Jaymr/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki 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
dto/billing_usage.go
+1
View File
@@ -88,6 +88,7 @@ func HasOpenAIUsageTokens(usage *Usage) bool {
}
if usage.PromptTokensDetails.CachedTokens != 0 ||
usage.PromptTokensDetails.CachedCreationTokens != 0 ||
usage.PromptTokensDetails.CacheWriteTokens != 0 ||
usage.PromptTokensDetails.TextTokens != 0 ||
usage.PromptTokensDetails.ImageTokens != 0 ||
usage.PromptTokensDetails.AudioTokens != 0 {