github/new-api
1
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-04-18 20:47:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: claude 1h cache (#2155)

Browse Source 
* feat: claude 1h cache

* feat: claude 1h cache

* fix price
This commit is contained in:
Seefs
2025-11-04 00:20:50 +08:00
committed by GitHub
parent 00782aae88
commit df2ee649ab
15 changed files with 384 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
relay/channel/claude/relay-claude.go
View File

@@ -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 {

10
relay/helper/price.go
View File

@@ -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,
}