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
service/tiered_settle.go
+1 -1
View File
@@ -22,7 +22,7 @@ func BuildTieredTokenParams(usage *dto.Usage, isClaudeUsageSemantic bool, usedVa
p := float64(usage.PromptTokens)
c := float64(usage.CompletionTokens)
cr := float64(usage.PromptTokensDetails.CachedTokens)
cc5m := float64(usage.PromptTokensDetails.CachedCreationTokens)
cc5m := float64(usage.PromptTokensDetails.CacheCreationTokensTotal())
cc1h := float64(0)
if usage.UsageSemantic == "anthropic" {