Skip to main content

Use images in prompts in Sheets

Use images in your prompts with GPT for Sheets and vision models, which can process images as input. For example, you can prompt images to describe them, or prompt images with additional text input from your spreadsheet to create product descriptions based on their photos and names.

info

  • Image URLs must be publicly accessible.

  • Supported image formats: PNG, JPEG, WebP, non-animated GIF.

Supported vision models​

We recommend using gpt-4.1 to analyze images, but you can use any vision model supported by GPT for Sheets.

Click here for a list of all vision models supported by GPT for Sheets.
ProviderModelWithout API keyWith API key

OpenAI

gpt-4.1

✅

✅

gpt-4.1-mini

✅

✅

gpt-4.1-nano

✅

✅

gpt-4o

✅

✅

gpt-4o-mini

✅

✅

gpt-5

✅

✅

gpt-5-chat

✅

✅

gpt-5-mini

✅

✅

gpt-5-nano

✅

✅

o1

✅

✅

o3

✅

✅

o4-mini

✅

✅

Anthropic

claude-3-opus

❌

✅

claude-3.5-haiku

❌

✅

claude-3.5-sonnet

✅

✅

claude-3.7-sonnet

❌

✅

claude-4-sonnet

✅

✅

Prompt images​

Bulk AI tools vs. GPT functions​

To apply a prompt to images in your spreadsheet, you can either use the Prompt images (Vision) bulk AI tool or the GPT_VISION function. Choose the method that best fits your needs:

  • Use the Prompt images (Vision) bulk AI tool if:

    • You want to perform bulk searches on entire columns (row-by-row).

    • You are working with thousands of rows.

    • You want to include up to 5 images per prompt.

    • A low image resolution is sufficient for your needs.

  • Use the GPT_VISION function if:

    • You're comfortable using spreadsheet formulas.

    • You're working with up to a few hundred cells or you want to prompt images for individual cells.

    • You need the flexibility of nested formulas or of combining GPT functions with native functions.

    • You only need to include a single image per prompt.

    • You want to control the image resolution.

Prompt images (Vision) bulk AI tool​

Use the Prompt images (Vision) bulk AI tool to apply a prompt to images in your spreadsheet.

  1. Open GPT for Sheets.

  2. In the sidebar, select Bulk AI tools and click Prompt images (Vision).

    Prompt images (Vision) bulk AI tool in the sidebar

  3. Expand the model switcher and select a vision model.

    A vision model in the model switcher

  4. Set up your bulk tool run.

    Set up a Prompt images (Vision) run
    FieldDescriptionExample

    1

    Prompt

    Enter the prompt you want to apply to each image.

    Write a short description of this product based on how it looks, how it's used, and its build quality.

    2

    Columns containing image URLs

    Select up to five columns that contain image URLs. For each row, the tool processes all images present in the selected columns. URLs must be publicly accessible.

    C: Front image, D: In-use image, E: Material detail image

    3

    Image resolution

    Choose the level of detail for image processing:

    • High: Better image understanding, higher latency and cost
    • Low: Faster processing, lower cost
    • Auto: Let the model decide (default)

    Low

    4

    Put results in column

    Select the column to put the results in. Cells in this column won't be overwritten with the results if they contain text.

    F: Description

  5. Click Run rows.

    Run the Prompt images (Vision) tool

You have set up and run the Prompt images (Vision) bulk tool to apply a prompt to images in your spreadsheet.

Prompt images (Vision) results

For instructions on how to improve the results, see Prompt images (Vision) bulk AI tool.

GPT_VISION function​

Use the GPT_VISION function to describe or analyze images in individual cells.

Using the model switcher​

  1. Open GPT for Sheets.

  2. In the sidebar, select GPT functions.

  3. Expand the model switcher and select a vision model.

    A vision model in the model switcher

  4. In the spreadsheet, select a cell and write your formula:

    =GPT_VISION("Extract the coffee brand from this image. Normalize the brand name to title case.",C9)
    A GPT_VISION formula

    The formula uses the vision model selected in the model switcher.

Specifying the model in the formula​

  1. Open GPT for Sheets.

  2. In the spreadsheet, select a cell and write your formula, specifying a vision model directly in the formula:

    =GPT_VISION("Extract the coffee brand from this image. Normalize the brand name to title case.",C9, , , "gpt-4.1")
    A GPT_VISION formula with the model parameter

    The formula uses the vision model regardless of what's currently selected in the model switcher.

For instructions on how to write formulas with the GPT_VISION function and set the image resolution, see GPT_VISION.

Prompt images with additional text input​

Custom prompt bulk AI tool​

Use the Custom prompt bulk AI tool to combine a prompt with text and images from your spreadsheet.

info

In the Custom prompt bulk AI tool, the image resolution is fixed to Low and cannot be changed.

  1. Open GPT for Sheets.

  2. In the sidebar, select Bulk AI tools and click Custom prompt.

    Custom prompt bulk AI tool in the sidebar

  3. Expand the model switcher and select a vision model.

    A vision model in the model switcher

  4. Write your prompt and include any variables to be replaced with values from your spreadsheet.

    Write a short description of {{Product name}} based on how it looks, how it's used, and its build quality.

  5. Click Configure image columns to show the Columns containing image URLs dropdown, and select the columns that contain image URLs.

    Configure image columns

  6. Click Run rows.

    Run the Custom prompt bulk AI tool

You have set up and run the Custom prompt bulk tool to include images and text from your spreadsheet.

Custom prompt bulk AI tool results

For instructions on how to improve the results, see Custom prompt bulk AI tool.

On this page