ext/new-api
2
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-09-14 00:01:53 +00:00
Code Activity

feat: bill OpenAI cache_write_tokens at cache-creation price with zero clamp

Browse Source 
Parse OpenAI's native cache_write_tokens (chat prompt_tokens_details /
responses input_tokens_details), bill it at the cache-creation ratio, and
clamp the uncached prompt remainder at zero since cached + cache-write can
exceed prompt_tokens. Propagate the field through chat/responses/claude
format conversions and tiered expression billing (cc variable).
This commit is contained in:
CaIon
2026-07-11 21:18:49 +08:00
parent c36418c863
commit 48068ce923
18 changed files with 158 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
service/text_quota.go
+8 -1
View File
@@ -208,7 +208,7 @@ func calculateTextQuotaSummary(ctx *gin.Context, relayInfo *relaycommon.RelayInf
summary.CompletionTokens = usage.CompletionTokens
summary.TotalTokens = usage.PromptTokens + usage.CompletionTokens
summary.CacheTokens = usage.PromptTokensDetails.CachedTokens
summary.CacheCreationTokens = usage.PromptTokensDetails.CachedCreationTokens
summary.CacheCreationTokens = usage.PromptTokensDetails.CacheCreationTokensTotal()
summary.CacheCreationTokens5m = usage.ClaudeCacheCreation5mTokens
summary.CacheCreationTokens1h = usage.ClaudeCacheCreation1hTokens
summary.ImageTokens = usage.PromptTokensDetails.ImageTokens
@@ -294,6 +294,13 @@ func calculateTextQuotaSummary(ctx *gin.Context, relayInfo *relaycommon.RelayInf
}
}
// OpenAI cache-write usage can report cached_tokens + cache_write_tokens
// exceeding prompt_tokens; the uncached remainder must clamp at zero so
// billing never subtracts more than the reported input.
if baseTokens.IsNegative() {
baseTokens = decimal.Zero
}
promptQuota := baseTokens.Add(cachedTokensWithRatio).Add(imageTokensWithRatio).Add(cachedCreationTokensWithRatio)
completionQuota := dCompletionTokens.Mul(dCompletionRatio)
quotaCalculateDecimal := promptQuota.Add(completionQuota).Mul(ratio)