feat: claude 1h cache (#2155)

* feat: claude 1h cache

* feat: claude 1h cache

* fix price

dto/claude.go

@@ -514,9 +514,42 @@ type ClaudeUsage struct {
 	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()
+}
+
 type ClaudeServerToolUse struct {
 	WebSearchRequests int `json:"web_search_requests"`
 }

dto/openai_response.go

@@ -230,6 +230,11 @@ 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"`
 }

relay/channel/claude/relay-claude.go

@@ -596,6 +596,8 @@ 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 {
@@ -740,6 +742,8 @@ 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/helper/price.go

@@ -13,6 +13,9 @@ 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{
@@ -53,6 +56,8 @@ 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
@@ -76,6 +81,9 @@ 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)
@@ -116,6 +124,8 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
 		AudioRatio:           audioRatio,
 		AudioCompletionRatio: audioCompletionRatio,
 		CacheCreationRatio:   cacheCreationRatio,
+		CacheCreation5mRatio: cacheCreationRatio5m,
+		CacheCreation1hRatio: cacheCreationRatio1h,
 		QuotaToPreConsume:    preConsumedQuota,
 	}
 

service/log_info_generate.go

@@ -92,11 +92,23 @@ 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, modelPrice float64, userGroupRatio float64) map[string]interface{} {
+	cacheTokens int, cacheRatio float64,
+	cacheCreationTokens int, cacheCreationRatio float64,
+	cacheCreationTokens5m int, cacheCreationRatio5m float64,
+	cacheCreationTokens1h int, cacheCreationRatio1h 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

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

types/price_data.go

@@ -15,6 +15,8 @@ type PriceData struct {
 	CompletionRatio      float64
 	CacheRatio           float64
 	CacheCreationRatio   float64
+	CacheCreation5mRatio float64
+	CacheCreation1hRatio float64
 	ImageRatio           float64
 	AudioRatio           float64
 	AudioCompletionRatio float64
@@ -31,5 +33,5 @@ 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, 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)
+	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)
 }

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

@@ -551,6 +551,10 @@ 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,
@@ -565,6 +569,10 @@ 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/hooks/usage-logs/useUsageLogsData.jsx

@@ -361,6 +361,10 @@ 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,
@@ -429,6 +433,10 @@ 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

@@ -1516,6 +1516,10 @@
     "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",

web/src/i18n/locales/fr.json

@@ -1525,6 +1525,10 @@
     "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

@@ -1516,6 +1516,10 @@
     "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",

web/src/i18n/locales/ru.json

@@ -1534,6 +1534,10 @@
     "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

@@ -1507,6 +1507,10 @@
     "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",