? OpenAI prompt_cache_key, where to provide it?

flesicek · July 29, 2025, 12:27pm

Hey Guys, I want to use prompt_cache_key value when invoking OpenAI https://platform.openai.com/docs/api-reference/responses/create but I can’t seem to find any support in LangChain for it. Any suggestions where to look / how to provide it?

tingyiy · August 22, 2025, 10:23am

github.com/langchain-ai/langchain

libs/partners/openai/langchain_openai/chat_models/base.py

61bc1bf9c


      
          
          .. dropdown:: Prompt caching optimization
          
              For high-volume applications with repetitive prompts, use ``prompt_cache_key``
              per-invocation to improve cache hit rates and reduce costs:
          
              .. code-block:: python
          
                  llm = ChatOpenAI(model="gpt-4o-mini")
          
                  response = llm.invoke(
                      messages,
                      prompt_cache_key="example-key-a",  # Routes to same machine for cache hits
                  )
          
                  customer_response = llm.invoke(messages, prompt_cache_key="example-key-b")
                  support_response = llm.invoke(messages, prompt_cache_key="example-key-c")
          
                  # Dynamic cache keys based on context
                  cache_key = f"example-key-{dynamic_suffix}"
                  response = llm.invoke(messages, prompt_cache_key=cache_key)

Topic		Replies	Views
About the LangChain category LangChain	0	86	June 27, 2025
Cache on langgraph cloud LangGraph python-help	0	37	August 6, 2025
Prompt Playground does not support the Responses API LangSmith	1	66	July 28, 2025
Caching to PostgreSQL LangChain self-hosted , intro-to-langgraph , python-help	1	64	July 30, 2025
Fetching prompts from prompt registry at runtime on a thread level LangGraph python-help	1	40	August 21, 2025

? OpenAI prompt_cache_key, where to provide it?

Related topics