[NEW!] Box AI API updates

Today, Box has completed a huge release of several features that developers have been waiting for.

We’re incredibly excited to announce the rollout of Box AI capabilities to our customers on Business, Business Plus, and Enterprise plans. Users can now access unlimited document and image querying via Box Preview in the Box web app. We’re also enhancing this experience with Box AI seamlessly embedded into the side panel, and enabling users to provide feedback on AI response quality in an easy and intuitive way. Coming soon, customers in Individual, Personal Pro, and Starter plans can expect to leverage these Box AI capabilities as well.

Here’s what else is new…

Box AI API general availability and pricing

As organizations increasingly integrate AI into their user experiences and workflows, understanding and managing their AI consumption becomes critical. Traditional pricing models often fall short when it comes to measuring the dynamic value AI delivers. Recognizing this need, Box is introducing Box AI Units as a new way to track and manage AI API usage AI usage more transparently . Each AI interaction — from querying content to extracting metadata — is quantified into discrete units, enabling businesses to forecast AI needs and optimize budgets with clarity and precision.

Contact your Box sales representative to find out more on availability and pricing specifics for your specific Box instance.

Box AI API with images

The Box AI ask endpoint now supports querying images. You use the endpoints in the same way as before, but using an image file will now return information about that image.

For example, for this image…

running the below cURL snippet….

curl -i -L POST "https://api.box.com/2.0/ai/ask" \
    -H "content-type: application/json" \
    -H "authorization: Bearer TOKEN" \
    -d '{
        "mode": "single_item_qa",
        "prompt": "What results should be followed up on?",
        "items": [
           {
           "type": "file",
           "id": "FILE_ID"
           }
        ]
     }'

will return a response like this…

{
   "answer": "The blood test results for John Doe indicate that the following values should be followed up on:\n\n1. **Hemoglobin (Hb)**: The result is 12.2 g/dL, which is below the reference range of 13.0 - 17.0 g/dL, indicating a low hemoglobin level.\n2. **Platelet Count**: The result is 150000 cumm, which is at the borderline of the reference range of 150000 - 410000 cumm.\n\nThese deviations from the normal ranges suggest potential health issues that may require further investigation or medical intervention.",
   "created_at": "2025-02-18T07:16:21.492-08:00",
   "completion_reason": "done",
   "ai_agent_info": {
       "models": [{
           "name": "azure__openai__gpt_4o",
           "provider": "azure"
       }],
       "processor": "basic_image"
   }
}

Box AI extract agents, freeform and structured, also support images, so you can extract critical metadata and attach to images to get a comprehensive view of your content.

Box AI handles image documents with a resolution of 1024×1024 pixels, with a maximum of 5 images or 5 pages for multi-page images. If the number of image or image pages exceeds 5, the first 5 images or pages will be processed. If you set mode parameter to single_item_qa, the items array can have one element only. Currently Box AI does not support multi-modal requests. If both images and text are sent Box AI will only process the text.

Box AI API with Box Hubs

Press enter or click to view image in full size

The Box AI API ask endpoint now supports querying a Box Hub. Inputing hubs as the itemstype parameter, alongside a hub id (copied from a URL bar) and mode of single_item_qa will return information based on all content in a Box Hub.

For example, running the below cURL snippet…

curl -i -L POST "https://api.box.com/2.0/ai/ask" \
     -H "content-type: application/json" \
     -H "authorization: Bearer TOKEN" \
     -d '{
         "mode": "single_item_qa",
         "prompt": "PROMPT",
         "items": [
            {
            "type": "hubs",
            "id": "HUB_ID"
            }
         ]
      }'

will return a response like this…

{
  "answer": "ANSWER",
  "created_at": "DATE",
  "completion_reason": "done",
  "ai_agent_info": {
    "models": [{
      "name": "mlp__bge_large_gpu",
      "provider": "mlp",
      "supported_purpose": "embedding"
    }, {
      "name": "azure__openai__gpt_4o_mini",
      "provider": "azure"
    }],
    "processor": "long_text_multi"
  }
}

In order for a Box Hub to be queried by Box AI, both Box Hubs and Box AI must be turned on in the Box Admin Console. The Box Hub must have been indexed (which happens automatically) and have less than 10,000 files. Box Hubs are only available to Enterprise Plus and above license tiers. For the most up to date limitations, view this support page.

Box AI Studio API

The Box AI Studio API enables developers to create and deploy powerful Box AI agents specifically tailored to their unique needs — for instance, asking Box AI to act as a consulting expert that helps teams understand complex IT requirements to help address client concerns. The API extends the capabilities of the front-end launch of Box AI Studio released a couple months back, allowing Box admins and co-admins to generate and use Box AI agents almost immediately without using the front end.

Box for Salesforce updates

Our Box for Salesforce team has launched several updates that will make working with Box AI even easier. Checkout the release notes here.

With Box Doc Gen for Salesforce, teams can dynamically generate custom documents without leaving Salesforce, eliminating the need to manually create, modify, and process mission-critical documents — a process which can be tedious, time-consuming, and error-prone, resulting in significant productivity drains. This functionality can be installed using the default managed package in the app exchange, and utilizes Box Doc Gen behind the scenes to create content.

Box AI API support for scanned documents

The Box AI API metadata extraction freeform and structured endpoints can now support scanned documents. The documents must be stored as PDF files, and the process will run automatically in the background if files do not have text representation.

Please note, handwritten documents may not process correctly.

Wrap up

Box is thrilled to launch all of these features today, and we can’t wait to see what you build with them. Make sure to check out our launch webinar focused on Box AI. We will be spotlighting Miller Tanner using the Extract API agents in one of the demos.

Until then, happy coding!

Resources

Box AI API reference

Box AI API guides

Box AI API YouTube series

🦄 Want to engage with other Box Platform champions?

Join our Box Developer Community for support and knowledge sharing!