client.chat.completions.create works with neither messages or input #2560
Description
Confirm this is an issue with the Python library and not an underlying OpenAI API
- This is an issue with the Python library
Describe the bug
client.chat.completions.create works with neither messages or input
To Reproduce
When using
import json
import os
import random
from dotenv import load_dotenv
from openai import AzureOpenAI
from pydantic import BaseModel, Field
load_dotenv()
client = AzureOpenAI(
api_version="2025-03-01-preview",
azure_endpoint=os.getenv("AZURE_ENDPOINT"),
api_key=os.getenv("AZURE_GPT5_KEY"),
)
input_list = [
{
"role": "user",
"content": "What's today's horoscope for Aquarius and weather in Paris & Tokyo?",
}
]
response = client.chat.completions.create(
model="gpt-5", # Use your actual deployment name
input=input_list,
tools=tools,
tool_choice="auto",
)It yields error:
Traceback (most recent call last):
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/experiment2-parallell-tool-calling/main.py", line 66, in <module>
response = client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 286, in wrapper
raise TypeError(msg)
TypeError: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given
But when using
response = client.chat.completions.create(
model="gpt-5", # Use your actual deployment name
messages=input_list,
tools=tools,
tool_choice="auto",
)
It yields error
Traceback (most recent call last):
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/experiment2-parallell-tool-calling/par.py", line 176, in <module>
print(run_conversation())
^^^^^^^^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/experiment2-parallell-tool-calling/par.py", line 121, in run_conversation
response = client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 287, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 1150, in create
return self._post(
^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1259, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/torstein.sornes/code/kg-text-to-graph-experiments/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1047, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'messages'. In the Responses API, this parameter has moved to 'input'. Try again with the new parameter. See the API documentation for more information: https://platform.openai.com/docs/api-reference/responses/create.", 'type': 'invalid_request_error', 'param': None, 'code': 'unsupported_parameter'}}
Code snippets
OS
Linux
Python version
Python 3.12
Library version
1.99.9