メインコンテンツへスキップ
Box supports a variety of AI models, categorized along two dimensions: access level and capability tier.

アクセスレベル

Level説明Configuration Required
コアモデルBuilt into Box AI and available by default for all customersなし
顧客希望で有効化できるモデルRequire activation by Box admins in the Admin Console or a request to Box. Some models may be subject to additional terms or pricing.はい

機能レベル

Tier説明Best For
標準モデルHigh-speed, cost-efficient performanceBasic summarization, Q&A, structured data extraction from shorter or simpler documents. High-volume, low-complexity use cases
プレミアムモデルAdvanced reasoning, larger context windows, better performance on complex contentMulti-step reasoning, large taxonomies, lengthy or unstructured documents, domain-specific content
モデルは、顧客希望で有効化できるモデルかつプレミアムモデルにすることも、コアモデルかつ標準モデルにすることもできます。つまり、アクセルレベルと機能レベルは、それぞれ独立した分類です (たとえば、モデルは、アクセスレベルに関係なくどちらの機能レベルにもなる可能性があります)。この2つの分類は相互に補完します。

モデルの使用

サポートされているAIモデルの使用方法を以下に示します。
  • Get the .
  • Override the AI agent configuration used in , , , endpoints.
When using the model parameter in your API calls, use the API Name visible on each model card listed below. たとえば、特定のモデルのAIエージェントの構成を取得するには、パラメータを使用して、API名azure__openai__gpt_4o_miniを指定します。プロバイダ名の後に2つのアンダースコアを使用していることを確認してください。
このリストはモデルの提供状況により変更される可能性があります。

コアモデル

Box AIには以下のモデルが搭載されています。Box AIと統合されているこれらのモデルは、エンタープライズグレードの標準に準拠しながら、さまざまなユースケースを支援します。各モデルの機能、対象のアプリケーション、利用に関して該当するガイドラインなどの情報については、以下をご確認ください。
Models offered in Preview mode have not been fully performance-tested at scale. You may experience variability in output quality, availability, and accuracy.
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_5_4

Multimodal model for both broad general-purpose work and most coding tasksPremiumCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_5_2

Multimodal model for coding and agentic tasks across various industriesPremiumCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_5_1

エンタープライズグレードのパフォーマンスと適応的推論を備えたマルチモーダルモデルプレミアム
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_5

高度な推論機能と長いコンテキストの理解を備えたマルチモーダルモデルプレミアム
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_5_mini

Model designed for well-defined tasks and precise prompts, suitable for lightweight tasks標準
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

azure__openai__gpt_4_1

複雑なマルチステップタスクの処理で非常に効率的なマルチモーダルモデルPremiumISMAPFedRAMP ModerateFedRAMP HighDoD IL2
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

azure__openai__gpt_4_1_mini

Multimodal model designed to handle lightweight tasks and precise promptsStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL2
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

azure__openai__gpt_4o

複雑なマルチステップタスクの処理で非常に効率的なマルチモーダルモデルPremiumISMAPFedRAMP ModerateFedRAMP HighDoD IL2
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

azure__openai__gpt_4o_mini

Multimodal model for lightweight tasks and precise prompts, best suited for focused tasksStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL2
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

azure__openai__text_embedding_ada_002

2nd-generation embedding model for text search, code search, and sentence similarityEmbeddingsStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL2
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_2_5_pro

Multimodal model with a 1 million token context window and advanced reasoning capabilitiesPremiumISMAPFedRAMP ModerateFedRAMP HighDoD IL5
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_2_5_flash

Multimodal model offering well-round capabilites, including thinking capabilitiesStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL5
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_2_0_flash_001

Multimodal model designed for optimal high-volume, high-frequency tasks at scaleStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL5
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_2_0_flash_lite_preview

軽量のタスクを処理するように設計されたマルチモーダルモデルStandardISMAPFedRAMP ModerateFedRAMP HighDoD IL5
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_6_opus

Multimodal model for complex tasks with a 1 million token context windowPremiumCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_6_sonnet

Multimodal model for complex tasks with a 1 million token context windowPremiumCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_5_opus

最高峰のインテリジェンスと実用的な性能を兼ね備えたプレミアムモデルPremiumISMAPFedRAMP ModerateCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_5_sonnet

複雑なエージェント、コーディング、自律的なマルチステップワークフローに優れているモデルPremiumISMAPFedRAMP ModerateCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_5_haiku

Fast and cost-efficient model with near-frontier intelligence best for low-latency applicationsStandardISMAPFedRAMP ModerateCompatible with Box Agent
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_opus

Model that excels at coding and complex problem-solving, powering frontier agentsPremiumISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_4_sonnet

日常的なユースケースに最先端のパフォーマンスをもたらすモデルPremiumISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_3_7_sonnet

言語の理解と生成のタスクを強化するよう設計されたモデルPremiumISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_3_5_sonnet

言語の理解と生成のタスクを強化するよう設計されたモデルPremiumISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_3_haiku

Model tailored for various language tasks, creative writing, and conversational AIStandardISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__claude_3_sonnet

日常的なユースケースに最先端のパフォーマンスをもたらすモデルPremiumISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/claude.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=bd3fefa10e30eac617a43ae7609ac43a

aws__titan_text_lite

Language model for advanced text processing and complex tasks with large contextStandardISMAPFedRAMP Moderate
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/meta.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f7b4cbde68a60d7c515774808c8d50d1

ibm__llama_4_maverick

Multimodal model with a 1 million token context window and advanced reasoning capabilities標準
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/meta.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f7b4cbde68a60d7c515774808c8d50d1

ibm__llama_4_scout

Natively multimodal, mixture-of-experts (MoE) model designed to handle lightweight tasks標準
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/meta.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f7b4cbde68a60d7c515774808c8d50d1

ibm__llama_3_2_90b_vision_instruct

軽量のタスクを処理するように設計されたマルチモーダルモデル標準
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/mistral.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f130e27cd17d2cbcce4ad92affe1940b

ibm__mistral_medium_2505

コーディングや高度な推論に対応した、高性能のエンタープライズモデルPreviewStandard
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/mistral.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f130e27cd17d2cbcce4ad92affe1940b

ibm__mistral_small_3_1_24b_instruct_2503

低レイテンシで処理の速いオープンソースのマルチモーダルモデルPreviewStandard

顧客希望で有効化できるモデル

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 of their choice.
Models offered in Beta mode are provided on an as-is basis.
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/openai.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=84744284448f6109a9058cef53c3e01c

openai__gpt_o3

複雑なマルチステップタスクの処理で非常に効率的なマルチモーダルモデルBetaPremium
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_3_1_pro

高度な推論機能と大きなコンテキストウィンドウを備えた、複雑なタスク向けのモデルBetaPremium
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_3_1_flash_lite

Gemini multimodal model for high-speed and cost-efficient tasksBetaStandard
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_3_pro

Multimodal model for complex tasks with a 1 million token context windowBetaPremium
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/gemini.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=0d2975259aaa026bd24aa72adedc55f6

google__gemini_3_flash

Multimodal model designed for speed and efficiency across a wide range of tasksBetaPremium
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/grok.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f11f53fd44df5708ae7379de920ada3d

xai__grok_3_beta

Multimodal model for complex tasks with a 1 million token context windowBetaPremium
https://mintcdn.com/box/ZIWJfhT3Dv9f-PF4/static/guides-box-ai-ai-models/grok.svg?fit=max&auto=format&n=ZIWJfhT3Dv9f-PF4&q=85&s=f11f53fd44df5708ae7379de920ada3d

xai__grok_3_mini_beta

Multimodal model for complex tasks with a 1 million token context windowBetaPremium

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.
ユースケースProviderModel for Standard VersionModel for Advanced or Enhanced Version
Q&A for Documents, Notes, and HubsOpenAI (Default)
Claude
Llama

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.
AgentModel for Standard VersionModel for Pro or Enhanced Version
Box Agent
Extract Agent
Security Classification Agentなし
Threat Analysis Agentなし