How to beginner · 3 min read

How to get text from Gemini API response

Quick answer

Use the OpenAI SDK v1 pattern to call the Gemini API and access the generated text from the response's choices[0].message.content field. This field contains the text output from the model after a chat completion request.

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 to authenticate requests to the Gemini API.

bash

pip install openai>=1.0

Step by step

Use the OpenAI client to create a chat completion request with a Gemini model. Extract the generated text from the choices[0].message.content field in the response.

python

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="gemini-1.5-pro",
    messages=[{"role": "user", "content": "Hello, Gemini!"}]
)

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

output

Hello, Gemini! How can I assist you today?

Common variations

You can use different Gemini models like gemini-1.5-flash or gemini-2.0-flash by changing the model parameter. For asynchronous calls, use async client methods if supported. Streaming responses require handling partial data chunks.

python

import asyncio
import os
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    response = await client.chat.completions.acreate(
        model="gemini-1.5-flash",
        messages=[{"role": "user", "content": "Hello asynchronously!"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

output

Hello asynchronously! How can I help you today?

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the response has no choices or message, check that the model name is valid and the request format matches the SDK requirements.
For network errors, ensure your internet connection is stable and the OpenAI endpoint is reachable.

✅

Key Takeaways

Use the OpenAI Python SDK v1 pattern to call Gemini models for chat completions.
Extract generated text from the response's choices[0].message.content field.
Set your API key in the environment variable OPENAI_API_KEY for authentication.

Verified 2026-04 · gemini-1.5-pro, gemini-1.5-flash, gemini-2.0-flash

Verify ↗