BaseOpenAILLMService: include cached tokens to metrics frame

2025-09-24 19:32:16 -07:00
parent 3797f41c8c
commit 33447ad6f2
2 changed files with 12 additions and 0 deletions
--- a/src/pipecat/services/openai/base_llm.py
+++ b/src/pipecat/services/openai/base_llm.py
@@ -337,10 +337,16 @@ class BaseOpenAILLMService(LLMService):

        async for chunk in chunk_stream:
            if chunk.usage:
+                cached_tokens = (
+                    chunk.usage.prompt_tokens_details.cached_tokens
+                    if chunk.usage.prompt_tokens_details
+                    else None
+                )
                tokens = LLMTokenUsage(
                    prompt_tokens=chunk.usage.prompt_tokens,
                    completion_tokens=chunk.usage.completion_tokens,
                    total_tokens=chunk.usage.total_tokens,
+                    cache_read_input_tokens=cached_tokens,
                )
                await self.start_llm_usage_metrics(tokens)