The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: document OpenAI flex processing (#31023)
ccurmea60fd06784e8
diff --git a/docs/docs/integrations/chat/openai.ipynb b/docs/docs/integrations/chat/openai.ipynbindex 457293aac9..a1b3adeb82 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.pyindex 9e740f38a9..f1b3bc2104 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: E501max_tokens: Optional[int] = Field(default=None, alias="max_completion_tokens")