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
relay/channel/openai/relay_responses.go
+2
View File
@@ -51,6 +51,7 @@ func OaiResponsesHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http
usage.TotalTokens = responsesResponse.Usage.TotalTokens
if responsesResponse.Usage.InputTokensDetails != nil {
usage.PromptTokensDetails.CachedTokens = responsesResponse.Usage.InputTokensDetails.CachedTokens
usage.PromptTokensDetails.CacheWriteTokens = responsesResponse.Usage.InputTokensDetails.CacheWriteTokens
}
}
if info == nil || info.ResponsesUsageInfo == nil || info.ResponsesUsageInfo.BuiltInTools == nil {
@@ -104,6 +105,7 @@ func OaiResponsesStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp
}
if streamResponse.Response.Usage.InputTokensDetails != nil {
usage.PromptTokensDetails.CachedTokens = streamResponse.Response.Usage.InputTokensDetails.CachedTokens
usage.PromptTokensDetails.CacheWriteTokens = streamResponse.Response.Usage.InputTokensDetails.CacheWriteTokens
}
}
if streamResponse.Response.HasImageGenerationCall() {
relay/channel/openai/relay_responses_compact.go
+1
View File
@@ -37,6 +37,7 @@ func OaiResponsesCompactionHandler(c *gin.Context, resp *http.Response) (*dto.Us
usage.TotalTokens = compactResp.Usage.TotalTokens
if compactResp.Usage.InputTokensDetails != nil {
usage.PromptTokensDetails.CachedTokens = compactResp.Usage.InputTokensDetails.CachedTokens
usage.PromptTokensDetails.CacheWriteTokens = compactResp.Usage.InputTokensDetails.CacheWriteTokens
}
}
relay/responses_handler.go
+8 -6
View File
@@ -41,12 +41,14 @@ func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
responsesReq = req
case *dto.OpenAIResponsesCompactionRequest:
responsesReq = &dto.OpenAIResponsesRequest{
Model: req.Model,
Input: req.Input,
Instructions: req.Instructions,
PreviousResponseID: req.PreviousResponseID,
ParallelToolCalls: req.ParallelToolCalls,
ServiceTier: req.ServiceTier,
Model: req.Model,
Input: req.Input,
Instructions: req.Instructions,
PreviousResponseID: req.PreviousResponseID,
ParallelToolCalls: req.ParallelToolCalls,
ServiceTier: req.ServiceTier,
PromptCacheOptions: req.PromptCacheOptions,
PromptCacheRetention: req.PromptCacheRetention,
}
default:
return types.NewErrorWithStatusCode(