fix: 修复multipart表单字段内容复制问题

README.md

@@ -141,7 +141,6 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 - `NOTIFICATION_LIMIT_DURATION_MINUTE`：邮件等通知限制持续时间，默认 `10`分钟
 - `NOTIFY_LIMIT_COUNT`：用户通知在指定持续时间内的最大数量，默认 `2`
 - `ERROR_LOG_ENABLED=true`: 是否记录并显示错误日志，默认`false`
-- `TASK_PRICE_PATCH=sora-2-all,sora-2-pro-all`: 异步任务设置某些模型按次计费，多个模型用逗号分隔，例如`sora-2-all,sora-2-pro-all`，表示sora-2-all和sora-2-pro-all模型异步任务仅按次计费，不按秒等计费。
 
 ## 部署
 

common/constants.go

@@ -159,15 +159,14 @@ var (
 	GlobalWebRateLimitNum      int
 	GlobalWebRateLimitDuration int64
 
-	CriticalRateLimitEnable   bool
-	CriticalRateLimitNum            = 20
-	CriticalRateLimitDuration int64 = 20 * 60
-
 	UploadRateLimitNum            = 10
 	UploadRateLimitDuration int64 = 60
 
 	DownloadRateLimitNum            = 10
 	DownloadRateLimitDuration int64 = 60
+
+	CriticalRateLimitNum            = 20
+	CriticalRateLimitDuration int64 = 20 * 60
 )
 
 var RateLimitKeyExpirationDuration = 20 * time.Minute

common/init.go

@@ -99,9 +99,6 @@ func InitEnv() {
 	GlobalWebRateLimitNum = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration = int64(GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT_DURATION", 180))
 
-	CriticalRateLimitEnable = GetEnvOrDefaultBool("CRITICAL_RATE_LIMIT_ENABLE", true)
-	CriticalRateLimitNum = GetEnvOrDefault("CRITICAL_RATE_LIMIT", 20)
-	CriticalRateLimitDuration = int64(GetEnvOrDefault("CRITICAL_RATE_LIMIT_DURATION", 20*60))
 	initConstantEnv()
 }
 

controller/channel-test.go

@@ -617,10 +617,6 @@ func TestAllChannels(c *gin.Context) {
 var autoTestChannelsOnce sync.Once
 
 func AutomaticallyTestChannels() {
-	// 只在Master节点定时测试渠道
-	if !common.IsMasterNode {
-		return
-	}
 	autoTestChannelsOnce.Do(func() {
 		for {
 			if !operation_setting.GetMonitorSetting().AutoTestChannelEnabled {

controller/channel.go

@@ -649,15 +649,13 @@ func DeleteDisabledChannel(c *gin.Context) {
 }
 
 type ChannelTag struct {
-	Tag            string  `json:"tag"`
-	NewTag         *string `json:"new_tag"`
-	Priority       *int64  `json:"priority"`
-	Weight         *uint   `json:"weight"`
-	ModelMapping   *string `json:"model_mapping"`
-	Models         *string `json:"models"`
-	Groups         *string `json:"groups"`
-	ParamOverride  *string `json:"param_override"`
-	HeaderOverride *string `json:"header_override"`
+	Tag          string  `json:"tag"`
+	NewTag       *string `json:"new_tag"`
+	Priority     *int64  `json:"priority"`
+	Weight       *uint   `json:"weight"`
+	ModelMapping *string `json:"model_mapping"`
+	Models       *string `json:"models"`
+	Groups       *string `json:"groups"`
 }
 
 func DisableTagChannels(c *gin.Context) {
@@ -723,29 +721,7 @@ func EditTagChannels(c *gin.Context) {
 		})
 		return
 	}
-	if channelTag.ParamOverride != nil {
-		trimmed := strings.TrimSpace(*channelTag.ParamOverride)
-		if trimmed != "" && !json.Valid([]byte(trimmed)) {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "参数覆盖必须是合法的 JSON 格式",
-			})
-			return
-		}
-		channelTag.ParamOverride = common.GetPointer[string](trimmed)
-	}
-	if channelTag.HeaderOverride != nil {
-		trimmed := strings.TrimSpace(*channelTag.HeaderOverride)
-		if trimmed != "" && !json.Valid([]byte(trimmed)) {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "请求头覆盖必须是合法的 JSON 格式",
-			})
-			return
-		}
-		channelTag.HeaderOverride = common.GetPointer[string](trimmed)
-	}
-	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight, channelTag.ParamOverride, channelTag.HeaderOverride)
+	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight)
 	if err != nil {
 		common.ApiError(c, err)
 		return

dto/claude.go

@@ -510,44 +510,11 @@ func (c *ClaudeResponse) GetClaudeError() *types.ClaudeError {
 }
 
 type ClaudeUsage struct {
-	InputTokens              int                       `json:"input_tokens"`
-	CacheCreationInputTokens int                       `json:"cache_creation_input_tokens"`
-	CacheReadInputTokens     int                       `json:"cache_read_input_tokens"`
-	OutputTokens             int                       `json:"output_tokens"`
-	CacheCreation            *ClaudeCacheCreationUsage `json:"cache_creation,omitempty"`
-	// claude cache 1h
-	ClaudeCacheCreation5mTokens int                  `json:"claude_cache_creation_5_m_tokens"`
-	ClaudeCacheCreation1hTokens int                  `json:"claude_cache_creation_1_h_tokens"`
-	ServerToolUse               *ClaudeServerToolUse `json:"server_tool_use,omitempty"`
-}
-
-type ClaudeCacheCreationUsage struct {
-	Ephemeral5mInputTokens int `json:"ephemeral_5m_input_tokens,omitempty"`
-	Ephemeral1hInputTokens int `json:"ephemeral_1h_input_tokens,omitempty"`
-}
-
-func (u *ClaudeUsage) GetCacheCreation5mTokens() int {
-	if u == nil || u.CacheCreation == nil {
-		return 0
-	}
-	return u.CacheCreation.Ephemeral5mInputTokens
-}
-
-func (u *ClaudeUsage) GetCacheCreation1hTokens() int {
-	if u == nil || u.CacheCreation == nil {
-		return 0
-	}
-	return u.CacheCreation.Ephemeral1hInputTokens
-}
-
-func (u *ClaudeUsage) GetCacheCreationTotalTokens() int {
-	if u == nil {
-		return 0
-	}
-	if u.CacheCreationInputTokens > 0 {
-		return u.CacheCreationInputTokens
-	}
-	return u.GetCacheCreation5mTokens() + u.GetCacheCreation1hTokens()
+	InputTokens              int                  `json:"input_tokens"`
+	CacheCreationInputTokens int                  `json:"cache_creation_input_tokens"`
+	CacheReadInputTokens     int                  `json:"cache_read_input_tokens"`
+	OutputTokens             int                  `json:"output_tokens"`
+	ServerToolUse            *ClaudeServerToolUse `json:"server_tool_use,omitempty"`
 }
 
 type ClaudeServerToolUse struct {

dto/openai_request.go

@@ -232,13 +232,10 @@ func (r *GeneralOpenAIRequest) GetSystemRoleName() string {
 	return "system"
 }
 
-const CustomType = "custom"
-
 type ToolCallRequest struct {
 	ID       string          `json:"id,omitempty"`
 	Type     string          `json:"type"`
-	Function FunctionRequest `json:"function,omitempty"`
-	Custom   json.RawMessage `json:"custom,omitempty"`
+	Function FunctionRequest `json:"function"`
 }
 
 type FunctionRequest struct {

dto/openai_response.go

@@ -230,11 +230,6 @@ type Usage struct {
 	InputTokens            int                `json:"input_tokens"`
 	OutputTokens           int                `json:"output_tokens"`
 	InputTokensDetails     *InputTokenDetails `json:"input_tokens_details"`
-
-	// claude cache 1h
-	ClaudeCacheCreation5mTokens int `json:"claude_cache_creation_5_m_tokens"`
-	ClaudeCacheCreation1hTokens int `json:"claude_cache_creation_1_h_tokens"`
-
 	// OpenRouter Params
 	Cost any `json:"cost,omitempty"`
 }

logger/logger.go

@@ -67,10 +67,8 @@ func LogError(ctx context.Context, msg string) {
 }
 
 func LogDebug(ctx context.Context, msg string, args ...any) {
+	msg = fmt.Sprintf(msg, args...)
 	if common.DebugEnabled {
-		if len(args) > 0 {
-			msg = fmt.Sprintf(msg, args...)
-		}
 		logHelper(ctx, loggerDebug, msg)
 	}
 }

middleware/rate-limit.go

@@ -102,10 +102,7 @@ func GlobalAPIRateLimit() func(c *gin.Context) {
 }
 
 func CriticalRateLimit() func(c *gin.Context) {
-	if common.CriticalRateLimitEnable {
-		return rateLimitFactory(common.CriticalRateLimitNum, common.CriticalRateLimitDuration, "CT")
-	}
-	return defNext
+	return rateLimitFactory(common.CriticalRateLimitNum, common.CriticalRateLimitDuration, "CT")
 }
 
 func DownloadRateLimit() func(c *gin.Context) {

model/channel.go

@@ -138,11 +138,9 @@ func (channel *Channel) GetNextEnabledKey() (string, int, *types.NewAPIError) {
 			enabledIdx = append(enabledIdx, i)
 		}
 	}
-	// If no specific status list or none enabled, return an explicit error so caller can
-	// properly handle a channel with no available keys (e.g. mark channel disabled).
-	// Returning the first key here caused requests to keep using an already-disabled key.
+	// If no specific status list or none enabled, fall back to first key
 	if len(enabledIdx) == 0 {
-		return "", 0, types.NewError(errors.New("no enabled keys"), types.ErrorCodeChannelNoAvailableKey)
+		return keys[0], 0, nil
 	}
 
 	switch channel.ChannelInfo.MultiKeyMode {
@@ -690,7 +688,7 @@ func DisableChannelByTag(tag string) error {
 	return err
 }
 
-func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *string, group *string, priority *int64, weight *uint, paramOverride *string, headerOverride *string) error {
+func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *string, group *string, priority *int64, weight *uint) error {
 	updateData := Channel{}
 	shouldReCreateAbilities := false
 	updatedTag := tag
@@ -716,12 +714,6 @@ func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *
 	if weight != nil {
 		updateData.Weight = weight
 	}
-	if paramOverride != nil {
-		updateData.ParamOverride = paramOverride
-	}
-	if headerOverride != nil {
-		updateData.HeaderOverride = headerOverride
-	}
 
 	err := DB.Model(&Channel{}).Where("tag = ?", tag).Updates(updateData).Error
 	if err != nil {

relay/channel/ali/image.go

@@ -98,9 +98,9 @@ func oaiFormEdit2AliImageEdit(c *gin.Context, info *relaycommon.RelayInfo, reque
 		return nil, errors.New("image is required")
 	}
 
-	//if len(imageFiles) > 1 {
-	//	return nil, errors.New("only one image is supported for qwen edit")
-	//}
+	if len(imageFiles) > 1 {
+		return nil, errors.New("only one image is supported for qwen edit")
+	}
 
 	// 获取base64编码的图片
 	var imageBase64s []string

relay/channel/claude/relay-claude.go

@@ -189,9 +189,7 @@ func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRe
 		// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
 		claudeRequest.TopP = 0
 		claudeRequest.Temperature = common.GetPointer[float64](1.0)
-		if !model_setting.ShouldPreserveThinkingSuffix(textRequest.Model) {
-			claudeRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
-		}
+		claudeRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
 	}
 
 	if textRequest.ReasoningEffort != "" {
@@ -598,8 +596,6 @@ func FormatClaudeResponseInfo(requestMode int, claudeResponse *dto.ClaudeRespons
 			claudeInfo.Usage.PromptTokens = claudeResponse.Message.Usage.InputTokens
 			claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Message.Usage.CacheReadInputTokens
 			claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Message.Usage.CacheCreationInputTokens
-			claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Message.Usage.GetCacheCreation5mTokens()
-			claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Message.Usage.GetCacheCreation1hTokens()
 			claudeInfo.Usage.CompletionTokens = claudeResponse.Message.Usage.OutputTokens
 		} else if claudeResponse.Type == "content_block_delta" {
 			if claudeResponse.Delta.Text != nil {
@@ -744,8 +740,6 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 		claudeInfo.Usage.TotalTokens = claudeResponse.Usage.InputTokens + claudeResponse.Usage.OutputTokens
 		claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
 		claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
-		claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Usage.GetCacheCreation5mTokens()
-		claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Usage.GetCacheCreation1hTokens()
 	}
 	var responseData []byte
 	switch info.RelayFormat {

relay/channel/gemini/adaptor.go

@@ -127,8 +127,7 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 
-	if model_setting.GetGeminiSettings().ThinkingAdapterEnabled &&
-		!model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) {
+	if model_setting.GetGeminiSettings().ThinkingAdapterEnabled {
 		// 新增逻辑：处理 -thinking-<budget> 格式
 		if strings.Contains(info.UpstreamModelName, "-thinking-") {
 			parts := strings.Split(info.UpstreamModelName, "-thinking-")

relay/channel/openai/adaptor.go

@@ -27,7 +27,6 @@ import (
 	"github.com/QuantumNous/new-api/relay/common_handler"
 	relayconstant "github.com/QuantumNous/new-api/relay/constant"
 	"github.com/QuantumNous/new-api/service"
-	"github.com/QuantumNous/new-api/setting/model_setting"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -225,8 +224,7 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 			request.Usage = json.RawMessage(`{"include":true}`)
 		}
 		// 适配 OpenRouter 的 thinking 后缀
-		if !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) &&
-			strings.HasSuffix(info.UpstreamModelName, "-thinking") {
+		if strings.HasSuffix(info.UpstreamModelName, "-thinking") {
 			info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
 			request.Model = info.UpstreamModelName
 			if len(request.Reasoning) == 0 {

relay/channel/openai/relay-openai.go

@@ -122,10 +122,6 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 	var usage = &dto.Usage{}
 	var streamItems []string // store stream items
 	var lastStreamData string
-	var secondLastStreamData string // 存储倒数第二个stream data，用于音频模型
-
-	// 检查是否为音频模型
-	isAudioModel := strings.Contains(strings.ToLower(model), "audio")
 
 	helper.StreamScannerHandler(c, resp, info, func(data string) bool {
 		if lastStreamData != "" {
@@ -135,35 +131,12 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 			}
 		}
 		if len(data) > 0 {
-			// 对音频模型，保存倒数第二个stream data
-			if isAudioModel && lastStreamData != "" {
-				secondLastStreamData = lastStreamData
-			}
-
 			lastStreamData = data
 			streamItems = append(streamItems, data)
 		}
 		return true
 	})
 
-	// 对音频模型，从倒数第二个stream data中提取usage信息
-	if isAudioModel && secondLastStreamData != "" {
-		var streamResp struct {
-			Usage *dto.Usage `json:"usage"`
-		}
-		err := json.Unmarshal([]byte(secondLastStreamData), &streamResp)
-		if err == nil && streamResp.Usage != nil && service.ValidUsage(streamResp.Usage) {
-			usage = streamResp.Usage
-			containStreamUsage = true
-
-			if common.DebugEnabled {
-				logger.LogDebug(c, fmt.Sprintf("Audio model usage extracted from second last SSE: PromptTokens=%d, CompletionTokens=%d, TotalTokens=%d, InputTokens=%d, OutputTokens=%d",
-					usage.PromptTokens, usage.CompletionTokens, usage.TotalTokens,
-					usage.InputTokens, usage.OutputTokens))
-			}
-		}
-	}
-
 	// 处理最后的响应
 	shouldSendLastResp := true
 	if err := handleLastResponse(lastStreamData, &responseId, &createAt, &systemFingerprint, &model, &usage,

relay/channel/task/ali/adaptor.go

@@ -5,17 +5,14 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"strconv"
 	"strings"
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/dto"
-	"github.com/QuantumNous/new-api/logger"
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/relay/channel"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/service"
-	"github.com/samber/lo"
 
 	"github.com/gin-gonic/gin"
 	"github.com/pkg/errors"
@@ -111,7 +108,6 @@ type TaskAdaptor struct {
 	ChannelType int
 	apiKey      string
 	baseURL     string
-	aliReq      *AliVideoRequest
 }
 
 func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
@@ -122,16 +118,6 @@ func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
 
 func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.TaskError) {
 	// 阿里通义万相支持 JSON 格式，不使用 multipart
-	var taskReq relaycommon.TaskSubmitReq
-	if err := common.UnmarshalBodyReusable(c, &taskReq); err != nil {
-		return service.TaskErrorWrapper(err, "unmarshal_task_request_failed", http.StatusBadRequest)
-	}
-	aliReq, err := a.convertToAliRequest(info, taskReq)
-	if err != nil {
-		return service.TaskErrorWrapper(err, "convert_to_ali_request_failed", http.StatusInternalServerError)
-	}
-	a.aliReq = aliReq
-	logger.LogJson(c, "ali video request body", aliReq)
 	return relaycommon.ValidateMultipartDirect(c, info)
 }
 
@@ -148,7 +134,13 @@ func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info
 }
 
 func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayInfo) (io.Reader, error) {
-	bodyBytes, err := common.Marshal(a.aliReq)
+	var taskReq relaycommon.TaskSubmitReq
+	if err := common.UnmarshalBodyReusable(c, &taskReq); err != nil {
+		return nil, errors.Wrap(err, "unmarshal_task_request_failed")
+	}
+	aliReq := a.convertToAliRequest(taskReq)
+
+	bodyBytes, err := common.Marshal(aliReq)
 	if err != nil {
 		return nil, errors.Wrap(err, "marshal_ali_request_failed")
 	}
@@ -156,98 +148,7 @@ func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayIn
 	return bytes.NewReader(bodyBytes), nil
 }
 
-var (
-	size480p = []string{
-		"832*480",
-		"480*832",
-		"624*624",
-	}
-	size720p = []string{
-		"1280*720",
-		"720*1280",
-		"960*960",
-		"1088*832",
-		"832*1088",
-	}
-	size1080p = []string{
-		"1920*1080",
-		"1080*1920",
-		"1440*1440",
-		"1632*1248",
-		"1248*1632",
-	}
-)
-
-func sizeToResolution(size string) (string, error) {
-	if lo.Contains(size480p, size) {
-		return "480P", nil
-	} else if lo.Contains(size720p, size) {
-		return "720P", nil
-	} else if lo.Contains(size1080p, size) {
-		return "1080P", nil
-	}
-	return "", fmt.Errorf("invalid size: %s", size)
-}
-
-func ProcessAliOtherRatios(aliReq *AliVideoRequest) (map[string]float64, error) {
-	otherRatios := make(map[string]float64)
-	aliRatios := map[string]map[string]float64{
-		"wan2.5-t2v-preview": {
-			"480P":  1,
-			"720P":  2,
-			"1080P": 1 / 0.3,
-		},
-		"wan2.2-t2v-plus": {
-			"480P":  1,
-			"1080P": 0.7 / 0.14,
-		},
-		"wan2.5-i2v-preview": {
-			"480P":  1,
-			"720P":  2,
-			"1080P": 1 / 0.3,
-		},
-		"wan2.2-i2v-plus": {
-			"480P":  1,
-			"1080P": 0.7 / 0.14,
-		},
-		"wan2.2-kf2v-flash": {
-			"480P":  1,
-			"720P":  2,
-			"1080P": 4.8,
-		},
-		"wan2.2-i2v-flash": {
-			"480P": 1,
-			"720P": 2,
-		},
-		"wan2.2-s2v": {
-			"480P": 1,
-			"720P": 0.9 / 0.5,
-		},
-	}
-	var resolution string
-
-	// size match
-	if aliReq.Parameters.Size != "" {
-		toResolution, err := sizeToResolution(aliReq.Parameters.Size)
-		if err != nil {
-			return nil, err
-		}
-		resolution = toResolution
-	} else {
-		resolution = strings.ToUpper(aliReq.Parameters.Resolution)
-		if !strings.HasSuffix(resolution, "P") {
-			resolution = resolution + "P"
-		}
-	}
-	if otherRatio, ok := aliRatios[aliReq.Model]; ok {
-		if ratio, ok := otherRatio[resolution]; ok {
-			otherRatios[fmt.Sprintf("resolution-%s", resolution)] = ratio
-		}
-	}
-	return otherRatios, nil
-}
-
-func (a *TaskAdaptor) convertToAliRequest(info *relaycommon.RelayInfo, req relaycommon.TaskSubmitReq) (*AliVideoRequest, error) {
+func (a *TaskAdaptor) convertToAliRequest(req relaycommon.TaskSubmitReq) *AliVideoRequest {
 	aliReq := &AliVideoRequest{
 		Model: req.Model,
 		Input: AliVideoInput{
@@ -262,53 +163,28 @@ func (a *TaskAdaptor) convertToAliRequest(info *relaycommon.RelayInfo, req relay
 
 	// 处理分辨率映射
 	if req.Size != "" {
-		// text to video size must be contained *
-		if strings.Contains(req.Model, "t2v") && !strings.Contains(req.Size, "*") {
-			return nil, fmt.Errorf("invalid size: %s, example: %s", req.Size, "1920*1080")
-		}
-		if strings.Contains(req.Size, "*") {
-			aliReq.Parameters.Size = req.Size
-		} else {
-			resolution := strings.ToUpper(req.Size)
-			// 支持 480p, 720p, 1080p 或 480P, 720P, 1080P
-			if !strings.HasSuffix(resolution, "P") {
-				resolution = resolution + "P"
-			}
-			aliReq.Parameters.Resolution = resolution
+		resolution := strings.ToUpper(req.Size)
+		// 支持 480p, 720p, 1080p 或 480P, 720P, 1080P
+		if !strings.HasSuffix(resolution, "P") {
+			resolution = resolution + "P"
 		}
+		aliReq.Parameters.Resolution = resolution
 	} else {
 		// 根据模型设置默认分辨率
-		if strings.Contains(req.Model, "t2v") { // image to video
-			if strings.HasPrefix(req.Model, "wan2.5") {
-				aliReq.Parameters.Size = "1920*1080"
-			} else if strings.HasPrefix(req.Model, "wan2.2") {
-				aliReq.Parameters.Size = "1920*1080"
-			} else {
-				aliReq.Parameters.Size = "1280*720"
-			}
+		if strings.HasPrefix(req.Model, "wan2.5") {
+			aliReq.Parameters.Resolution = "1080P"
+		} else if strings.HasPrefix(req.Model, "wan2.2-i2v-flash") {
+			aliReq.Parameters.Resolution = "720P"
+		} else if strings.HasPrefix(req.Model, "wan2.2-i2v-plus") {
+			aliReq.Parameters.Resolution = "1080P"
 		} else {
-			if strings.HasPrefix(req.Model, "wan2.5") {
-				aliReq.Parameters.Resolution = "1080P"
-			} else if strings.HasPrefix(req.Model, "wan2.2-i2v-flash") {
-				aliReq.Parameters.Resolution = "720P"
-			} else if strings.HasPrefix(req.Model, "wan2.2-i2v-plus") {
-				aliReq.Parameters.Resolution = "1080P"
-			} else {
-				aliReq.Parameters.Resolution = "720P"
-			}
+			aliReq.Parameters.Resolution = "720P"
 		}
 	}
 
 	// 处理时长
 	if req.Duration > 0 {
 		aliReq.Parameters.Duration = req.Duration
-	} else if req.Seconds != "" {
-		seconds, err := strconv.Atoi(req.Seconds)
-		if err != nil {
-			return nil, errors.Wrap(err, "convert seconds to int failed")
-		} else {
-			aliReq.Parameters.Duration = seconds
-		}
 	} else {
 		aliReq.Parameters.Duration = 5 // 默认5秒
 	}
@@ -316,32 +192,11 @@ func (a *TaskAdaptor) convertToAliRequest(info *relaycommon.RelayInfo, req relay
 	// 从 metadata 中提取额外参数
 	if req.Metadata != nil {
 		if metadataBytes, err := common.Marshal(req.Metadata); err == nil {
-			err = common.Unmarshal(metadataBytes, aliReq)
-			if err != nil {
-				return nil, errors.Wrap(err, "unmarshal metadata failed")
-			}
-		} else {
-			return nil, errors.Wrap(err, "marshal metadata failed")
+			_ = common.Unmarshal(metadataBytes, aliReq)
 		}
 	}
 
-	if aliReq.Model != req.Model {
-		return nil, errors.New("can't change model with metadata")
-	}
-
-	info.PriceData.OtherRatios = map[string]float64{
-		"seconds": float64(aliReq.Parameters.Duration),
-	}
-
-	ratios, err := ProcessAliOtherRatios(aliReq)
-	if err != nil {
-		return nil, err
-	}
-	for s, f := range ratios {
-		info.PriceData.OtherRatios[s] = f
-	}
-
-	return aliReq, nil
+	return aliReq
 }
 
 // DoRequest delegates to common helper

relay/channel/task/jimeng/adaptor.go

@@ -406,15 +406,12 @@ func (a *TaskAdaptor) convertToRequestPayload(req *relaycommon.TaskSubmitReq) (*
 	// 即梦视频3.0 ReqKey转换
 	// https://www.volcengine.com/docs/85621/1792707
 	if strings.Contains(r.ReqKey, "jimeng_v30") {
-		if r.ReqKey == "jimeng_v30_pro" {
-			// 3.0 pro只有固定的jimeng_ti2v_v30_pro
-			r.ReqKey = "jimeng_ti2v_v30_pro"
-		} else if len(req.Images) > 1 {
+		if len(req.Images) > 1 {
 			// 多张图片：首尾帧生成
-			r.ReqKey = strings.TrimSuffix(strings.Replace(r.ReqKey, "jimeng_v30", "jimeng_i2v_first_tail_v30", 1), "p")
+			r.ReqKey = strings.Replace(r.ReqKey, "jimeng_v30", "jimeng_i2v_first_tail_v30", 1)
 		} else if len(req.Images) == 1 {
 			// 单张图片：图生视频
-			r.ReqKey = strings.TrimSuffix(strings.Replace(r.ReqKey, "jimeng_v30", "jimeng_i2v_first_v30", 1), "p")
+			r.ReqKey = strings.Replace(r.ReqKey, "jimeng_v30", "jimeng_i2v_first_v30", 1)
 		} else {
 			// 无图片：文生视频
 			r.ReqKey = strings.Replace(r.ReqKey, "jimeng_v30", "jimeng_t2v_v30", 1)

relay/channel/task/sora/adaptor.go

@@ -2,9 +2,13 @@ package sora
 
 import (
 	"bytes"
+	"encoding/json"
 	"fmt"
 	"io"
+	"mime"
+	"mime/multipart"
 	"net/http"
+	"strings"
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/dto"
@@ -87,9 +91,107 @@ func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayIn
 	if err != nil {
 		return nil, errors.Wrap(err, "get_request_body_failed")
 	}
+
+	// 检查是否需要模型重定向
+	if !info.IsModelMapped {
+		// 如果不需要重定向，直接返回原始请求体
+		return bytes.NewReader(cachedBody), nil
+	}
+
+	contentType := c.Request.Header.Get("Content-Type")
+
+	// 处理multipart/form-data请求
+	if strings.Contains(contentType, "multipart/form-data") {
+		return buildRequestBodyWithMappedModel(cachedBody, contentType, info.UpstreamModelName)
+	}
+	// 处理JSON请求
+	if strings.Contains(contentType, "application/json") {
+		var jsonData map[string]interface{}
+		if err := json.Unmarshal(cachedBody, &jsonData); err != nil {
+			return nil, errors.Wrap(err, "unmarshal_json_failed")
+		}
+
+		// 替换model字段为映射后的模型名
+		jsonData["model"] = info.UpstreamModelName
+
+		// 重新编码为JSON
+		newBody, err := json.Marshal(jsonData)
+		if err != nil {
+			return nil, errors.Wrap(err, "marshal_json_failed")
+		}
+
+		return bytes.NewReader(newBody), nil
+	}
+
 	return bytes.NewReader(cachedBody), nil
 }
 
+func buildRequestBodyWithMappedModel(originalBody []byte, contentType, redirectedModel string) (io.Reader, error) {
+	newBuffer := &bytes.Buffer{}
+	writer := multipart.NewWriter(newBuffer)
+
+	_, params, err := mime.ParseMediaType(contentType)
+	if err != nil {
+		return nil, errors.Wrap(err, "parse_content_type_failed")
+	}
+	boundary, ok := params["boundary"]
+	if !ok {
+		return nil, errors.New("boundary_not_found_in_content_type")
+	}
+	if err := writer.SetBoundary(boundary); err != nil {
+		return nil, errors.Wrap(err, "set_boundary_failed")
+	}
+	r := multipart.NewReader(bytes.NewReader(originalBody), boundary)
+
+	for {
+		part, err := r.NextPart()
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			return nil, errors.Wrap(err, "read_multipart_part_failed")
+		}
+
+		fieldName := part.FormName()
+
+		if fieldName == "model" {
+			// 修改 model 字段为映射后的模型名
+			if err := writer.WriteField("model", redirectedModel); err != nil {
+				return nil, errors.Wrap(err, "write_model_field_failed")
+			}
+		} else {
+			// 对于其他字段，保留原始内容
+			if part.FileName() != "" {
+				newPart, err := writer.CreatePart(part.Header)
+				if err != nil {
+					return nil, errors.Wrap(err, "create_form_file_failed")
+				}
+				if _, err := io.Copy(newPart, part); err != nil {
+					return nil, errors.Wrap(err, "copy_file_content_failed")
+				}
+			} else {
+				newPart, err := writer.CreatePart(part.Header)
+				if err != nil {
+					return nil, errors.Wrap(err, "create_form_field_failed")
+				}
+				if _, err := io.Copy(newPart, part); err != nil {
+					return nil, errors.Wrap(err, "copy_field_content_failed")
+				}
+			}
+		}
+
+		if err := part.Close(); err != nil {
+			return nil, errors.Wrap(err, "close_part_failed")
+		}
+	}
+
+	if err := writer.Close(); err != nil {
+		return nil, errors.Wrap(err, "close_multipart_writer_failed")
+	}
+
+	return newBuffer, nil
+}
+
 // DoRequest delegates to common helper.
 func (a *TaskAdaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoTaskApiRequest(a, c, info, requestBody)

relay/channel/vertex/adaptor.go

@@ -168,8 +168,7 @@ func (a *Adaptor) getRequestUrl(info *relaycommon.RelayInfo, modelName, suffix s
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	suffix := ""
 	if a.RequestMode == RequestModeGemini {
-		if model_setting.GetGeminiSettings().ThinkingAdapterEnabled &&
-			!model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) {
+		if model_setting.GetGeminiSettings().ThinkingAdapterEnabled {
 			// 新增逻辑：处理 -thinking-<budget> 格式
 			if strings.Contains(info.UpstreamModelName, "-thinking-") {
 				parts := strings.Split(info.UpstreamModelName, "-thinking-")

relay/channel/volcengine/adaptor.go

@@ -16,7 +16,6 @@ import (
 	"github.com/QuantumNous/new-api/relay/channel/openai"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/relay/constant"
-	"github.com/QuantumNous/new-api/setting/model_setting"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -292,9 +291,7 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 		return nil, errors.New("request is nil")
 	}
 
-	if !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) &&
-		strings.HasSuffix(info.UpstreamModelName, "-thinking") &&
-		strings.HasPrefix(info.UpstreamModelName, "deepseek") {
+	if strings.HasSuffix(info.UpstreamModelName, "-thinking") && strings.HasPrefix(info.UpstreamModelName, "deepseek") {
 		info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
 		request.Model = info.UpstreamModelName
 		request.THINKING = json.RawMessage(`{"type": "enabled"}`)

relay/claude_handler.go

@@ -67,9 +67,7 @@ func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 			request.TopP = 0
 			request.Temperature = common.GetPointer[float64](1.0)
 		}
-		if !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) {
-			request.Model = strings.TrimSuffix(request.Model, "-thinking")
-		}
+		request.Model = strings.TrimSuffix(request.Model, "-thinking")
 		info.UpstreamModelName = request.Model
 	}
 

relay/common/relay_utils.go

@@ -121,7 +121,6 @@ func ValidateMultipartDirect(c *gin.Context, info *RelayInfo) *dto.TaskError {
 
 	prompt = req.Prompt
 	model = req.Model
-	size = req.Size
 	seconds, _ = strconv.Atoi(req.Seconds)
 	if seconds == 0 {
 		seconds = req.Duration
@@ -224,6 +223,11 @@ func ValidateBasicTaskRequest(c *gin.Context, info *RelayInfo, action string) *d
 		}
 	}
 
+	// 模型映射
+	if info.IsModelMapped {
+		req.Model = info.UpstreamModelName
+	}
+
 	storeTaskRequest(c, info, action, req)
 	return nil
 }

relay/helper/price.go

@@ -13,9 +13,6 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
-// https://docs.claude.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration
-const claudeCacheCreation1hMultiplier = 6 / 3.75
-
 // HandleGroupRatio checks for "auto_group" in the context and updates the group ratio and relayInfo.UsingGroup if present
 func HandleGroupRatio(ctx *gin.Context, relayInfo *relaycommon.RelayInfo) types.GroupRatioInfo {
 	groupRatioInfo := types.GroupRatioInfo{
@@ -56,8 +53,6 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
 	var cacheRatio float64
 	var imageRatio float64
 	var cacheCreationRatio float64
-	var cacheCreationRatio5m float64
-	var cacheCreationRatio1h float64
 	var audioRatio float64
 	var audioCompletionRatio float64
 	var freeModel bool
@@ -81,9 +76,6 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
 		completionRatio = ratio_setting.GetCompletionRatio(info.OriginModelName)
 		cacheRatio, _ = ratio_setting.GetCacheRatio(info.OriginModelName)
 		cacheCreationRatio, _ = ratio_setting.GetCreateCacheRatio(info.OriginModelName)
-		cacheCreationRatio5m = cacheCreationRatio
-		// 固定1h和5min缓存写入价格的比例
-		cacheCreationRatio1h = cacheCreationRatio * claudeCacheCreation1hMultiplier
 		imageRatio, _ = ratio_setting.GetImageRatio(info.OriginModelName)
 		audioRatio = ratio_setting.GetAudioRatio(info.OriginModelName)
 		audioCompletionRatio = ratio_setting.GetAudioCompletionRatio(info.OriginModelName)
@@ -124,8 +116,6 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
 		AudioRatio:           audioRatio,
 		AudioCompletionRatio: audioCompletionRatio,
 		CacheCreationRatio:   cacheCreationRatio,
-		CacheCreation5mRatio: cacheCreationRatio5m,
-		CacheCreation1hRatio: cacheCreationRatio1h,
 		QuotaToPreConsume:    preConsumedQuota,
 	}
 

relay/relay_task.go

@@ -17,6 +17,7 @@ import (
 	"github.com/QuantumNous/new-api/relay/channel"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	relayconstant "github.com/QuantumNous/new-api/relay/constant"
+	"github.com/QuantumNous/new-api/relay/helper"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
 
@@ -38,6 +39,11 @@ func RelayTaskSubmit(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.
 	}
 
 	info.InitChannelMeta(c)
+
+	// 模型映射
+	if err := helper.ModelMappedHelper(c, info, nil); err != nil {
+		return service.TaskErrorWrapper(err, "model_mapped_failed", http.StatusBadRequest)
+	}
 	adaptor := GetTaskAdaptor(platform)
 	if adaptor == nil {
 		return service.TaskErrorWrapperLocal(fmt.Errorf("invalid api platform: %s", platform), "invalid_api_platform", http.StatusBadRequest)
@@ -208,6 +214,10 @@ func RelayTaskSubmit(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.
 	task.Quota = quota
 	task.Data = taskData
 	task.Action = info.Action
+	task.Properties = model.Properties{
+		UpstreamModelName: info.UpstreamModelName,
+		OriginModelName:   info.OriginModelName,
+	}
 	err = task.Insert()
 	if err != nil {
 		taskErr = service.TaskErrorWrapper(err, "insert_task_failed", http.StatusInternalServerError)

service/log_info_generate.go

@@ -92,23 +92,11 @@ func GenerateAudioOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 }
 
 func GenerateClaudeOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelRatio, groupRatio, completionRatio float64,
-	cacheTokens int, cacheRatio float64,
-	cacheCreationTokens int, cacheCreationRatio float64,
-	cacheCreationTokens5m int, cacheCreationRatio5m float64,
-	cacheCreationTokens1h int, cacheCreationRatio1h float64,
-	modelPrice float64, userGroupRatio float64) map[string]interface{} {
+	cacheTokens int, cacheRatio float64, cacheCreationTokens int, cacheCreationRatio float64, modelPrice float64, userGroupRatio float64) map[string]interface{} {
 	info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, cacheTokens, cacheRatio, modelPrice, userGroupRatio)
 	info["claude"] = true
 	info["cache_creation_tokens"] = cacheCreationTokens
 	info["cache_creation_ratio"] = cacheCreationRatio
-	if cacheCreationTokens5m != 0 {
-		info["cache_creation_tokens_5m"] = cacheCreationTokens5m
-		info["cache_creation_ratio_5m"] = cacheCreationRatio5m
-	}
-	if cacheCreationTokens1h != 0 {
-		info["cache_creation_tokens_1h"] = cacheCreationTokens1h
-		info["cache_creation_ratio_1h"] = cacheCreationRatio1h
-	}
 	return info
 }
 

service/quota.go

@@ -251,11 +251,7 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	cacheTokens := usage.PromptTokensDetails.CachedTokens
 
 	cacheCreationRatio := relayInfo.PriceData.CacheCreationRatio
-	cacheCreationRatio5m := relayInfo.PriceData.CacheCreation5mRatio
-	cacheCreationRatio1h := relayInfo.PriceData.CacheCreation1hRatio
 	cacheCreationTokens := usage.PromptTokensDetails.CachedCreationTokens
-	cacheCreationTokens5m := usage.ClaudeCacheCreation5mTokens
-	cacheCreationTokens1h := usage.ClaudeCacheCreation1hTokens
 
 	if relayInfo.ChannelType == constant.ChannelTypeOpenRouter {
 		promptTokens -= cacheTokens
@@ -273,12 +269,7 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	if !relayInfo.PriceData.UsePrice {
 		calculateQuota = float64(promptTokens)
 		calculateQuota += float64(cacheTokens) * cacheRatio
-		calculateQuota += float64(cacheCreationTokens5m) * cacheCreationRatio5m
-		calculateQuota += float64(cacheCreationTokens1h) * cacheCreationRatio1h
-		remainingCacheCreationTokens := cacheCreationTokens - cacheCreationTokens5m - cacheCreationTokens1h
-		if remainingCacheCreationTokens > 0 {
-			calculateQuota += float64(remainingCacheCreationTokens) * cacheCreationRatio
-		}
+		calculateQuota += float64(cacheCreationTokens) * cacheCreationRatio
 		calculateQuota += float64(completionTokens) * completionRatio
 		calculateQuota = calculateQuota * groupRatio * modelRatio
 	} else {
@@ -331,11 +322,7 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	}
 
 	other := GenerateClaudeOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio,
-		cacheTokens, cacheRatio,
-		cacheCreationTokens, cacheCreationRatio,
-		cacheCreationTokens5m, cacheCreationRatio5m,
-		cacheCreationTokens1h, cacheCreationRatio1h,
-		modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
+		cacheTokens, cacheRatio, cacheCreationTokens, cacheCreationRatio, modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
 	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
 		ChannelId:        relayInfo.ChannelId,
 		PromptTokens:     promptTokens,

setting/model_setting/global.go

@@ -1,23 +1,16 @@
 package model_setting
 
 import (
-	"strings"
-
 	"github.com/QuantumNous/new-api/setting/config"
 )
 
 type GlobalSettings struct {
-	PassThroughRequestEnabled bool     `json:"pass_through_request_enabled"`
-	ThinkingModelBlacklist    []string `json:"thinking_model_blacklist"`
+	PassThroughRequestEnabled bool `json:"pass_through_request_enabled"`
 }
 
 // 默认配置
 var defaultOpenaiSettings = GlobalSettings{
 	PassThroughRequestEnabled: false,
-	ThinkingModelBlacklist: []string{
-		"moonshotai/kimi-k2-thinking",
-		"kimi-k2-thinking",
-	},
 }
 
 // 全局实例
@@ -31,18 +24,3 @@ func init() {
 func GetGlobalSettings() *GlobalSettings {
 	return &globalSettings
 }
-
-// ShouldPreserveThinkingSuffix 判断模型是否配置为保留 thinking/-nothinking 后缀
-func ShouldPreserveThinkingSuffix(modelName string) bool {
-	target := strings.TrimSpace(modelName)
-	if target == "" {
-		return false
-	}
-
-	for _, entry := range globalSettings.ThinkingModelBlacklist {
-		if strings.TrimSpace(entry) == target {
-			return true
-		}
-	}
-	return false
-}

types/price_data.go

@@ -15,8 +15,6 @@ type PriceData struct {
 	CompletionRatio      float64
 	CacheRatio           float64
 	CacheCreationRatio   float64
-	CacheCreation5mRatio float64
-	CacheCreation1hRatio float64
 	ImageRatio           float64
 	AudioRatio           float64
 	AudioCompletionRatio float64
@@ -33,5 +31,5 @@ type PerCallPriceData struct {
 }
 
 func (p PriceData) ToSetting() string {
-	return fmt.Sprintf("ModelPrice: %f, ModelRatio: %f, CompletionRatio: %f, CacheRatio: %f, GroupRatio: %f, UsePrice: %t, CacheCreationRatio: %f, CacheCreation5mRatio: %f, CacheCreation1hRatio: %f, QuotaToPreConsume: %d, ImageRatio: %f, AudioRatio: %f, AudioCompletionRatio: %f", p.ModelPrice, p.ModelRatio, p.CompletionRatio, p.CacheRatio, p.GroupRatioInfo.GroupRatio, p.UsePrice, p.CacheCreationRatio, p.CacheCreation5mRatio, p.CacheCreation1hRatio, p.QuotaToPreConsume, p.ImageRatio, p.AudioRatio, p.AudioCompletionRatio)
+	return fmt.Sprintf("ModelPrice: %f, ModelRatio: %f, CompletionRatio: %f, CacheRatio: %f, GroupRatio: %f, UsePrice: %t, CacheCreationRatio: %f, QuotaToPreConsume: %d, ImageRatio: %f, AudioRatio: %f, AudioCompletionRatio: %f", p.ModelPrice, p.ModelRatio, p.CompletionRatio, p.CacheRatio, p.GroupRatioInfo.GroupRatio, p.UsePrice, p.CacheCreationRatio, p.QuotaToPreConsume, p.ImageRatio, p.AudioRatio, p.AudioCompletionRatio)
 }

web/src/components/settings/ModelSetting.jsx

@@ -37,7 +37,6 @@ const ModelSetting = () => {
     'claude.default_max_tokens': '',
     'claude.thinking_adapter_budget_tokens_percentage': 0.8,
     'global.pass_through_request_enabled': false,
-    'global.thinking_model_blacklist': '[]',
     'general_setting.ping_interval_enabled': false,
     'general_setting.ping_interval_seconds': 60,
     'gemini.thinking_adapter_enabled': false,
@@ -57,8 +56,7 @@ const ModelSetting = () => {
           item.key === 'gemini.version_settings' ||
           item.key === 'claude.model_headers_settings' ||
           item.key === 'claude.default_max_tokens' ||
-          item.key === 'gemini.supported_imagine_models' ||
-          item.key === 'global.thinking_model_blacklist'
+          item.key === 'gemini.supported_imagine_models'
         ) {
           if (item.value !== '') {
             item.value = JSON.stringify(JSON.parse(item.value), null, 2);

web/src/components/table/channels/modals/EditTagModal.jsx

@@ -45,7 +45,6 @@ import {
   IconBookmark,
   IconUser,
   IconCode,
-  IconSetting,
 } from '@douyinfe/semi-icons';
 import { getChannelModels } from '../../../../helpers';
 import { useTranslation } from 'react-i18next';
@@ -70,8 +69,6 @@ const EditTagModal = (props) => {
     model_mapping: null,
     groups: [],
     models: [],
-    param_override: null,
-    header_override: null,
   };
   const [inputs, setInputs] = useState(originInputs);
   const formApiRef = useRef(null);
@@ -193,48 +190,12 @@ const EditTagModal = (props) => {
     if (formVals.models && formVals.models.length > 0) {
       data.models = formVals.models.join(',');
     }
-    if (
-      formVals.param_override !== undefined &&
-      formVals.param_override !== null
-    ) {
-      if (typeof formVals.param_override !== 'string') {
-        showInfo('参数覆盖必须是合法的 JSON 格式！');
-        setLoading(false);
-        return;
-      }
-      const trimmedParamOverride = formVals.param_override.trim();
-      if (trimmedParamOverride !== '' && !verifyJSON(trimmedParamOverride)) {
-        showInfo('参数覆盖必须是合法的 JSON 格式！');
-        setLoading(false);
-        return;
-      }
-      data.param_override = trimmedParamOverride;
-    }
-    if (
-      formVals.header_override !== undefined &&
-      formVals.header_override !== null
-    ) {
-      if (typeof formVals.header_override !== 'string') {
-        showInfo('请求头覆盖必须是合法的 JSON 格式！');
-        setLoading(false);
-        return;
-      }
-      const trimmedHeaderOverride = formVals.header_override.trim();
-      if (trimmedHeaderOverride !== '' && !verifyJSON(trimmedHeaderOverride)) {
-        showInfo('请求头覆盖必须是合法的 JSON 格式！');
-        setLoading(false);
-        return;
-      }
-      data.header_override = trimmedHeaderOverride;
-    }
     data.new_tag = formVals.new_tag;
     if (
       data.model_mapping === undefined &&
       data.groups === undefined &&
       data.models === undefined &&
-      data.new_tag === undefined &&
-      data.param_override === undefined &&
-      data.header_override === undefined
+      data.new_tag === undefined
     ) {
       showWarning('没有任何修改！');
       setLoading(false);
@@ -530,157 +491,6 @@ const EditTagModal = (props) => {
                 </div>
               </Card>
 
-              <Card className='!rounded-2xl shadow-sm border-0 mb-6'>
-                {/* Header: Advanced Settings */}
-                <div className='flex items-center mb-2'>
-                  <Avatar size='small' color='orange' className='mr-2 shadow-md'>
-                    <IconSetting size={16} />
-                  </Avatar>
-                  <div>
-                    <Text className='text-lg font-medium'>{t('高级设置')}</Text>
-                    <div className='text-xs text-gray-600'>
-                      {t('渠道的高级配置选项')}
-                    </div>
-                  </div>
-                </div>
-
-                <div className='space-y-4'>
-                  <Form.TextArea
-                    field='param_override'
-                    label={t('参数覆盖')}
-                    placeholder={
-                      t(
-                        '此项可选，用于覆盖请求参数。不支持覆盖 stream 参数',
-                      ) +
-                      '\n' +
-                      t('旧格式（直接覆盖）：') +
-                      '\n{\n  "temperature": 0,\n  "max_tokens": 1000\n}' +
-                      '\n\n' +
-                      t('新格式（支持条件判断与json自定义）：') +
-                      '\n{\n  "operations": [\n    {\n      "path": "temperature",\n      "mode": "set",\n      "value": 0.7,\n      "conditions": [\n        {\n          "path": "model",\n          "mode": "prefix",\n          "value": "gpt"\n        }\n      ]\n    }\n  ]\n}'
-                    }
-                    autosize
-                    showClear
-                    onChange={(value) =>
-                      handleInputChange('param_override', value)
-                    }
-                    extraText={
-                      <div className='flex gap-2 flex-wrap'>
-                        <Text
-                          className='!text-semi-color-primary cursor-pointer'
-                          onClick={() =>
-                            handleInputChange(
-                              'param_override',
-                              JSON.stringify({ temperature: 0 }, null, 2),
-                            )
-                          }
-                        >
-                          {t('旧格式模板')}
-                        </Text>
-                        <Text
-                          className='!text-semi-color-primary cursor-pointer'
-                          onClick={() =>
-                            handleInputChange(
-                              'param_override',
-                              JSON.stringify(
-                                {
-                                  operations: [
-                                    {
-                                      path: 'temperature',
-                                      mode: 'set',
-                                      value: 0.7,
-                                      conditions: [
-                                        {
-                                          path: 'model',
-                                          mode: 'prefix',
-                                          value: 'gpt',
-                                        },
-                                      ],
-                                      logic: 'AND',
-                                    },
-                                  ],
-                                },
-                                null,
-                                2,
-                              ),
-                            )
-                          }
-                        >
-                          {t('新格式模板')}
-                        </Text>
-                        <Text
-                          className='!text-semi-color-primary cursor-pointer'
-                          onClick={() =>
-                            handleInputChange('param_override', null)
-                          }
-                        >
-                          {t('不更改')}
-                        </Text>
-                      </div>
-                    }
-                  />
-
-                  <Form.TextArea
-                    field='header_override'
-                    label={t('请求头覆盖')}
-                    placeholder={
-                      t('此项可选，用于覆盖请求头参数') +
-                      '\n' +
-                      t('格式示例：') +
-                      '\n{\n  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36 Edg/139.0.0.0",\n  "Authorization": "Bearer {api_key}"\n}'
-                    }
-                    autosize
-                    showClear
-                    onChange={(value) =>
-                      handleInputChange('header_override', value)
-                    }
-                    extraText={
-                      <div className='flex flex-col gap-1'>
-                        <div className='flex gap-2 flex-wrap items-center'>
-                          <Text
-                            className='!text-semi-color-primary cursor-pointer'
-                            onClick={() =>
-                              handleInputChange(
-                                'header_override',
-                                JSON.stringify(
-                                  {
-                                    'User-Agent':
-                                      'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36 Edg/139.0.0.0',
-                                    Authorization: 'Bearer {api_key}',
-                                  },
-                                  null,
-                                  2,
-                                ),
-                              )
-                            }
-                          >
-                            {t('填入模板')}
-                          </Text>
-                          <Text
-                            className='!text-semi-color-primary cursor-pointer'
-                            onClick={() =>
-                              handleInputChange('header_override', null)
-                            }
-                          >
-                            {t('不更改')}
-                          </Text>
-                        </div>
-                        <div>
-                          <Text type='tertiary' size='small'>
-                            {t('支持变量：')}
-                          </Text>
-                          <div className='text-xs text-tertiary ml-2'>
-                            <div>
-                              {t('渠道密钥')}: {'{api_key}'}
-                            </div>
-                          </div>
-                        </div>
-                      </div>
-                    }
-                  />
-                </div>
-              </Card>
-
               <Card className='!rounded-2xl shadow-sm border-0'>
                 {/* Header: Group Settings */}
                 <div className='flex items-center mb-2'>

web/src/components/table/model-pricing/filter/PricingTags.jsx

@@ -44,7 +44,7 @@ const PricingTags = ({
     (allModels.length > 0 ? allModels : models).forEach((model) => {
       if (model.tags) {
         model.tags
-          .split(/[,;|]+/) // 逗号、分号或竖线（保留空格，允许多词标签如 "open weights"）
+          .split(/[,;|\s]+/) // 逗号、分号、竖线或空白字符
           .map((tag) => tag.trim())
           .filter(Boolean)
           .forEach((tag) => tagSet.add(tag.toLowerCase()));
@@ -64,7 +64,7 @@ const PricingTags = ({
         if (!model.tags) return false;
         return model.tags
           .toLowerCase()
-          .split(/[,;|]+/)
+          .split(/[,;|\s]+/)
           .map((tg) => tg.trim())
           .includes(tagLower);
       }).length;

web/src/components/table/tokens/modals/EditTokenModal.jsx

@@ -66,9 +66,9 @@ const EditTokenModal = (props) => {
 
   const getInitValues = () => ({
     name: '',
-    remain_quota: 0,
+    remain_quota: 500000,
     expired_time: -1,
-    unlimited_quota: true,
+    unlimited_quota: false,
     model_limits_enabled: false,
     model_limits: [],
     allow_ips: '',

web/src/components/table/usage-logs/UsageLogsColumnDefs.jsx

@@ -551,10 +551,6 @@ export const getLogsColumns = ({
               other.cache_ratio || 1.0,
               other.cache_creation_tokens || 0,
               other.cache_creation_ratio || 1.0,
-              other.cache_creation_tokens_5m || 0,
-              other.cache_creation_ratio_5m || other.cache_creation_ratio || 1.0,
-              other.cache_creation_tokens_1h || 0,
-              other.cache_creation_ratio_1h || other.cache_creation_ratio || 1.0,
               false,
               1.0,
               other?.is_system_prompt_overwritten,
@@ -569,10 +565,6 @@ export const getLogsColumns = ({
               other.cache_ratio || 1.0,
               0,
               1.0,
-              0,
-              1.0,
-              0,
-              1.0,
               false,
               1.0,
               other?.is_system_prompt_overwritten,

web/src/helpers/base64.js

@@ -1,56 +0,0 @@
-/*
-Copyright (C) 2025 QuantumNous
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU Affero General Public License as
-published by the Free Software Foundation, either version 3 of the
-License, or (at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-GNU Affero General Public License for more details.
-
-You should have received a copy of the GNU Affero General Public License
-along with this program. If not, see <https://www.gnu.org/licenses/>.
-
-For commercial licensing, please contact support@quantumnous.com
-*/
-
-const toBinaryString = (text) => {
-  if (typeof TextEncoder !== 'undefined') {
-    const bytes = new TextEncoder().encode(text);
-    let binary = '';
-
-    bytes.forEach((byte) => {
-      binary += String.fromCharCode(byte);
-    });
-
-    return binary;
-  }
-
-  return encodeURIComponent(text).replace(/%([0-9A-F]{2})/g, (_, hex) =>
-    String.fromCharCode(parseInt(hex, 16)),
-  );
-};
-
-export const encodeToBase64 = (value) => {
-  const input = value == null ? '' : String(value);
-
-  if (typeof window === 'undefined') {
-    if (typeof Buffer !== 'undefined') {
-      return Buffer.from(input, 'utf-8').toString('base64');
-    }
-    if (
-      typeof globalThis !== 'undefined' &&
-      typeof globalThis.btoa === 'function'
-    ) {
-      return globalThis.btoa(toBinaryString(input));
-    }
-    throw new Error(
-      'Base64 encoding is unavailable in the current environment',
-    );
-  }
-
-  return window.btoa(toBinaryString(input));
-};

web/src/helpers/index.js

@@ -20,7 +20,6 @@ For commercial licensing, please contact support@quantumnous.com
 export * from './history';
 export * from './auth';
 export * from './utils';
-export * from './base64';
 export * from './api';
 export * from './render';
 export * from './log';

web/src/helpers/render.jsx

@@ -1046,10 +1046,6 @@ function renderPriceSimpleCore({
   cacheRatio = 1.0,
   cacheCreationTokens = 0,
   cacheCreationRatio = 1.0,
-  cacheCreationTokens5m = 0,
-  cacheCreationRatio5m = 1.0,
-  cacheCreationTokens1h = 0,
-  cacheCreationRatio1h = 1.0,
   image = false,
   imageRatio = 1.0,
   isSystemPromptOverride = false,
@@ -1068,40 +1064,17 @@ function renderPriceSimpleCore({
     });
   }
 
-  const hasSplitCacheCreation =
-    cacheCreationTokens5m > 0 || cacheCreationTokens1h > 0;
-
-  const shouldShowLegacyCacheCreation =
-    !hasSplitCacheCreation && cacheCreationTokens !== 0;
-
-  const shouldShowCache = cacheTokens !== 0;
-  const shouldShowCacheCreation5m =
-    hasSplitCacheCreation && cacheCreationTokens5m > 0;
-  const shouldShowCacheCreation1h =
-    hasSplitCacheCreation && cacheCreationTokens1h > 0;
-
   const parts = [];
   // base: model ratio
   parts.push(i18next.t('模型: {{ratio}}'));
 
   // cache part (label differs when with image)
-  if (shouldShowCache) {
+  if (cacheTokens !== 0) {
     parts.push(i18next.t('缓存: {{cacheRatio}}'));
   }
 
-  if (hasSplitCacheCreation) {
-    if (shouldShowCacheCreation5m && shouldShowCacheCreation1h) {
-      parts.push(
-        i18next.t(
-          '缓存创建: 5m {{cacheCreationRatio5m}} / 1h {{cacheCreationRatio1h}}',
-        ),
-      );
-    } else if (shouldShowCacheCreation5m) {
-      parts.push(i18next.t('缓存创建: 5m {{cacheCreationRatio5m}}'));
-    } else if (shouldShowCacheCreation1h) {
-      parts.push(i18next.t('缓存创建: 1h {{cacheCreationRatio1h}}'));
-    }
-  } else if (shouldShowLegacyCacheCreation) {
+  // cache creation part (Claude specific if passed)
+  if (cacheCreationTokens !== 0) {
     parts.push(i18next.t('缓存创建: {{cacheCreationRatio}}'));
   }
 
@@ -1118,8 +1091,6 @@ function renderPriceSimpleCore({
     groupRatio: finalGroupRatio,
     cacheRatio: cacheRatio,
     cacheCreationRatio: cacheCreationRatio,
-    cacheCreationRatio5m: cacheCreationRatio5m,
-    cacheCreationRatio1h: cacheCreationRatio1h,
     imageRatio: imageRatio,
   });
 
@@ -1479,10 +1450,6 @@ export function renderModelPriceSimple(
   cacheRatio = 1.0,
   cacheCreationTokens = 0,
   cacheCreationRatio = 1.0,
-  cacheCreationTokens5m = 0,
-  cacheCreationRatio5m = 1.0,
-  cacheCreationTokens1h = 0,
-  cacheCreationRatio1h = 1.0,
   image = false,
   imageRatio = 1.0,
   isSystemPromptOverride = false,
@@ -1497,10 +1464,6 @@ export function renderModelPriceSimple(
     cacheRatio,
     cacheCreationTokens,
     cacheCreationRatio,
-    cacheCreationTokens5m,
-    cacheCreationRatio5m,
-    cacheCreationTokens1h,
-    cacheCreationRatio1h,
     image,
     imageRatio,
     isSystemPromptOverride,
@@ -1718,10 +1681,6 @@ export function renderClaudeModelPrice(
   cacheRatio = 1.0,
   cacheCreationTokens = 0,
   cacheCreationRatio = 1.0,
-  cacheCreationTokens5m = 0,
-  cacheCreationRatio5m = 1.0,
-  cacheCreationTokens1h = 0,
-  cacheCreationRatio1h = 1.0,
 ) {
   const { ratio: effectiveGroupRatio, label: ratioLabel } = getEffectiveRatio(
     groupRatio,
@@ -1751,121 +1710,20 @@ export function renderClaudeModelPrice(
     const completionRatioValue = completionRatio || 0;
     const inputRatioPrice = modelRatio * 2.0;
     const completionRatioPrice = modelRatio * 2.0 * completionRatioValue;
-    const cacheRatioPrice = modelRatio * 2.0 * cacheRatio;
-    const cacheCreationRatioPrice = modelRatio * 2.0 * cacheCreationRatio;
-    const cacheCreationRatioPrice5m = modelRatio * 2.0 * cacheCreationRatio5m;
-    const cacheCreationRatioPrice1h = modelRatio * 2.0 * cacheCreationRatio1h;
-
-    const hasSplitCacheCreation =
-      cacheCreationTokens5m > 0 || cacheCreationTokens1h > 0;
-
-    const shouldShowCache = cacheTokens > 0;
-    const shouldShowLegacyCacheCreation =
-      !hasSplitCacheCreation && cacheCreationTokens > 0;
-    const shouldShowCacheCreation5m =
-      hasSplitCacheCreation && cacheCreationTokens5m > 0;
-    const shouldShowCacheCreation1h =
-      hasSplitCacheCreation && cacheCreationTokens1h > 0;
+    let cacheRatioPrice = (modelRatio * 2.0 * cacheRatio).toFixed(2);
+    let cacheCreationRatioPrice = modelRatio * 2.0 * cacheCreationRatio;
 
     // Calculate effective input tokens (non-cached + cached with ratio applied + cache creation with ratio applied)
     const nonCachedTokens = inputTokens;
     const effectiveInputTokens =
       nonCachedTokens +
       cacheTokens * cacheRatio +
-      cacheCreationTokens * cacheCreationRatio +
-      cacheCreationTokens5m * cacheCreationRatio5m +
-      cacheCreationTokens1h * cacheCreationRatio1h;
+      cacheCreationTokens * cacheCreationRatio;
 
     let price =
       (effectiveInputTokens / 1000000) * inputRatioPrice * groupRatio +
       (completionTokens / 1000000) * completionRatioPrice * groupRatio;
 
-    const inputUnitPrice = inputRatioPrice * rate;
-    const completionUnitPrice = completionRatioPrice * rate;
-    const cacheUnitPrice = cacheRatioPrice * rate;
-    const cacheCreationUnitPrice = cacheCreationRatioPrice * rate;
-    const cacheCreationUnitPrice5m = cacheCreationRatioPrice5m * rate;
-    const cacheCreationUnitPrice1h = cacheCreationRatioPrice1h * rate;
-    const cacheCreationUnitPriceTotal =
-      cacheCreationUnitPrice5m + cacheCreationUnitPrice1h;
-
-    const breakdownSegments = [
-      i18next.t('提示 {{input}} tokens / 1M tokens * {{symbol}}{{price}}', {
-        input: inputTokens,
-        symbol,
-        price: inputUnitPrice.toFixed(6),
-      }),
-    ];
-
-    if (shouldShowCache) {
-      breakdownSegments.push(
-        i18next.t(
-          '缓存 {{tokens}} tokens / 1M tokens * {{symbol}}{{price}} (倍率: {{ratio}})',
-          {
-            tokens: cacheTokens,
-            symbol,
-            price: cacheUnitPrice.toFixed(6),
-            ratio: cacheRatio,
-          },
-        ),
-      );
-    }
-
-    if (shouldShowLegacyCacheCreation) {
-      breakdownSegments.push(
-        i18next.t(
-          '缓存创建 {{tokens}} tokens / 1M tokens * {{symbol}}{{price}} (倍率: {{ratio}})',
-          {
-            tokens: cacheCreationTokens,
-            symbol,
-            price: cacheCreationUnitPrice.toFixed(6),
-            ratio: cacheCreationRatio,
-          },
-        ),
-      );
-    }
-
-    if (shouldShowCacheCreation5m) {
-      breakdownSegments.push(
-        i18next.t(
-          '5m缓存创建 {{tokens}} tokens / 1M tokens * {{symbol}}{{price}} (倍率: {{ratio}})',
-          {
-            tokens: cacheCreationTokens5m,
-            symbol,
-            price: cacheCreationUnitPrice5m.toFixed(6),
-            ratio: cacheCreationRatio5m,
-          },
-        ),
-      );
-    }
-
-    if (shouldShowCacheCreation1h) {
-      breakdownSegments.push(
-        i18next.t(
-          '1h缓存创建 {{tokens}} tokens / 1M tokens * {{symbol}}{{price}} (倍率: {{ratio}})',
-          {
-            tokens: cacheCreationTokens1h,
-            symbol,
-            price: cacheCreationUnitPrice1h.toFixed(6),
-            ratio: cacheCreationRatio1h,
-          },
-        ),
-      );
-    }
-
-    breakdownSegments.push(
-      i18next.t(
-        '补全 {{completion}} tokens / 1M tokens * {{symbol}}{{price}}',
-        {
-          completion: completionTokens,
-          symbol,
-          price: completionUnitPrice.toFixed(6),
-        },
-      ),
-    );
-
-    const breakdownText = breakdownSegments.join(' + ');
-
     return (
       <>
         <article>
@@ -1886,7 +1744,7 @@ export function renderClaudeModelPrice(
               },
             )}
           </p>
-          {shouldShowCache && (
+          {cacheTokens > 0 && (
             <p>
               {i18next.t(
                 '缓存价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存倍率: {{cacheRatio}})',
@@ -1894,13 +1752,13 @@ export function renderClaudeModelPrice(
                   symbol: symbol,
                   price: (inputRatioPrice * rate).toFixed(6),
                   ratio: cacheRatio,
-                  total: cacheUnitPrice.toFixed(6),
+                  total: (cacheRatioPrice * rate).toFixed(2),
                   cacheRatio: cacheRatio,
                 },
               )}
             </p>
           )}
-          {shouldShowLegacyCacheCreation && (
+          {cacheCreationTokens > 0 && (
             <p>
               {i18next.t(
                 '缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})',
@@ -1908,65 +1766,49 @@ export function renderClaudeModelPrice(
                   symbol: symbol,
                   price: (inputRatioPrice * rate).toFixed(6),
                   ratio: cacheCreationRatio,
-                  total: cacheCreationUnitPrice.toFixed(6),
+                  total: (cacheCreationRatioPrice * rate).toFixed(6),
                   cacheCreationRatio: cacheCreationRatio,
                 },
               )}
             </p>
           )}
-          {shouldShowCacheCreation5m && (
-            <p>
-              {i18next.t(
-                '5m缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (5m缓存创建倍率: {{cacheCreationRatio5m}})',
-                {
-                  symbol: symbol,
-                  price: (inputRatioPrice * rate).toFixed(6),
-                  ratio: cacheCreationRatio5m,
-                  total: cacheCreationUnitPrice5m.toFixed(6),
-                  cacheCreationRatio5m: cacheCreationRatio5m,
-                },
-              )}
-            </p>
-          )}
-          {shouldShowCacheCreation1h && (
-            <p>
-              {i18next.t(
-                '1h缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (1h缓存创建倍率: {{cacheCreationRatio1h}})',
-                {
-                  symbol: symbol,
-                  price: (inputRatioPrice * rate).toFixed(6),
-                  ratio: cacheCreationRatio1h,
-                  total: cacheCreationUnitPrice1h.toFixed(6),
-                  cacheCreationRatio1h: cacheCreationRatio1h,
-                },
-              )}
-            </p>
-          )}
-          {shouldShowCacheCreation5m && shouldShowCacheCreation1h && (
-            <p>
-              {i18next.t(
-                '缓存创建价格合计：5m {{symbol}}{{five}} + 1h {{symbol}}{{one}} = {{symbol}}{{total}} / 1M tokens',
-                {
-                  symbol: symbol,
-                  five: cacheCreationUnitPrice5m.toFixed(6),
-                  one: cacheCreationUnitPrice1h.toFixed(6),
-                  total: cacheCreationUnitPriceTotal.toFixed(6),
-                },
-              )}
-            </p>
-          )}
           <p></p>
           <p>
-            {i18next.t(
-              '{{breakdown}} * {{ratioType}} {{ratio}} = {{symbol}}{{total}}',
-              {
-                breakdown: breakdownText,
-                ratioType: ratioLabel,
-                ratio: groupRatio,
-                symbol: symbol,
-                total: (price * rate).toFixed(6),
-              },
-            )}
+            {cacheTokens > 0 || cacheCreationTokens > 0
+              ? i18next.t(
+                  '提示 {{nonCacheInput}} tokens / 1M tokens * {{symbol}}{{price}} + 缓存 {{cacheInput}} tokens / 1M tokens * {{symbol}}{{cachePrice}} + 缓存创建 {{cacheCreationInput}} tokens / 1M tokens * {{symbol}}{{cacheCreationPrice}} + 补全 {{completion}} tokens / 1M tokens * {{symbol}}{{compPrice}} * {{ratioType}} {{ratio}} = {{symbol}}{{total}}',
+                  {
+                    nonCacheInput: nonCachedTokens,
+                    cacheInput: cacheTokens,
+                    cacheRatio: cacheRatio,
+                    cacheCreationInput: cacheCreationTokens,
+                    cacheCreationRatio: cacheCreationRatio,
+                    symbol: symbol,
+                    cachePrice: (cacheRatioPrice * rate).toFixed(2),
+                    cacheCreationPrice: (
+                      cacheCreationRatioPrice * rate
+                    ).toFixed(6),
+                    price: (inputRatioPrice * rate).toFixed(6),
+                    completion: completionTokens,
+                    compPrice: (completionRatioPrice * rate).toFixed(6),
+                    ratio: groupRatio,
+                    ratioType: ratioLabel,
+                    total: (price * rate).toFixed(6),
+                  },
+                )
+              : i18next.t(
+                  '提示 {{input}} tokens / 1M tokens * {{symbol}}{{price}} + 补全 {{completion}} tokens / 1M tokens * {{symbol}}{{compPrice}} * {{ratioType}} {{ratio}} = {{symbol}}{{total}}',
+                  {
+                    input: inputTokens,
+                    symbol: symbol,
+                    price: (inputRatioPrice * rate).toFixed(6),
+                    completion: completionTokens,
+                    compPrice: (completionRatioPrice * rate).toFixed(6),
+                    ratio: groupRatio,
+                    ratioType: ratioLabel,
+                    total: (price * rate).toFixed(6),
+                  },
+                )}
           </p>
           <p>{i18next.t('仅供参考，以实际扣费为准')}</p>
         </article>
@@ -1983,10 +1825,6 @@ export function renderClaudeLogContent(
   user_group_ratio,
   cacheRatio = 1.0,
   cacheCreationRatio = 1.0,
-  cacheCreationTokens5m = 0,
-  cacheCreationRatio5m = 1.0,
-  cacheCreationTokens1h = 0,
-  cacheCreationRatio1h = 1.0,
 ) {
   const { ratio: effectiveGroupRatio, label: ratioLabel } = getEffectiveRatio(
     groupRatio,
@@ -2005,58 +1843,17 @@ export function renderClaudeLogContent(
       ratio: groupRatio,
     });
   } else {
-    const hasSplitCacheCreation =
-      cacheCreationTokens5m > 0 || cacheCreationTokens1h > 0;
-    const shouldShowCacheCreation5m =
-      hasSplitCacheCreation && cacheCreationTokens5m > 0;
-    const shouldShowCacheCreation1h =
-      hasSplitCacheCreation && cacheCreationTokens1h > 0;
-
-    let cacheCreationPart = null;
-    if (hasSplitCacheCreation) {
-      if (shouldShowCacheCreation5m && shouldShowCacheCreation1h) {
-        cacheCreationPart = i18next.t(
-          '缓存创建倍率 5m {{cacheCreationRatio5m}} / 1h {{cacheCreationRatio1h}}',
-          {
-            cacheCreationRatio5m,
-            cacheCreationRatio1h,
-          },
-        );
-      } else if (shouldShowCacheCreation5m) {
-        cacheCreationPart = i18next.t(
-          '缓存创建倍率 5m {{cacheCreationRatio5m}}',
-          {
-            cacheCreationRatio5m,
-          },
-        );
-      } else if (shouldShowCacheCreation1h) {
-        cacheCreationPart = i18next.t(
-          '缓存创建倍率 1h {{cacheCreationRatio1h}}',
-          {
-            cacheCreationRatio1h,
-          },
-        );
-      }
-    }
-
-    if (!cacheCreationPart) {
-      cacheCreationPart = i18next.t('缓存创建倍率 {{cacheCreationRatio}}', {
-        cacheCreationRatio,
-      });
-    }
-
-    const parts = [
-      i18next.t('模型倍率 {{modelRatio}}', { modelRatio }),
-      i18next.t('输出倍率 {{completionRatio}}', { completionRatio }),
-      i18next.t('缓存倍率 {{cacheRatio}}', { cacheRatio }),
-      cacheCreationPart,
-      i18next.t('{{ratioType}} {{ratio}}', {
+    return i18next.t(
+      '模型倍率 {{modelRatio}}，输出倍率 {{completionRatio}}，缓存倍率 {{cacheRatio}}，缓存创建倍率 {{cacheCreationRatio}}，{{ratioType}} {{ratio}}',
+      {
+        modelRatio: modelRatio,
+        completionRatio: completionRatio,
+        cacheRatio: cacheRatio,
+        cacheCreationRatio: cacheCreationRatio,
         ratioType: ratioLabel,
         ratio: groupRatio,
-      }),
-    ];
-
-    return parts.join('，');
+      },
+    );
   }
 }
 

web/src/hooks/model-pricing/useModelPricingData.jsx

@@ -128,7 +128,7 @@ export const useModelPricingData = () => {
         if (!model.tags) return false;
         const tagsArr = model.tags
           .toLowerCase()
-          .split(/[,;|]+/)
+          .split(/[,;|\s]+/)
           .map((tag) => tag.trim())
           .filter(Boolean);
         return tagsArr.includes(tagLower);

web/src/hooks/model-pricing/usePricingFilterCounts.js

@@ -23,7 +23,7 @@ import { useMemo } from 'react';
 const normalizeTags = (tags = '') =>
   tags
     .toLowerCase()
-    .split(/[,;|]+/)
+    .split(/[,;|\s]+/)
     .map((t) => t.trim())
     .filter(Boolean);
 

web/src/hooks/tokens/useTokensData.jsx

@@ -20,13 +20,7 @@ For commercial licensing, please contact support@quantumnous.com
 import { useState, useEffect } from 'react';
 import { useTranslation } from 'react-i18next';
 import { Modal } from '@douyinfe/semi-ui';
-import {
-  API,
-  copy,
-  showError,
-  showSuccess,
-  encodeToBase64,
-} from '../../helpers';
+import { API, copy, showError, showSuccess } from '../../helpers';
 import { ITEMS_PER_PAGE } from '../../constants';
 import { useTableCompactMode } from '../common/useTableCompactMode';
 
@@ -142,7 +136,7 @@ export const useTokensData = (openFluentNotification) => {
         apiKey: 'sk-' + record.key,
       };
       let encodedConfig = encodeURIComponent(
-        encodeToBase64(JSON.stringify(cherryConfig)),
+        btoa(JSON.stringify(cherryConfig)),
       );
       url = url.replaceAll('{cherryConfig}', encodedConfig);
     } else {

web/src/hooks/usage-logs/useUsageLogsData.jsx

@@ -361,10 +361,6 @@ export const useLogsData = () => {
                 other?.user_group_ratio,
                 other.cache_ratio || 1.0,
                 other.cache_creation_ratio || 1.0,
-                other.cache_creation_tokens_5m || 0,
-                other.cache_creation_ratio_5m || other.cache_creation_ratio || 1.0,
-                other.cache_creation_tokens_1h || 0,
-                other.cache_creation_ratio_1h || other.cache_creation_ratio || 1.0,
               )
             : renderLogContent(
                 other?.model_ratio,
@@ -433,10 +429,6 @@ export const useLogsData = () => {
             other.cache_ratio || 1.0,
             other.cache_creation_tokens || 0,
             other.cache_creation_ratio || 1.0,
-            other.cache_creation_tokens_5m || 0,
-            other.cache_creation_ratio_5m || other.cache_creation_ratio || 1.0,
-            other.cache_creation_tokens_1h || 0,
-            other.cache_creation_ratio_1h || other.cache_creation_ratio || 1.0,
           );
         } else {
           content = renderModelPrice(

web/src/i18n/locales/en.json

@@ -561,9 +561,6 @@
     "启用绘图功能": "Enable drawing function",
     "启用请求体透传功能": "Enable request body pass-through functionality",
     "启用请求透传": "Enable request pass-through",
-    "禁用思考处理的模型列表": "Models skipping thinking handling",
-    "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀": "Models in this list will not automatically add or remove the -thinking/-nothinking suffix.",
-    "请输入JSON数组，如 [\"model-a\",\"model-b\"]": "Enter a JSON array, e.g. [\"model-a\",\"model-b\"]",
     "启用额度消费日志记录": "Enable quota consumption logging",
     "启用验证": "Enable Authentication",
     "周": "week",
@@ -1519,10 +1516,6 @@
     "缓存倍率": "Cache ratio",
     "缓存创建 Tokens": "Cache Creation Tokens",
     "缓存创建: {{cacheCreationRatio}}": "Cache creation: {{cacheCreationRatio}}",
-    "缓存创建: 5m {{cacheCreationRatio5m}}": "Cache creation: 5m {{cacheCreationRatio5m}}",
-    "缓存创建: 1h {{cacheCreationRatio1h}}": "Cache creation: 1h {{cacheCreationRatio1h}}",
-    "缓存创建倍率 5m {{cacheCreationRatio5m}}": "Cache creation multiplier 5m {{cacheCreationRatio5m}}",
-    "缓存创建倍率 1h {{cacheCreationRatio1h}}": "Cache creation multiplier 1h {{cacheCreationRatio1h}}",
     "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})": "Cache creation price: {{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (Cache creation ratio: {{cacheCreationRatio}})",
     "编辑": "Edit",
     "编辑API": "Edit API",
@@ -2111,4 +2104,4 @@
     "统一的": "The Unified",
     "大模型接口网关": "LLM API Gateway"
   }
-}
+}

web/src/i18n/locales/fr.json

@@ -564,9 +564,6 @@
     "启用绘图功能": "Activer la fonction de dessin",
     "启用请求体透传功能": "Activer la fonctionnalité de transmission du corps de la requête",
     "启用请求透传": "Activer la transmission de la requête",
-    "禁用思考处理的模型列表": "Liste noire des modèles pour le traitement thinking",
-    "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀": "Les modèles listés ici n'ajouteront ni ne retireront automatiquement le suffixe -thinking/-nothinking.",
-    "请输入JSON数组，如 [\"model-a\",\"model-b\"]": "Saisissez un tableau JSON, par ex. [\"model-a\",\"model-b\"]",
     "启用额度消费日志记录": "Activer la journalisation de la consommation de quota",
     "启用验证": "Activer l'authentification",
     "周": "semaine",
@@ -1528,10 +1525,6 @@
     "缓存倍率": "Ratio de cache",
     "缓存创建 Tokens": "Jetons de création de cache",
     "缓存创建: {{cacheCreationRatio}}": "Création de cache : {{cacheCreationRatio}}",
-    "缓存创建: 5m {{cacheCreationRatio5m}}": "Création de cache : 5m {{cacheCreationRatio5m}}",
-    "缓存创建: 1h {{cacheCreationRatio1h}}": "Création de cache : 1h {{cacheCreationRatio1h}}",
-    "缓存创建倍率 5m {{cacheCreationRatio5m}}": "Multiplicateur de création de cache 5m {{cacheCreationRatio5m}}",
-    "缓存创建倍率 1h {{cacheCreationRatio1h}}": "Multiplicateur de création de cache 1h {{cacheCreationRatio1h}}",
     "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})": "Prix de création du cache : {{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (taux de création de cache : {{cacheCreationRatio}})",
     "编辑": "Modifier",
     "编辑API": "Modifier l'API",

web/src/i18n/locales/ja.json

@@ -561,9 +561,6 @@
     "启用绘图功能": "画像生成機能を有効にする",
     "启用请求体透传功能": "リクエストボディのパススルー機能を有効にします。",
     "启用请求透传": "リクエストパススルーを有効にする",
-    "禁用思考处理的模型列表": "Thinking処理を無効化するモデル一覧",
-    "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀": "ここに含まれるモデルでは-thinking/-nothinkingサフィックスを自動的に追加・削除しません。",
-    "请输入JSON数组，如 [\"model-a\",\"model-b\"]": "JSON配列を入力してください（例：[\"model-a\",\"model-b\"]）",
     "启用额度消费日志记录": "クォータ消費のログ記録を有効にする",
     "启用验证": "認証を有効にする",
     "周": "週",
@@ -1519,10 +1516,6 @@
     "缓存倍率": "キャッシュ倍率",
     "缓存创建 Tokens": "キャッシュ作成トークン",
     "缓存创建: {{cacheCreationRatio}}": "キャッシュ作成：{{cacheCreationRatio}}",
-    "缓存创建: 5m {{cacheCreationRatio5m}}": "キャッシュ作成：5m {{cacheCreationRatio5m}}",
-    "缓存创建: 1h {{cacheCreationRatio1h}}": "キャッシュ作成：1h {{cacheCreationRatio1h}}",
-    "缓存创建倍率 5m {{cacheCreationRatio5m}}": "キャッシュ作成倍率 5m {{cacheCreationRatio5m}}",
-    "缓存创建倍率 1h {{cacheCreationRatio1h}}": "キャッシュ作成倍率 1h {{cacheCreationRatio1h}}",
     "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})": "キャッシュ作成料金：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1Mtokens（キャッシュ作成倍率：{{cacheCreationRatio}}）",
     "编辑": "編集",
     "编辑API": "API編集",
@@ -2082,4 +2075,4 @@
     "统一的": "統合型",
     "大模型接口网关": "LLM APIゲートウェイ"
   }
-}
+}

web/src/i18n/locales/ru.json

@@ -567,9 +567,6 @@
     "启用绘图功能": "Включить функцию рисования",
     "启用请求体透传功能": "Включить функцию прозрачной передачи тела запроса",
     "启用请求透传": "Включить прозрачную передачу запросов",
-    "禁用思考处理的模型列表": "Список моделей без обработки thinking",
-    "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀": "Для этих моделей суффиксы -thinking/-nothinking не будут добавляться или удаляться автоматически.",
-    "请输入JSON数组，如 [\"model-a\",\"model-b\"]": "Введите JSON-массив, например [\"model-a\",\"model-b\"]",
     "启用额度消费日志记录": "Включить журналирование потребления квоты",
     "启用验证": "Включить проверку",
     "周": "Неделя",
@@ -1537,10 +1534,6 @@
     "缓存倍率": "Коэффициент кэширования",
     "缓存创建 Tokens": "Создание кэша токенов",
     "缓存创建: {{cacheCreationRatio}}": "Создание кэша: {{cacheCreationRatio}}",
-    "缓存创建: 5m {{cacheCreationRatio5m}}": "Создание кэша: 5m {{cacheCreationRatio5m}}",
-    "缓存创建: 1h {{cacheCreationRatio1h}}": "Создание кэша: 1h {{cacheCreationRatio1h}}",
-    "缓存创建倍率 5m {{cacheCreationRatio5m}}": "Множитель создания кэша 5m {{cacheCreationRatio5m}}",
-    "缓存创建倍率 1h {{cacheCreationRatio1h}}": "Множитель создания кэша 1h {{cacheCreationRatio1h}}",
     "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})": "Цена создания кэша: {{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M токенов (коэффициент создания кэша: {{cacheCreationRatio}})",
     "编辑": "Редактировать",
     "编辑API": "Редактировать API",

web/src/i18n/locales/zh.json

@@ -558,9 +558,6 @@
     "启用绘图功能": "启用绘图功能",
     "启用请求体透传功能": "启用请求体透传功能",
     "启用请求透传": "启用请求透传",
-    "禁用思考处理的模型列表": "禁用思考处理的模型列表",
-    "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀": "列出的模型将不会自动添加或移除-thinking/-nothinking 后缀",
-    "请输入JSON数组，如 [\"model-a\",\"model-b\"]": "请输入JSON数组，如 [\"model-a\",\"model-b\"]",
     "启用额度消费日志记录": "启用额度消费日志记录",
     "启用验证": "启用验证",
     "周": "周",
@@ -1510,10 +1507,6 @@
     "缓存倍率": "缓存倍率",
     "缓存创建 Tokens": "缓存创建 Tokens",
     "缓存创建: {{cacheCreationRatio}}": "缓存创建: {{cacheCreationRatio}}",
-    "缓存创建: 5m {{cacheCreationRatio5m}}": "缓存创建: 5m {{cacheCreationRatio5m}}",
-    "缓存创建: 1h {{cacheCreationRatio1h}}": "缓存创建: 1h {{cacheCreationRatio1h}}",
-    "缓存创建倍率 5m {{cacheCreationRatio5m}}": "缓存创建倍率 5m {{cacheCreationRatio5m}}",
-    "缓存创建倍率 1h {{cacheCreationRatio1h}}": "缓存创建倍率 1h {{cacheCreationRatio1h}}",
     "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})": "缓存创建价格：{{symbol}}{{price}} * {{ratio}} = {{symbol}}{{total}} / 1M tokens (缓存创建倍率: {{cacheCreationRatio}})",
     "编辑": "编辑",
     "编辑API": "编辑API",
@@ -2073,4 +2066,4 @@
     "Creem 介绍": "Creem 是一个简单的支付处理平台，支持固定金额产品销售，以及订阅销售。",
     "Creem Setting Tips": "Creem 只支持预设的固定金额产品，这产品以及价格需要提前在Creem网站内创建配置，所以不支持自定义动态金额充值。在Creem端配置产品的名字以及价格，获取Product Id 后填到下面的产品，在new-api为该产品设置充值额度，以及展示价格。"
   }
-}
+}

web/src/pages/Playground/index.jsx

@@ -47,7 +47,6 @@ import {
   createLoadingAssistantMessage,
   getTextContent,
   buildApiPayload,
-  encodeToBase64,
 } from '../../helpers';
 
 // Components
@@ -73,7 +72,7 @@ const generateAvatarDataUrl = (username) => {
       <text x="50%" y="50%" dominant-baseline="central" text-anchor="middle" font-size="16" fill="#ffffff" font-family="sans-serif">${firstLetter}</text>
     </svg>
   `;
-  return `data:image/svg+xml;base64,${encodeToBase64(svg)}`;
+  return `data:image/svg+xml;base64,${btoa(svg)}`;
 };
 
 const Playground = () => {

web/src/pages/Setting/Model/SettingGlobalModel.jsx

@@ -29,44 +29,23 @@ import {
 } from '../../../helpers';
 import { useTranslation } from 'react-i18next';
 
-const thinkingExample = JSON.stringify(
-  ['moonshotai/kimi-k2-thinking', 'kimi-k2-thinking'],
-  null,
-  2,
-);
-
-const defaultGlobalSettingInputs = {
-  'global.pass_through_request_enabled': false,
-  'global.thinking_model_blacklist': '[]',
-  'general_setting.ping_interval_enabled': false,
-  'general_setting.ping_interval_seconds': 60,
-};
-
 export default function SettingGlobalModel(props) {
   const { t } = useTranslation();
 
   const [loading, setLoading] = useState(false);
-  const [inputs, setInputs] = useState(defaultGlobalSettingInputs);
+  const [inputs, setInputs] = useState({
+    'global.pass_through_request_enabled': false,
+    'general_setting.ping_interval_enabled': false,
+    'general_setting.ping_interval_seconds': 60,
+  });
   const refForm = useRef();
-  const [inputsRow, setInputsRow] = useState(defaultGlobalSettingInputs);
-
-  const normalizeValueBeforeSave = (key, value) => {
-    if (key === 'global.thinking_model_blacklist') {
-      const text = typeof value === 'string' ? value.trim() : '';
-      return text === '' ? '[]' : value;
-    }
-    return value;
-  };
+  const [inputsRow, setInputsRow] = useState(inputs);
 
   function onSubmit() {
     const updateArray = compareObjects(inputs, inputsRow);
     if (!updateArray.length) return showWarning(t('你似乎并没有修改什么'));
     const requestQueue = updateArray.map((item) => {
-      const normalizedValue = normalizeValueBeforeSave(
-        item.key,
-        inputs[item.key],
-      );
-      let value = String(normalizedValue);
+      let value = String(inputs[item.key]);
 
       return API.put('/api/option/', {
         key: item.key,
@@ -95,30 +74,14 @@ export default function SettingGlobalModel(props) {
 
   useEffect(() => {
     const currentInputs = {};
-    for (const key of Object.keys(defaultGlobalSettingInputs)) {
-      if (props.options[key] !== undefined) {
-        let value = props.options[key];
-        if (key === 'global.thinking_model_blacklist') {
-          try {
-            value =
-              value && String(value).trim() !== ''
-                ? JSON.stringify(JSON.parse(value), null, 2)
-                : defaultGlobalSettingInputs[key];
-          } catch (error) {
-            value = defaultGlobalSettingInputs[key];
-          }
-        }
-        currentInputs[key] = value;
-      } else {
-        currentInputs[key] = defaultGlobalSettingInputs[key];
+    for (let key in props.options) {
+      if (Object.keys(inputs).includes(key)) {
+        currentInputs[key] = props.options[key];
       }
     }
-
     setInputs(currentInputs);
     setInputsRow(structuredClone(currentInputs));
-    if (refForm.current) {
-      refForm.current.setValues(currentInputs);
-    }
+    refForm.current.setValues(currentInputs);
   }, [props.options]);
 
   return (
@@ -147,38 +110,6 @@ export default function SettingGlobalModel(props) {
                 />
               </Col>
             </Row>
-            <Row>
-              <Col span={24}>
-                <Form.TextArea
-                  label={t('禁用思考处理的模型列表')}
-                  field={'global.thinking_model_blacklist'}
-                  placeholder={
-                    t('例如：') +
-                    '\n' +
-                    thinkingExample
-                  }
-                  rows={4}
-                  rules={[
-                    {
-                      validator: (rule, value) => {
-                        if (!value || value.trim() === '') return true;
-                        return verifyJSON(value);
-                      },
-                      message: t('不是合法的 JSON 字符串'),
-                    },
-                  ]}
-                  extraText={t(
-                    '列出的模型将不会自动添加或移除-thinking/-nothinking 后缀',
-                  )}
-                  onChange={(value) =>
-                    setInputs({
-                      ...inputs,
-                      'global.thinking_model_blacklist': value,
-                    })
-                  }
-                />
-              </Col>
-            </Row>
 
             <Form.Section text={t('连接保活设置')}>
               <Row style={{ marginTop: 10 }}>