> ## Documentation Index > Fetch the complete documentation index at: https://developer.box.com/llms.txt > Use this file to discover all available pages before exploring further. # Supported AI models export const SignupCTA = ({children}) => { return
{children}
Get started for free Already have an account? Log in
; }; export const CustomCard = ({icon, title, href, tags, children, ...props}) => { const handleClick = e => { if (href) { e.preventDefault(); window.location.href = href; } }; const getDescription = () => { if (children) { if (typeof children === "string") { return children; } else { const childrenArray = Array.isArray(children) ? children : [children]; for (const child of childrenArray) { if (typeof child === "string") { return child; } else if (child && typeof child === "object" && child.props?.children) { const childText = child.props.children; if (typeof childText === "string") { return childText; } } } } } return null; }; const description = getDescription(); const isCustomSvg = icon?.includes('/') || icon?.includes('.svg'); const iconSize = isCustomSvg ? 48 : 24; return

{title}

{description &&
{description}
} {tags && tags.length > 0 &&
{tags.map((tag, index) => { const bgColor = tag.bgColor || tag.backgroundColor || "#e5e7eb"; return {tag.text || tag.label} ; })}
} ; }; export const Link = ({href, children, className, ...props}) => { const localizedHref = href; return {children} ; }; Box supports a variety of AI models, categorized along two dimensions: [access level](#access-levels) and [capability tier](#capability-tiers). ## Access levels | Level | Description | Configuration Required | | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- | | [**Core models**](#core-box-ai-models) | Built into Box AI and available by default for all customers | None | | [**Customer-enabled models**](#customer-enabled-models) | Require activation by Box admins in the Admin Console or a request to Box. Some models may be subject to additional terms or pricing. | Yes | ## Capability tiers | Tier | Description | Best For | | ------------------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | | **Standard models** | High-speed, cost-efficient performance | Basic summarization, Q\&A, structured data extraction from shorter or simpler documents. High-volume, low-complexity use cases | | **Premium models** | Advanced reasoning, larger context windows, better performance on complex content | Multi-step reasoning, large taxonomies, lengthy or unstructured documents, domain-specific content | A model can be both customer-enabled and premium, or core and standard. In other words, access level and capability tiers are independent categorizations (for example, models can be either capability tier regardless of access level). The two categorizations are complementary. ## Using models How to use the supported AI models: * Get the default AI agent configuration. * Override the AI agent configuration used in `POST 2.0/ai/ask`, `POST 2.0/ai/text_gen`, `POST 2.0/ai/extract`, `POST 2.0/ai/extract_structured` endpoints. When using the `model` parameter in your API calls, use the **API Name** visible on each model card listed below. For example, to get the AI agent configuration for a specific model, use the model parameter and provide the `azure__openai__gpt_4o_mini` API name. Make sure you use **two underscores** after the provider name. The list may change depending on the model availability. A free developer account gives you access to these AI models through the Box AI API. Start making API calls to test summarization, extraction, and more. ## Core models Box AI is powered by the following AI models. These models are integrated with Box AI to facilitate various use cases while adhering to enterprise grade standards. Below, you’ll find information about each model, including its capabilities, intended applications, and applicable usage guidelines. Models offered in **Preview** mode have not been fully performance-tested at scale. You may experience variability in output quality, availability, and accuracy. Multimodal model for both broad general-purpose work and most coding tasks Premium Compatible with Box Agent Multimodal model for coding and agentic tasks across various industries Premium Compatible with Box Agent Multimodal model with enterprise-grade performance and adaptive reasoning Premium Multimodal model with advanced reasoning and long-context understanding Premium Model designed for well-defined tasks and precise prompts, suitable for lightweight tasks Standard Multimodal model, highly efficient in handling complex, multi-step tasks Premium ISMAP FedRAMP Moderate FedRAMP High DoD IL2 Multimodal model designed to handle lightweight tasks and precise prompts Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL2 Multimodal model, highly efficient in handling complex, multi-step tasks Premium ISMAP FedRAMP Moderate FedRAMP High DoD IL2 Multimodal model for lightweight tasks and precise prompts, best suited for focused tasks Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL2 2nd-generation embedding model for text search, code search, and sentence similarity Embeddings Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL2 Multimodal model with a 1 million token context window and advanced reasoning capabilities Premium ISMAP FedRAMP Moderate FedRAMP High DoD IL5 Multimodal model offering well-round capabilites, including thinking capabilities Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL5 Multimodal model designed for optimal high-volume, high-frequency tasks at scale Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL5 Multimodal model designed to handle lightweight tasks Standard ISMAP FedRAMP Moderate FedRAMP High DoD IL5 Multimodal model for complex tasks with a 1 million token context window Premium Compatible with Box Agent Multimodal model for complex tasks with a 1 million token context window Premium Compatible with Box Agent Premium model combining maximum intelligence with practical performance Premium ISMAP FedRAMP Moderate Compatible with Box Agent Model that excels at complex agents, coding, and autonomous multi-step workflows Premium ISMAP FedRAMP Moderate Compatible with Box Agent Fast and cost-efficient model with near-frontier intelligence best for low-latency applications Standard ISMAP FedRAMP Moderate Compatible with Box Agent Model that excels at coding and complex problem-solving, powering frontier agents Premium ISMAP FedRAMP Moderate Model that brings frontier performance to everyday use cases Premium ISMAP FedRAMP Moderate Model designed to enhance language understanding and generation tasks Premium ISMAP FedRAMP Moderate Model designed to enhance language understanding and generation tasks Premium ISMAP FedRAMP Moderate Model tailored for various language tasks, creative writing, and conversational AI Standard ISMAP FedRAMP Moderate Model that brings frontier performance to everyday use cases Premium ISMAP FedRAMP Moderate Language model for advanced text processing and complex tasks with large context Standard ISMAP FedRAMP Moderate Multimodal model with a 1 million token context window and advanced reasoning capabilities Standard Natively multimodal, mixture-of-experts (MoE) model designed to handle lightweight tasks Standard Multimodal model designed to handle lightweight tasks Standard High-performance enterprise model for coding and advanced reasoning Preview Standard Fast open-source multimodal model with low latency Preview Standard ## Customer-enabled models Certain Box AI customers may enable additional AI models upon their request or upon the models otherwise being made available through their Admin Console. Use of these models may be subject to additional terms. By selecting a customer-enabled model, the customer acknowledges that their data may be processed by additional [subprocessors][subprocessors] of their choice. Models offered in **Beta** mode are provided on an as-is basis. Multimodal model, highly efficient in handling complex, multi-step tasks Beta Premium Model for complex tasks with advanced reasoning and a large context window Beta Premium Gemini multimodal model for high-speed and cost-efficient tasks Beta Standard Multimodal model for complex tasks with a 1 million token context window Beta Premium Multimodal model designed for speed and efficiency across a wide range of tasks Beta Premium Multimodal model for complex tasks with a 1 million token context window Beta Premium Multimodal model for complex tasks with a 1 million token context window Beta Premium ## Default models The following tables list the default AI models used when you do not override the agent configuration. The model that runs depends on the agent type, the provider, and the capability tier. Default settings shown below may not be applicable for certain customers with specific configurations or requirements. ### Legacy agents Legacy agents represent the initial generation of Box AI capabilities, designed to handle basic, single-step tasks such as simple Q\&A and document summarization. The table below specifies available models for a particular use case. | Use case | Provider | Model for Standard Version | Model for Advanced or Enhanced Version | | ----------------------------------- | ---------------- | ----------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | | Q\&A for Documents, Notes, and Hubs | OpenAI (Default) | GPT-5 mini | GPT-5.2 | | | Claude | Claude 4.5 Sonnet | Claude 4.5 Opus | | | Llama | Llama 4 Maverick | Llama 4 Maverick | ### Box agents Box agents are the next generation of intelligent assistants built with advanced reasoning and orchestration, capable of planning and executing complex, multi-step workflows across your entire Box content ecosystem. The table below specifies available models for each specialized agent type. | Agent | Model for Standard Version | Model for Pro or Enhanced Version | | ----------------------------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | | Box Agent | GPT 5.4 | Claude Sonnet 4.6 | | Extract Agent | Gemini 2.5 Flash | Gemini 2.5 Pro | | Security Classification Agent | Gemini 2.5 Flash | N/A | | Threat Analysis Agent | Gemini 2.5 Flash | N/A | [azure-ai-mini-4o-model]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=python-secure#gpt-4o-and-gpt-4-turbo [vertex-ai-model]: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#models [vertex-ai-gemini-models]: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models [vertex-text-models]: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text [azure-ai-embeddings]: https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#embeddings [aws-claude]: https://aws.amazon.com/bedrock/claude/ [aws-titan]: https://aws.amazon.com/bedrock/titan/ [subprocessors]: https://www.box.com/legal/subprocessors