How to Intermediate · 3 min read

How to use function calling in Gemini API

Q: How to use function calling in Gemini API

Use the OpenAI Python SDK to call the Gemini API with the functions parameter in chat.completions.create. Define your functions schema and handle the function_call response to execute or respond accordingly.

Quick answer

Use the OpenAI Python SDK to call the Gemini API with the functions parameter in chat.completions.create. Define your functions schema and handle the function_call response to execute or respond accordingly.

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.

bash

pip install openai>=1.0

Step by step

Define your functions schema and call the Gemini model with functions and function_call parameters. Handle the response to detect if the model wants to call a function and process accordingly.

python

import os
from openai import OpenAI

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

functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
            },
            "required": ["location"]
        }
    }
]

messages = [
    {"role": "user", "content": "What is the weather like in New York?"}
]

response = client.chat.completions.create(
    model="gemini-1.5-pro",
    messages=messages,
    functions=functions,
    function_call="auto"  # or specify function name
)

message = response.choices[0].message

if message.get("function_call"):
    function_name = message["function_call"]["name"]
    function_args = message["function_call"]["arguments"]
    print(f"Function to call: {function_name}")
    print(f"Arguments: {function_args}")
    # Here you would implement the actual function call and return the result
else:
    print(message.content)

output

Function to call: get_current_weather
Arguments: {"location": "New York", "unit": "fahrenheit"}

Common variations

Use function_call="none" to disable function calling.
Use function_call="auto" to let the model decide when to call functions.
Switch models like gemini-2.0-flash for faster responses.
Implement async calls with asyncio and await in Python.

python

import asyncio
import os
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

    functions = [
        {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location"]
            }
        }
    ]

    messages = [{"role": "user", "content": "Tell me the weather in Boston."}]

    response = await client.chat.completions.acreate(
        model="gemini-2.0-flash",
        messages=messages,
        functions=functions,
        function_call="auto"
    )

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

asyncio.run(main())

output

{'role': 'assistant', 'function_call': {'name': 'get_current_weather', 'arguments': '{"location": "Boston", "unit": "celsius"}'}}

Troubleshooting

If you get a 400 Bad Request, verify your functions JSON schema is valid.
If the model never calls functions, ensure function_call is set to "auto" or the specific function name.
Check your API key environment variable is correctly set as OPENAI_API_KEY.

✅

Key Takeaways

Use the functions parameter to define callable functions in Gemini API requests.
Set function_call to "auto" to enable automatic function invocation by the model.
Parse the function_call field in the response to handle function execution in your app.

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

Verify ↗