	"yi-large":              20.0 / 1000 * RMB,
+	"yi-medium":             2.5 / 1000 * RMB,
+	"yi-vision":             6.0 / 1000 * RMB,
+	"yi-medium-200k":        12.0 / 1000 * RMB,
+	"yi-spark":              1.0 / 1000 * RMB,
+	"yi-large-rag":          25.0 / 1000 * RMB,
+	"yi-large-turbo":        12.0 / 1000 * RMB,
+	"yi-large-preview":      20.0 / 1000 * RMB,
+	"yi-large-rag-preview":  25.0 / 1000 * RMB,
 	"command":               0.5,
 	"command-nightly":       0.5,
 	"command-light":         0.5,
@@ -114,6 +142,11 @@ var DefaultModelRatio = map[string]float64{
 	"command-r-plus	":       1.5,
 	"deepseek-chat":         0.07,
 	"deepseek-coder":        0.07,
+	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
+	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
+	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
+	"llama-3-sonar-large-32k-chat":   1 / 1000 * USD,
+	"llama-3-sonar-large-32k-online": 1 / 1000 * USD,
 }
 
 var DefaultModelPrice = map[string]float64{
@@ -256,7 +289,7 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
+	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
 		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4o") {
 			return 3
 		}
@@ -288,6 +321,15 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "deepseek") {
 		return 2
 	}
+	if strings.HasPrefix(name, "ERNIE-Speed-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Lite-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Character") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Functions") {
+		return 2
+	}
 	switch name {
 	case "llama2-70b-4096":
 		return 0.8 / 0.64

common/utils.go

@@ -258,3 +258,12 @@ func MapToJsonStrFloat(m map[string]float64) string {
 	}
 	return string(bytes)
 }
+
+func StrToMap(str string) map[string]interface{} {
+	m := make(map[string]interface{})
+	err := json.Unmarshal([]byte(str), &m)
+	if err != nil {
+		return nil
+	}
+	return m
+}

controller/channel-test.go

@@ -64,7 +64,21 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		} else {
 			testModel = adaptor.GetModelList()[0]
 		}
+	} else {
+		modelMapping := *channel.ModelMapping
+		if modelMapping != "" && modelMapping != "{}" {
+			modelMap := make(map[string]string)
+			err := json.Unmarshal([]byte(modelMapping), &modelMap)
+			if err != nil {
+				openaiErr := service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError).Error
+				return err, &openaiErr
+			}
+			if modelMap[testModel] != "" {
+				testModel = modelMap[testModel]
+			}
+		}
 	}
+
 	request := buildTestRequest()
 	request.Model = testModel
 	meta.UpstreamModelName = testModel

controller/model.go

@@ -11,6 +11,7 @@ import (
 	"one-api/relay"
 	"one-api/relay/channel/ai360"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/minimax"
 	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
@@ -79,7 +80,7 @@ func init() {
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "moonshot",
+			OwnedBy:    moonshot.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
@@ -90,7 +91,18 @@ func init() {
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "lingyiwanwu",
+			OwnedBy:    lingyiwanwu.ChannelName,
+			Permission: permission,
+			Root:       modelName,
+			Parent:     nil,
+		})
+	}
+	for _, modelName := range minimax.ModelList {
+		openAIModels = append(openAIModels, dto.OpenAIModels{
+			Id:         modelName,
+			Object:     "model",
+			Created:    1626777600,
+			OwnedBy:    minimax.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
@@ -108,8 +120,8 @@ func init() {
 		})
 	}
 	openAIModelsMap = make(map[string]dto.OpenAIModels)
-	for _, model := range openAIModels {
-		openAIModelsMap[model.Id] = model
+	for _, aiModel := range openAIModels {
+		openAIModelsMap[aiModel.Id] = aiModel
 	}
 	channelId2Models = make(map[int][]string)
 	for i := 1; i <= common.ChannelTypeDummy; i++ {
@@ -174,8 +186,8 @@ func DashboardListModels(c *gin.Context) {
 
 func RetrieveModel(c *gin.Context) {
 	modelId := c.Param("model")
-	if model, ok := openAIModelsMap[modelId]; ok {
-		c.JSON(200, model)
+	if aiModel, ok := openAIModelsMap[modelId]; ok {
+		c.JSON(200, aiModel)
 	} else {
 		openAIError := dto.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),
@@ -191,12 +203,12 @@ func RetrieveModel(c *gin.Context) {
 
 func GetPricing(c *gin.Context) {
 	userId := c.GetInt("id")
-	user, _ := model.GetUserById(userId, true)
+	group, err := model.CacheGetUserGroup(userId)
 	groupRatio := common.GetGroupRatio("default")
-	if user != nil {
-		groupRatio = common.GetGroupRatio(user.Group)
+	if err != nil {
+		groupRatio = common.GetGroupRatio(group)
 	}
-	pricing := model.GetPricing(user, openAIModels)
+	pricing := model.GetPricing(group)
 	c.JSON(200, gin.H{
 		"success":     true,
 		"data":        pricing,

controller/relay.go

@@ -43,7 +43,7 @@ func Relay(c *gin.Context) {
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
 	openaiErr := relayHandler(c, relayMode)
-	useChannel := []int{channelId}
+	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
 	if openaiErr != nil {
 		go processChannelError(c, channelId, openaiErr)
 	} else {
@@ -56,7 +56,9 @@ func Relay(c *gin.Context) {
 			break
 		}
 		channelId = channel.Id
-		useChannel = append(useChannel, channelId)
+		useChannel := c.GetStringSlice("use_channel")
+		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		c.Set("use_channel", useChannel)
 		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
@@ -67,6 +69,7 @@ func Relay(c *gin.Context) {
 			go processChannelError(c, channelId, openaiErr)
 		}
 	}
+	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.Request.Context(), retryLogStr)

go.mod

@@ -17,11 +17,11 @@ require (
 	github.com/go-playground/validator/v10 v10.19.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/golang-jwt/jwt v3.2.2+incompatible
-	github.com/google/uuid v1.3.0
+	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/jinzhu/copier v0.4.0
+	github.com/linux-do/tiktoken-go v0.7.0
 	github.com/pkg/errors v0.9.1
-	github.com/pkoukk/tiktoken-go v0.1.6
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
 	golang.org/x/crypto v0.21.0
@@ -42,7 +42,7 @@ require (
 	github.com/cespare/xxhash/v2 v2.1.2 // 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 v1.10.0 // indirect
+	github.com/dlclark/regexp2 v1.11.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect

go.sum

@@ -32,8 +32,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
-github.com/dlclark/regexp2 v1.10.0 h1:+/GIL799phkJqYW+3YbOd8LCcbHzT0Pbo8zl70MHsq0=
-github.com/dlclark/regexp2 v1.10.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
+github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
 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=
@@ -81,8 +81,8 @@ github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaS
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
-github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
-github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/context v1.1.1 h1:AWwleXJkX/nhcU9bZSnZoi3h/qGYqQAGhq6zZe/aQW8=
 github.com/gorilla/context v1.1.1/go.mod h1:kBGZzfjB9CEq2AlWe17Uuf7NDRt0dE0s8S51q0aT7Yg=
 github.com/gorilla/securecookie v1.1.1 h1:miw7JPhV+b/lAHSXz4qd/nN9jRiAFV5FwjeKyCS8BvQ=
@@ -124,6 +124,8 @@ github.com/leodido/go-urn v1.2.0/go.mod h1:+8+nEpDfqqsY+g338gtMEUOtuK+4dEMhiQEgx
 github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
 github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ=
 github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI=
+github.com/linux-do/tiktoken-go v0.7.0 h1:Kcm/miJ5gp77srtF8GQWnfq7W9kTaXEuHZg/g9IVEu8=
+github.com/linux-do/tiktoken-go v0.7.0/go.mod h1:9Vkdtp0ngi4USmrdSx984iuIQ5IMr0hnUdz4jZZTJb8=
 github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
 github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
@@ -148,8 +150,6 @@ github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNc
 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=
-github.com/pkoukk/tiktoken-go v0.1.6 h1:JF0TlJzhTbrI30wCvFuiw6FzP2+/bR+FIxUdgEAcUsw=
-github.com/pkoukk/tiktoken-go v0.1.6/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=

model/log.go

@@ -142,6 +142,15 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
+	for i := range logs {
+		var otherMap map[string]interface{}
+		otherMap = common.StrToMap(logs[i].Other)
+		if otherMap != nil {
+			// delete admin
+			delete(otherMap, "admin_info")
+		}
+		logs[i].Other = common.MapToJsonStr(otherMap)
+	}
 	return logs, err
 }
 

model/main.go

@@ -93,12 +93,12 @@ func InitDB() (err error) {
 		if !common.IsMasterNode {
 			return nil
 		}
-		if common.UsingMySQL {
-			_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
-		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
 		common.SysLog("database migration started")
 		err = db.AutoMigrate(&Channel{})
 		if err != nil {

model/pricing.go

@@ -13,16 +13,16 @@ var (
 	updatePricingLock  sync.Mutex
 )
 
-func GetPricing(user *User, openAIModels []dto.OpenAIModels) []dto.ModelPricing {
+func GetPricing(group string) []dto.ModelPricing {
 	updatePricingLock.Lock()
 	defer updatePricingLock.Unlock()
 
 	if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
-		updatePricing(openAIModels)
+		updatePricing()
 	}
-	if user != nil {
+	if group != "" {
 		userPricingMap := make([]dto.ModelPricing, 0)
-		models := GetGroupModels(user.Group)
+		models := GetGroupModels(group)
 		for _, pricing := range pricingMap {
 			if !common.StringsContains(models, pricing.ModelName) {
 				pricing.Available = false
@@ -34,28 +34,19 @@ func GetPricing(user *User, openAIModels []dto.OpenAIModels) []dto.ModelPricing
 	return pricingMap
 }
 
-func updatePricing(openAIModels []dto.OpenAIModels) {
-	modelRatios := common.GetModelRatios()
+func updatePricing() {
+	//modelRatios := common.GetModelRatios()
 	enabledModels := GetEnabledModels()
-	allModels := make(map[string]string)
-	for _, openAIModel := range openAIModels {
-		if common.StringsContains(enabledModels, openAIModel.Id) {
-			allModels[openAIModel.Id] = openAIModel.OwnedBy
-		}
-	}
-	for model, _ := range modelRatios {
-		if common.StringsContains(enabledModels, model) {
-			if _, ok := allModels[model]; !ok {
-				allModels[model] = "custom"
-			}
-		}
+	allModels := make(map[string]int)
+	for i, model := range enabledModels {
+		allModels[model] = i
 	}
+
 	pricingMap = make([]dto.ModelPricing, 0)
-	for model, ownerBy := range allModels {
+	for model, _ := range allModels {
 		pricing := dto.ModelPricing{
 			Available: true,
 			ModelName: model,
-			OwnerBy:   ownerBy,
 		}
 		modelPrice, findPrice := common.GetModelPrice(model, false)
 		if findPrice {

model/token.go

@@ -11,7 +11,7 @@ import (
 
 type Token struct {
 	Id                 int            `json:"id"`
-	UserId             int            `json:"user_id"`
+	UserId             int            `json:"user_id" gorm:"index"`
 	Key                string         `json:"key" gorm:"type:char(48);uniqueIndex"`
 	Status             int            `json:"status" gorm:"default:1"`
 	Name               string         `json:"name" gorm:"index" `

relay/channel/ai360/constants.go

@@ -1,6 +1,9 @@
 package ai360
 
 var ModelList = []string{
+	"360gpt-turbo",
+	"360gpt-turbo-responsibility-8k",
+	"360gpt-pro",
 	"360GPT_S2_V9",
 	"embedding-bert-512-v1",
 	"embedding_s1_v1",

relay/channel/baidu/adaptor.go

@@ -9,6 +9,7 @@ import (
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+	"strings"
 )
 
 type Adaptor struct {
@@ -33,8 +34,24 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
 	case "BLOOMZ-7B":
 		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
+	case "ERNIE-4.0-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
+	case "ERNIE-3.5-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
+	case "ERNIE-Speed-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
+	case "ERNIE-Character-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-char-8k"
+	case "ERNIE-Functions-8K":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-func-8k"
+	case "ERNIE-Lite-8K-0922":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
+	case "Yi-34B-Chat":
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/yi_34b_chat"
 	case "Embedding-V1":
 		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
+	default:
+		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/" + strings.ToLower(info.UpstreamModelName)
 	}
 	var accessToken string
 	var err error

relay/channel/baidu/constants.go

@@ -1,11 +1,19 @@
 package baidu
 
 var ModelList = []string{
-	"ERNIE-Bot-4",
-	"ERNIE-Bot-8K",
-	"ERNIE-Bot",
-	"ERNIE-Speed",
-	"ERNIE-Bot-turbo",
+	"ERNIE-3.5-8K",
+	"ERNIE-4.0-8K",
+	"ERNIE-Speed-8K",
+	"ERNIE-Speed-128K",
+	"ERNIE-Lite-8K",
+	"ERNIE-Tiny-8K",
+	"ERNIE-Character-8K",
+	"ERNIE-Functions-8K",
+	//"ERNIE-Bot-4",
+	//"ERNIE-Bot-8K",
+	//"ERNIE-Bot",
+	//"ERNIE-Speed",
+	//"ERNIE-Bot-turbo",
 	"Embedding-V1",
 }
 

relay/channel/gemini/adaptor.go

@@ -21,6 +21,7 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
 // 定义一个映射，存储模型名称和对应的版本
 var modelVersionMap = map[string]string{
     "gemini-1.5-pro-latest": "v1beta",
+    "gemini-1.5-flash-latest": "v1beta",
     "gemini-ultra":   "v1beta",
 }
 

relay/channel/gemini/constant.go

@@ -5,7 +5,7 @@ const (
 )
 
 var ModelList = []string{
-	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-ultra",
+	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
 	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001",
 }
 

relay/channel/lingyiwanwu/constrants.go

@@ -1,9 +1,9 @@
-package lingyiwanwu
-
-// https://platform.lingyiwanwu.com/docs
-
-var ModelList = []string{
-	"yi-34b-chat-0205",
-	"yi-34b-chat-200k",
-	"yi-vl-plus",
-}
+package lingyiwanwu
+
+// https://platform.lingyiwanwu.com/docs
+
+var ModelList = []string{
+	"yi-large", "yi-medium", "yi-vision", "yi-medium-200k", "yi-spark", "yi-large-rag", "yi-large-turbo", "yi-large-preview", "yi-large-rag-preview",
+}
+
+var ChannelName = "lingyiwanwu"

relay/channel/minimax/constants.go

@@ -0,0 +1,13 @@
+package minimax
+
+// https://www.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd
+
+var ModelList = []string{
+	"abab6.5-chat",
+	"abab6.5s-chat",
+	"abab6-chat",
+	"abab5.5-chat",
+	"abab5.5s-chat",
+}
+
+var ChannelName = "minimax"

relay/channel/minimax/relay-minimax.go

@@ -0,0 +1,10 @@
+package minimax
+
+import (
+	"fmt"
+	relaycommon "one-api/relay/common"
+)
+
+func GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/text/chatcompletion_v2", info.BaseUrl), nil
+}

relay/channel/moonshot/constants.go

@@ -5,3 +5,5 @@ var ModelList = []string{
 	"moonshot-v1-32k",
 	"moonshot-v1-128k",
 }
+
+var ChannelName = "moonshot"

relay/channel/openai/adaptor.go

@@ -11,6 +11,7 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/minimax"
 	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
@@ -26,7 +27,8 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	if info.ChannelType == common.ChannelTypeAzure {
+	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
 		requestURL := strings.Split(info.RequestURLPath, "?")[0]
 		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
@@ -37,8 +39,15 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
+	case common.ChannelTypeMiniMax:
+		return minimax.GetRequestURL(info)
+	case common.ChannelTypeCustom:
+		url := info.BaseUrl
+		url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
+		return url, nil
+	default:
+		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 	}
-	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -90,11 +99,24 @@ func (a *Adaptor) GetModelList() []string {
 		return moonshot.ModelList
 	case common.ChannelTypeLingYiWanWu:
 		return lingyiwanwu.ModelList
+	case common.ChannelTypeMiniMax:
+		return minimax.ModelList
 	default:
 		return ModelList
 	}
 }
 
 func (a *Adaptor) GetChannelName() string {
-	return ChannelName
+	switch a.ChannelType {
+	case common.ChannelType360:
+		return ai360.ChannelName
+	case common.ChannelTypeMoonshot:
+		return moonshot.ChannelName
+	case common.ChannelTypeLingYiWanWu:
+		return lingyiwanwu.ChannelName
+	case common.ChannelTypeMiniMax:
+		return minimax.ChannelName
+	default:
+		return ChannelName
+	}
 }

relay/channel/openai/constant.go

@@ -1,7 +1,6 @@
 package openai
 
 var ModelList = []string{
-	"gpt-4o",
 	"gpt-3.5-turbo", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125",
 	"gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613",
 	"gpt-3.5-turbo-instruct",
@@ -9,6 +8,7 @@ var ModelList = []string{
 	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
+	"gpt-4o", "gpt-4o-2024-05-13",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",
 	"text-moderation-latest", "text-moderation-stable",

relay/channel/perplexity/constants.go

@@ -1,7 +1,7 @@
 package perplexity
 
 var ModelList = []string{
-	"sonar-small-chat", "sonar-small-online", "sonar-medium-chat", "sonar-medium-online", "mistral-7b-instruct", "mixtral-8x7b-instruct",
+	"llama-3-sonar-small-32k-chat", "llama-3-sonar-small-32k-online", "llama-3-sonar-large-32k-chat", "llama-3-sonar-large-32k-online", "llama-3-8b-instruct", "llama-3-70b-instruct", "mixtral-8x7b-instruct",
 }
 
 var ChannelName = "perplexity"

relay/constant/api_type.go

@@ -15,7 +15,7 @@ const (
 	APITypeAIProxyLibrary
 	APITypeTencent
 	APITypeGemini
-	APITypeZhipu_v4
+	APITypeZhipuV4
 	APITypeOllama
 	APITypePerplexity
 	APITypeAws
@@ -48,7 +48,7 @@ func ChannelType2APIType(channelType int) (int, bool) {
 	case common.ChannelTypeGemini:
 		apiType = APITypeGemini
 	case common.ChannelTypeZhipu_v4:
-		apiType = APITypeZhipu_v4
+		apiType = APITypeZhipuV4
 	case common.ChannelTypeOllama:
 		apiType = APITypeOllama
 	case common.ChannelTypePerplexity:

relay/relay-text.go

@@ -320,6 +320,9 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRe
 	other["group_ratio"] = groupRatio
 	other["completion_ratio"] = completionRatio
 	other["model_price"] = modelPrice
+	adminInfo := make(map[string]interface{})
+	adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
+	other["admin_info"] = adminInfo
 	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel, tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
 
 	//if quota != 0 {

relay/relay_adaptor.go

@@ -41,7 +41,7 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &xunfei.Adaptor{}
 	case constant.APITypeZhipu:
 		return &zhipu.Adaptor{}
-	case constant.APITypeZhipu_v4:
+	case constant.APITypeZhipuV4:
 		return &zhipu_4v.Adaptor{}
 	case constant.APITypeOllama:
 		return &ollama.Adaptor{}

router/api-router.go

@@ -20,7 +20,7 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/about", controller.GetAbout)
 		//apiRouter.GET("/midjourney", controller.GetMidjourney)
 		apiRouter.GET("/home_page_content", controller.GetHomePageContent)
-		apiRouter.GET("/pricing", middleware.CriticalRateLimit(), middleware.TryUserAuth(), controller.GetPricing)
+		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)

service/token_counter.go

@@ -4,7 +4,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/pkoukk/tiktoken-go"
+	"github.com/linux-do/tiktoken-go"
 	"image"
 	"log"
 	"math"
@@ -26,6 +26,7 @@ func InitTokenEncoders() {
 	}
 	defaultTokenEncoder = gpt35TokenEncoder
 	gpt4TokenEncoder, err := tiktoken.EncodingForModel("gpt-4")
+	gpt4oTokenEncoder, err := tiktoken.EncodingForModel("gpt-4o")
 	if err != nil {
 		common.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
 	}
@@ -33,7 +34,11 @@ func InitTokenEncoders() {
 		if strings.HasPrefix(model, "gpt-3.5") {
 			tokenEncoderMap[model] = gpt35TokenEncoder
 		} else if strings.HasPrefix(model, "gpt-4") {
-			tokenEncoderMap[model] = gpt4TokenEncoder
+			if strings.HasPrefix(model, "gpt-4o") {
+				tokenEncoderMap[model] = gpt4oTokenEncoder
+			} else {
+				tokenEncoderMap[model] = gpt4TokenEncoder
+			}
 		} else {
 			tokenEncoderMap[model] = nil
 		}
@@ -62,7 +67,11 @@ func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
 	return len(tokenEncoder.Encode(text, nil, nil))
 }
 
-func getImageToken(imageUrl *dto.MessageImageUrl) (int, error) {
+func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (int, error) {
+	// TODO: 非流模式下不计算图片token数量
+	if model == "glm-4v" {
+		return 1047, nil
+	}
 	if imageUrl.Detail == "low" {
 		return 85, nil
 	}
@@ -118,7 +127,7 @@ func getImageToken(imageUrl *dto.MessageImageUrl) (int, error) {
 
 func CountTokenChatRequest(request dto.GeneralOpenAIRequest, model string, checkSensitive bool) (int, error, bool) {
 	tkm := 0
-	msgTokens, err, b := CountTokenMessages(request.Messages, model, checkSensitive)
+	msgTokens, err, b := CountTokenMessages(request.Messages, model, request.Stream, checkSensitive)
 	if err != nil {
 		return 0, err, b
 	}
@@ -151,7 +160,7 @@ func CountTokenChatRequest(request dto.GeneralOpenAIRequest, model string, check
 	return tkm, nil, false
 }
 
-func CountTokenMessages(messages []dto.Message, model string, checkSensitive bool) (int, error, bool) {
+func CountTokenMessages(messages []dto.Message, model string, stream bool, checkSensitive bool) (int, error, bool) {
 	//recover when panic
 	tokenEncoder := getTokenEncoder(model)
 	// Reference:
@@ -188,19 +197,13 @@ func CountTokenMessages(messages []dto.Message, model string, checkSensitive boo
 					tokenNum += getTokenNum(tokenEncoder, *message.Name)
 				}
 			} else {
-				var err error
 				arrayContent := message.ParseContent()
 				for _, m := range arrayContent {
 					if m.Type == "image_url" {
-						var imageTokenNum int
-						if model == "glm-4v" {
-							imageTokenNum = 1047
-						} else {
-							imageUrl := m.ImageUrl.(dto.MessageImageUrl)
-							imageTokenNum, err = getImageToken(&imageUrl)
-							if err != nil {
-								return 0, err, false
-							}
+						imageUrl := m.ImageUrl.(dto.MessageImageUrl)
+						imageTokenNum, err := getImageToken(&imageUrl, model, stream)
+						if err != nil {
+							return 0, err, false
 						}
 						tokenNum += imageTokenNum
 						log.Printf("image token num: %d", imageTokenNum)

web/src/components/ChannelsTable.js

@@ -6,6 +6,7 @@ import {
   showError,
   showInfo,
   showSuccess,
+  showWarning,
   timestamp2string,
 } from '../helpers';
 
@@ -309,6 +310,12 @@ const ChannelsTable = () => {
 
   const setChannelFormat = (channels) => {
     for (let i = 0; i < channels.length; i++) {
+      // if (channels[i].type === 8) {
+      //   showWarning(
+      //     '检测到您使用了“自定义渠道”类型，请更换为“OpenAI”渠道类型！',
+      //   );
+      //   showWarning('下个版本将不再支持“自定义渠道”类型！');
+      // }
       channels[i].key = '' + channels[i].id;
       let test_models = [];
       channels[i].models.split(',').forEach((item, index) => {

web/src/components/LogsTable.js

@@ -294,11 +294,39 @@ const LogsTable = () => {
         );
       },
     },
+    {
+      title: '重试',
+      dataIndex: 'retry',
+      className: isAdmin() ? 'tableShow' : 'tableHiddle',
+      render: (text, record, index) => {
+        let content = '渠道：' + record.channel;
+        if (record.other !== '') {
+          let other = JSON.parse(record.other);
+          if (other === null) {
+            return <></>
+          }
+          if (other.admin_info !== undefined) {
+            if (
+              other.admin_info.use_channel !== null &&
+              other.admin_info.use_channel !== undefined &&
+              other.admin_info.use_channel !== ''
+            ) {
+              // channel id array
+              let useChannel = other.admin_info.use_channel;
+              let useChannelStr = useChannel.join('->');
+              content = `渠道：${useChannelStr}`;
+            }
+          }
+        }
+        return isAdminUser ? <div>{content}</div> : <></>;
+      },
+    },
     {
       title: '详情',
       dataIndex: 'content',
       render: (text, record, index) => {
-        if (record.other === '') {
+        let other = JSON.parse(record.other);
+        if (other == null) {
           return (
             <Paragraph
               ellipsis={{
@@ -314,7 +342,6 @@ const LogsTable = () => {
             </Paragraph>
           );
         }
-        let other = JSON.parse(record.other);
         let content = renderModelPrice(
           record.prompt_tokens,
           record.completion_tokens,

web/src/components/ModelPricing.js

@@ -1,7 +1,16 @@
-import React, { useContext, useEffect, useState } from 'react';
+import React, { useContext, useEffect, useRef, useState } from 'react';
 import { API, copy, showError, showSuccess } from '../helpers';
 
-import { Banner, Layout, Modal, Table, Tag, Tooltip } from '@douyinfe/semi-ui';
+import {
+  Banner,
+  Input,
+  Layout,
+  Modal,
+  Space,
+  Table,
+  Tag,
+  Tooltip,
+} from '@douyinfe/semi-ui';
 import { stringToColor } from '../helpers/render.js';
 import { UserContext } from '../context/User/index.js';
 import Text from '@douyinfe/semi-ui/lib/es/typography/text';
@@ -45,6 +54,27 @@ function renderAvailable(available) {
 }
 
 const ModelPricing = () => {
+  const [filteredValue, setFilteredValue] = useState([]);
+  const compositionRef = useRef({ isComposition: false });
+
+  const handleChange = (value) => {
+    if (compositionRef.current.isComposition) {
+      return;
+    }
+    const newFilteredValue = value ? [value] : [];
+    setFilteredValue(newFilteredValue);
+  };
+  const handleCompositionStart = () => {
+    compositionRef.current.isComposition = true;
+  };
+
+  const handleCompositionEnd = (event) => {
+    compositionRef.current.isComposition = false;
+    const value = event.target.value;
+    const newFilteredValue = value ? [value] : [];
+    setFilteredValue(newFilteredValue);
+  };
+
   const columns = [
     {
       title: '可用性',
@@ -52,28 +82,28 @@ const ModelPricing = () => {
       render: (text, record, index) => {
         return renderAvailable(text);
       },
+      sorter: (a, b) => a.available - b.available,
     },
     {
-      title: '提供者',
-      dataIndex: 'owner_by',
-      render: (text, record, index) => {
-        return (
-          <>
-            <Tag color={stringToColor(text)} size='large'>
-              {text}
-            </Tag>
-          </>
-        );
-      },
-    },
-    {
-      title: '模型名称',
+      title: (
+        <Space>
+          <span>模型名称</span>
+          <Input
+            placeholder='模糊搜索'
+            style={{ width: 200 }}
+            onCompositionStart={handleCompositionStart}
+            onCompositionEnd={handleCompositionEnd}
+            onChange={handleChange}
+            showClear
+          />
+        </Space>
+      ),
       dataIndex: 'model_name', // 以finish_time作为dataIndex
       render: (text, record, index) => {
         return (
           <>
             <Tag
-              color={stringToColor(record.owner_by)}
+              color={stringToColor(text)}
               size='large'
               onClick={() => {
                 copyText(text);
@@ -84,6 +114,8 @@ const ModelPricing = () => {
           </>
         );
       },
+      onFilter: (value, record) => record.model_name.includes(value),
+      filteredValue,
     },
     {
       title: '计费类型',
@@ -91,6 +123,7 @@ const ModelPricing = () => {
       render: (text, record, index) => {
         return renderQuotaType(parseInt(text));
       },
+      sorter: (a, b) => a.quota_type - b.quota_type,
     },
     {
       title: '模型倍率',
@@ -113,11 +146,10 @@ const ModelPricing = () => {
       render: (text, record, index) => {
         let content = text;
         if (record.quota_type === 0) {
-          let inputRatioPrice = record.model_ratio * 2.0 * record.group_ratio;
+          let inputRatioPrice = record.model_ratio * 2 * record.group_ratio;
           let completionRatioPrice =
             record.model_ratio *
             record.completion_ratio *
-            2.0 *
             record.group_ratio;
           content = (
             <>
@@ -150,14 +182,17 @@ const ModelPricing = () => {
       return a.quota_type - b.quota_type;
     });
 
-    // sort by owner_by, openai is max, other use localeCompare
+    // sort by model_name, start with gpt is max, other use localeCompare
     models.sort((a, b) => {
-      if (a.owner_by === 'openai') {
+      if (a.model_name.startsWith('gpt') && !b.model_name.startsWith('gpt')) {
         return -1;
-      } else if (b.owner_by === 'openai') {
+      } else if (
+        !a.model_name.startsWith('gpt') &&
+        b.model_name.startsWith('gpt')
+      ) {
         return 1;
       } else {
-        return a.owner_by.localeCompare(b.owner_by);
+        return a.model_name.localeCompare(b.model_name);
       }
     });
 

web/src/constants/channel.constants.js

@@ -36,13 +36,6 @@ export const CHANNEL_OPTIONS = [
     color: 'teal',
     label: 'Azure OpenAI',
   },
-  {
-    key: 11,
-    text: 'Google PaLM2',
-    value: 11,
-    color: 'orange',
-    label: 'Google PaLM2',
-  },
   {
     key: 24,
     text: 'Google Gemini',
@@ -92,10 +85,18 @@ export const CHANNEL_OPTIONS = [
     color: 'purple',
     label: '智谱 GLM-4V',
   },
+  {
+    key: 11,
+    text: 'Google PaLM2',
+    value: 11,
+    color: 'orange',
+    label: 'Google PaLM2',
+  },
   { key: 25, text: 'Moonshot', value: 25, color: 'green', label: 'Moonshot' },
   { key: 19, text: '360 智脑', value: 19, color: 'blue', label: '360 智脑' },
   { key: 23, text: '腾讯混元', value: 23, color: 'teal', label: '腾讯混元' },
   { key: 31, text: '零一万物', value: 31, color: 'green', label: '零一万物' },
+  { key: 35, text: 'MiniMax', value: 35, color: 'green', label: 'MiniMax' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink', label: '自定义渠道' },
   {
     key: 22,

web/src/helpers/render.js

@@ -150,7 +150,7 @@ export function renderModelPrice(
       completionRatio = 0;
     }
     let inputRatioPrice = modelRatio * 2.0 * groupRatio;
-    let completionRatioPrice = modelRatio * completionRatio * 2.0 * groupRatio;
+    let completionRatioPrice = modelRatio * completionRatio * groupRatio;
     let price =
       (inputTokens / 1000000) * inputRatioPrice +
       (completionTokens / 1000000) * completionRatioPrice;

web/src/pages/Channel/EditChannel.js

@@ -301,17 +301,18 @@ const EditChannel = (props) => {
   const addCustomModels = () => {
     if (customModel.trim() === '') return;
     // 使用逗号分隔字符串，然后去除每个模型名称前后的空格
-    const modelArray = customModel.split(',').map(model => model.trim());
-    
+    const modelArray = customModel.split(',').map((model) => model.trim());
+
     let localModels = [...inputs.models];
     let localModelOptions = [...modelOptions];
     let hasError = false;
 
-    modelArray.forEach(model => {
+    modelArray.forEach((model) => {
       // 检查模型是否已存在，且模型名称非空
       if (model && !localModels.includes(model)) {
         localModels.push(model); // 添加到模型列表
-        localModelOptions.push({ // 添加到下拉选项
+        localModelOptions.push({
+          // 添加到下拉选项
           key: model,
           text: model,
           value: model,
@@ -330,7 +331,6 @@ const EditChannel = (props) => {
     handleInputChange('models', localModels);
   };
 
-
   return (
     <>
       <SideSheet
@@ -433,11 +433,15 @@ const EditChannel = (props) => {
           {inputs.type === 8 && (
             <>
               <div style={{ marginTop: 10 }}>
-                <Typography.Text strong>Base URL：</Typography.Text>
+                <Typography.Text strong>
+                  完整的 Base URL，支持变量{'{model}'}：
+                </Typography.Text>
               </div>
               <Input
                 name='base_url'
-                placeholder={'请输入自定义渠道的 Base URL'}
+                placeholder={
+                  '请输入完整的URL，例如：https://api.openai.com/v1/chat/completions'
+                }
                 onChange={(value) => {
                   handleInputChange('base_url', value);
                 }}

web/src/pages/Setting/Operation/SettingsMagnification.js

@@ -135,7 +135,7 @@ export default function SettingsMagnification(props) {
             <Row gutter={16}>
               <Col span={16}>
                 <Form.TextArea
-                  label={'模型补全倍率'}
+                  label={'模型补全倍率（仅对自定义模型有效）'}
                   extraText={'仅对自定义模型有效'}
                   placeholder={'为一个 JSON 文本，键为模型名称，值为倍率'}
                   field={'CompletionRatio'}