From a60fd06784e8a5a28c380aec659297f3f15f7e34 Mon Sep 17 00:00:00 2001
From: ccurme <chester.curme@gmail.com>
Date: Fri, 25 Apr 2025 15:10:25 -0400
Subject: [PATCH] docs: document OpenAI flex processing (#31023)
Following https://github.com/langchain-ai/langchain/pull/31005
---
docs/docs/integrations/chat/openai.ipynb | 19 ++++++++++++++++-
.../langchain_openai/chat_models/base.py | 21 +++++++++++++++++++
2 files changed, 39 insertions(+), 1 deletion(-)
diff --git a/docs/docs/integrations/chat/openai.ipynb b/docs/docs/integrations/chat/openai.ipynb
index 457293aac9e..a1b3adeb821 100644
--- a/docs/docs/integrations/chat/openai.ipynb
+++ b/docs/docs/integrations/chat/openai.ipynb
@@ -1413,6 +1413,23 @@
"second_output_message = llm.invoke(history)"
]
},
+ {
+ "cell_type": "markdown",
+ "id": "90c18d18-b25c-4509-a639-bd652b92f518",
+ "metadata": {},
+ "source": [
+ "## Flex processing\n",
+ "\n",
+ "OpenAI offers a variety of [service tiers](https://platform.openai.com/docs/guides/flex-processing). The \"flex\" tier offers cheaper pricing for requests, with the trade-off that responses may take longer and resources might not always be available. This approach is best suited for non-critical tasks, including model testing, data enhancement, or jobs that can be run asynchronously.\n",
+ "\n",
+ "To use it, initialize the model with `service_tier=\"flex\"`:\n",
+ "```python\n",
+ "llm = ChatOpenAI(model=\"o4-mini\", service_tier=\"flex\")\n",
+ "```\n",
+ "\n",
+ "Note that this is a beta feature that is only available for a subset of models. See OpenAI [docs](https://platform.openai.com/docs/guides/flex-processing) for more detail."
+ ]
+ },
{
"cell_type": "markdown",
"id": "a796d728-971b-408b-88d5-440015bbb941",
@@ -1420,7 +1437,7 @@
"source": [
"## API reference\n",
"\n",
- "For detailed documentation of all ChatOpenAI features and configurations head to the API reference: https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html"
+ "For detailed documentation of all ChatOpenAI features and configurations head to the [API reference](https://python.langchain.com/api_reference/openai/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html)."
]
}
],
diff --git a/libs/partners/openai/langchain_openai/chat_models/base.py b/libs/partners/openai/langchain_openai/chat_models/base.py
index 9e740f38a95..f1b3bc2104d 100644
--- a/libs/partners/openai/langchain_openai/chat_models/base.py
+++ b/libs/partners/openai/langchain_openai/chat_models/base.py
@@ -2331,6 +2331,27 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]
"logprobs": None,
}
+ .. dropdown:: Flex processing
+
+ OpenAI offers a variety of
+ `service tiers <https://platform.openai.com/docs/guides/flex-processing>`_.
+ The "flex" tier offers cheaper pricing for requests, with the trade-off that
+ responses may take longer and resources might not always be available.
+ This approach is best suited for non-critical tasks, including model testing,
+ data enhancement, or jobs that can be run asynchronously.
+
+ To use it, initialize the model with ``service_tier="flex"``:
+
+ .. code-block:: python
+
+ from langchain_openai import ChatOpenAI
+
+ llm = ChatOpenAI(model="o4-mini", service_tier="flex")
+
+ Note that this is a beta feature that is only available for a subset of models.
+ See OpenAI `docs <https://platform.openai.com/docs/guides/flex-processing>`_
+ for more detail.
+
""" # noqa: E501
max_tokens: Optional[int] = Field(default=None, alias="max_completion_tokens")