I have an issue here:
"Run failed: OpenAI API hits BadRequestError: Error code: 400 - {‘error’: {‘code’: ‘OperationNotSupported’, ‘message’: 'The chatCompletion operation does not work with the specified model, gpt-4o. Please choose different model and try again. You can learn more about which models can be used with each operation here:
It gives me a link, but it’s not specific and so much information.
Can anyone guide me where is it?
The API SDK method chatCompletion.create(), which might have been produced by asking an AI with obsolete knowledge, is indeed obsolete. The API SDK must also be updated in order to not block unknown models.
Assuming Python 3.9 - Python 3.13 is being used
Update the openai library module. At a command shell with rights to direct the installation to your current Python environment: pip install --upgrade openai tiktoken
Use API reference code for making API calls, examples from “API reference” on the sidebar of this forum.
Or begin with a better example: a pattern you’ll want for making a responsive application:
import asyncio
from openai import AsyncOpenAI
async def stream_chat(prompt):
'''example chat completions - only parses text response content
directly employs environment variable OPENAI_API_KEY'''
client = AsyncOpenAI(timeout=240)
kwargs = {
"model": "gpt-4.1-mini",
"messages": [
{"role": "developer", "content": "You are ChatAPI, an AI assistant."},
{"role": "user", "content": prompt},
],
"max_completion_tokens": 2000,
"stream": True,
}
reply = ""
async for chunk in await client.chat.completions.create(**kwargs):
delta = chunk.choices[0].delta
if delta.content:
print(delta.content, end="", flush=True) # streaming print function
reply += delta.content # gatherer for later
return reply
if __name__ == "__main__":
print("Chat Completions API call response:")
try:
asyncio.run(stream_chat("Write a haiki poem: AI friends"))
except Exception as e:
# real code would capture error type and branch
raise