How to beginner · 3 min read

How to set temperature in OpenAI API

Q: How to set temperature in OpenAI API

Set the temperature parameter in the OpenAI API's chat.completions.create method to control randomness in responses. A lower temperature (e.g., 0.0) makes output more deterministic, while a higher value (up to 2.0) increases creativity.

Quick answer

Set the temperature parameter in the OpenAI API's chat.completions.create method to control randomness in responses. A lower temperature (e.g., 0.0) makes output more deterministic, while a higher value (up to 2.0) increases creativity.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official OpenAI Python SDK and set your API key as an environment variable.

Install SDK: pip install openai
Set environment variable in your shell: export OPENAI_API_KEY='your_api_key_here'

bash

pip install openai

Step by step

Use the temperature parameter in the chat.completions.create call to adjust randomness. Values range from 0.0 (most deterministic) to 2.0 (most creative). Here's a complete example:

python

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a creative poem about spring."}],
    temperature=0.7
)

print(response.choices[0].message.content)

output

A gentle breeze whispers through the trees,
Spring awakens with vibrant ease.
Blossoms dance in morning light,
Nature's canvas, pure delight.

Common variations

You can adjust temperature for different use cases:

Low temperature (0.0 - 0.3): Use for precise, factual answers.
Medium temperature (0.4 - 0.7): Balanced creativity and coherence.
High temperature (0.8 - 2.0): More creative, diverse outputs.

Also, you can use other models like gpt-4o-mini or async calls with the same parameter.

Temperature range	Effect
0.0 - 0.3	Deterministic, factual responses
0.4 - 0.7	Balanced creativity and coherence
0.8 - 2.0	Creative and diverse outputs

Troubleshooting

If you get repetitive or dull responses, increase the temperature. If output is too random or off-topic, lower it. Ensure your API key is set correctly in os.environ["OPENAI_API_KEY"] to avoid authentication errors.

✅

Key Takeaways

Set temperature in chat.completions.create to control output randomness.
Use lower temperatures for factual answers and higher for creative text.
Always source your API key from os.environ for security.
The temperature parameter accepts values from 0.0 to 2.0.
Adjust temperature based on your application's need for creativity versus precision.

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

Verify ↗