Code beginner · 3 min read

How to create OpenAI client in python

Q: How to create OpenAI client in python

Create an OpenAI client in Python by importing OpenAI from openai and initializing it with your API key from os.environ like client = OpenAI(api_key=os.environ["OPENAI_API_KEY"]).

Direct answer

Create an OpenAI client in Python by importing OpenAI from openai and initializing it with your API key from os.environ like client = OpenAI(api_key=os.environ["OPENAI_API_KEY"]).

Setup

Install

bash

pip install openai

Env vars

OPENAI_API_KEY

Imports

python

import os
from openai import OpenAI

Examples

inCreate client and send a simple chat message 'Hello'

outclient = OpenAI(api_key=os.environ["OPENAI_API_KEY"]) response = client.chat.completions.create(model="gpt-4o", messages=[{"role": "user", "content": "Hello"}]) print(response.choices[0].message.content)

inInitialize client and request a chat completion with model 'gpt-4o-mini'

outclient = OpenAI(api_key=os.environ["OPENAI_API_KEY"]) response = client.chat.completions.create(model="gpt-4o-mini", messages=[{"role": "user", "content": "What is AI?"}]) print(response.choices[0].message.content)

inCreate client and handle empty message list error

outclient = OpenAI(api_key=os.environ["OPENAI_API_KEY"]) try: response = client.chat.completions.create(model="gpt-4o", messages=[]) except Exception as e: print(f"Error: {e}")

Integration steps

Install the OpenAI Python SDK with pip.
Set your OpenAI API key in the environment variable OPENAI_API_KEY.
Import OpenAI from the openai package and os.
Initialize the client using OpenAI(api_key=os.environ["OPENAI_API_KEY"]).
Use the client to call API methods such as chat.completions.create with the desired model and messages.
Extract the response text from response.choices[0].message.content.

Full code

python

import os
from openai import OpenAI

# Initialize OpenAI client with API key from environment
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Create a chat completion request
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, how do I create an OpenAI client in Python?"}]
)

# Print the assistant's reply
print("Response:", response.choices[0].message.content)

output

Response: To create an OpenAI client in Python, import OpenAI from the openai package and initialize it with your API key from the environment variable OPENAI_API_KEY.

API trace

Request

json

{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello, how do I create an OpenAI client in Python?"}]}

Response

json

{"choices": [{"message": {"content": "To create an OpenAI client in Python, import OpenAI from the openai package and initialize it with your API key from the environment variable OPENAI_API_KEY."}}], "usage": {"total_tokens": 30}}

Extractresponse.choices[0].message.content

Variants

Streaming chat completion ›

Use streaming to display partial results immediately for long or interactive responses.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Stream response for better UX on long outputs
response_stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain streaming in OpenAI Python SDK."}],
    stream=True
)

for chunk in response_stream:
    print(chunk.choices[0].delta.get('content', ''), end='')
print()

Async client usage ›

Use async when integrating OpenAI calls into asynchronous Python applications for concurrency.

python

import os
import asyncio
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    response = await client.chat.completions.acreate(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Async client example."}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

Use smaller model for cost efficiency ›

Use smaller models like gpt-4o-mini to reduce cost and latency for simpler tasks.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What is the weather today?"}]
)
print(response.choices[0].message.content)

Performance

Latency~800ms for gpt-4o non-streaming calls

Cost~$0.002 per 500 tokens for gpt-4o

Rate limitsTier 1: 500 requests per minute / 30,000 tokens per minute

Keep messages concise to reduce token usage.
Use smaller models like gpt-4o-mini for cheaper calls.
Cache frequent responses to avoid repeated calls.

Approach	Latency	Cost/call	Best for
Standard client	~800ms	~$0.002 per 500 tokens	General purpose chat completions
Streaming client	Starts immediately, total ~800ms	Same as standard	Long responses with better UX
Async client	~800ms	~$0.002 per 500 tokens	Concurrent calls in async apps
Smaller model (gpt-4o-mini)	~400ms	~$0.0005 per 500 tokens	Cost-sensitive or simple tasks

✓

Quick tip

Always load your API key from environment variables to keep credentials secure and avoid accidental leaks.

⚠

Common mistake

Beginners often forget to use the latest SDK v1+ pattern and try deprecated methods like openai.ChatCompletion.create(), which no longer work.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗