How to beginner · 3 min read

How to send multiple images to Gemini API

Quick answer

To send multiple images to the Gemini API, use the OpenAI Python SDK's client.chat.completions.create method with the gemini-1.5-flash model, including each image as a separate message with role set to user and content containing the image data or URL. The images should be passed as part of the messages array in the request.

PREREQUISITES

Python 3.8+
OpenAI API key
pip install openai>=1.0

Setup

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

Run pip install openai to install the SDK.
Set your API key in your environment: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows).

bash

pip install openai

Step by step

Use the gemini-1.5-flash model and send multiple images by including them as separate messages in the messages list. Each image can be represented as a base64 string or a URL in the content field.

python

import os
from openai import OpenAI

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

# Example images as URLs or base64 strings
images = [
    "https://example.com/image1.png",
    "https://example.com/image2.jpg"
]

# Prepare messages with images
messages = []
for idx, img_url in enumerate(images, start=1):
    messages.append({
        "role": "user",
        "content": f"[Image {idx}] {img_url}"
    })

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=messages
)

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

output

AI response text based on the multiple images sent

Common variations

Using base64 images: Instead of URLs, encode images as base64 strings and include them in the content field.
Async calls: Use async/await with the OpenAI SDK for non-blocking calls.
Different Gemini models: You can switch model to gemini-2.0-flash or others as needed.

python

import asyncio
import os
from openai import OpenAI

async def send_images_async():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    images = ["https://example.com/image1.png", "https://example.com/image2.jpg"]
    messages = [{"role": "user", "content": f"[Image {i+1}] {url}"} for i, url in enumerate(images)]

    response = await client.chat.completions.acreate(
        model="gemini-1.5-flash",
        messages=messages
    )
    print(response.choices[0].message.content)

asyncio.run(send_images_async())

output

AI response text based on the multiple images sent

Troubleshooting

If you get an error about invalid message format, ensure each image is included as a separate message with role set to user and content properly formatted.
If the API does not recognize the images, verify the URLs are accessible or base64 strings are correctly encoded.
Check your API key environment variable if authentication errors occur.

✅

Key Takeaways

Use the OpenAI Python SDK with gemini-1.5-flash to send multiple images as separate messages.
Images can be URLs or base64-encoded strings included in the content field of each message.
Always set your API key in os.environ["OPENAI_API_KEY"] and never hardcode it.
Async calls are supported for non-blocking image sending with the Gemini API.
Validate image accessibility and message formatting to avoid common errors.

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

Verify ↗