Document explicit prompt caching support in ChatOpenAI

src/oss/python/integrations/chat/openai.mdx

@@ -1887,6 +1887,79 @@ response1 = llm.invoke(messages)
 response2 = llm.invoke(messages, prompt_cache_key="override-cache-v1")
 ```
 
+### Explicit caching with breakpoints (Responses API)
+
+<Note>
+Requires `langchain-openai>=1.3.5` and `openai>=2.45.0`. Only supported when using the [Responses API](/oss/python/integrations/chat/openai#responses-api).
+</Note>
+
+OpenAI's Responses API supports [explicit prompt-cache breakpoints](https://developers.openai.com/api/docs/guides/prompt-caching?prompt-cache-api=responses#prompt-cache-breakpoints), which let you designate specific content blocks as cache boundaries. This gives you fine-grained control over which parts of a prompt are cached, rather than relying solely on automatic prefix caching.
+
+To mark a content block as a cache breakpoint, add `"prompt_cache_breakpoint": True` to the block:
+
+```python
+from langchain_openai import ChatOpenAI
+
+llm = ChatOpenAI(model="gpt-4.1", use_responses_api=True)
+
+messages = [
+    {
+        "role": "system",
+        "content": [
+            {
+                "type": "text",
+                "text": "You are a helpful assistant with access to a large knowledge base.",
+                "prompt_cache_breakpoint": True,  # [!code highlight]
+            }
+        ],
+    },
+    {"role": "user", "content": "Summarize the key points."},
+]
+
+response = llm.invoke(messages)
+```
+
+Breakpoints are supported on text, image, and file content blocks. You can also nest `prompt_cache_breakpoint` inside an `extras` dict if you prefer to keep the LangChain content block structure clean:
+
+```python
+content_block = {
+    "type": "text",
+    "text": "Long system prompt...",
+    "extras": {"prompt_cache_breakpoint": True},
+}
+```
+
+### Request-level cache options
+
+<Note>
+Requires `langchain-openai>=1.3.5`.
+</Note>
+
+You can pass request-level prompt cache options to the Responses API using the `prompt_cache_options` parameter on the model:
+
+```python
+llm = ChatOpenAI(
+    model="gpt-4.1",
+    use_responses_api=True,
+    prompt_cache_options={"cache_type": "ephemeral"},
+)
+```
+
+### Cache write tokens
+
+When OpenAI writes new content to the prompt cache, it reports `cache_write_tokens` in the response. `ChatOpenAI` surfaces this as `cache_creation` in `input_token_details`:
+
+```python
+response = llm.invoke(messages)
+
+cache_read = response.usage_metadata["input_token_details"].get("cache_read")
+cache_creation = response.usage_metadata["input_token_details"].get("cache_creation")
+print(f"Cache read tokens:     {cache_read}")
+print(f"Cache creation tokens: {cache_creation}")
+```
+
+On the `"priority"` and `"flex"` service tiers, these keys are prefixed with the tier name — for example, `"priority_cache_read"` and `"priority_cache_creation"`.
+
 ---
 
 ## Flex processing