Merge branch 'main' of github.com:box/developer.box.com

Author: SowaProgramuje

.spelling

@@ -366,3 +366,4 @@ add-ons
 cybersecurity
 SObject
 WatsonX
+400k

content/guides/box-ai/ai-models/azure-openai-gpt-4-1-mini-model-card.md

@@ -1,5 +1,5 @@
 ---
-rank: 5
+rank: 6
 related_guides:
   - box-ai/ai-tutorials/ask-questions
   - box-ai/ai-tutorials/generate-text

content/guides/box-ai/ai-models/azure-openai-gpt-4-1-model-card.md

@@ -1,5 +1,5 @@
 ---
-rank: 4
+rank: 5
 related_guides:
   - box-ai/ai-tutorials/ask-questions
   - box-ai/ai-tutorials/generate-text

content/guides/box-ai/ai-models/azure-openai-gpt-4o-mini-model-card.md

@@ -1,5 +1,5 @@
 ---
-rank: 7
+rank: 8
 related_guides:
   - box-ai/ai-tutorials/ask-questions
   - box-ai/ai-tutorials/generate-text

content/guides/box-ai/ai-models/azure-openai-gpt-4o-model-card.md

@@ -1,5 +1,5 @@
 ---
-rank: 6
+rank: 7
 related_guides:
   - box-ai/ai-tutorials/ask-questions
   - box-ai/ai-tutorials/generate-text

content/guides/box-ai/ai-models/azure-text-embedding-ada-002-model-card.md

@@ -1,5 +1,5 @@
 ---
-rank: 8
+rank: 9
 related_guides:
   - box-ai/ai-tutorials/ask-questions
   - box-ai/ai-tutorials/generate-text

content/guides/box-ai/ai-models/google-gemini-2-5-flash-model-card.md

@@ -0,0 +1,36 @@
+---
+rank: 16
+related_guides:
+  - box-ai/ai-tutorials/ask-questions
+  - box-ai/ai-tutorials/generate-text
+  - box-ai/ai-tutorials/extract-metadata
+  - box-ai/ai-tutorials/extract-metadata-structured
+  - box-ai/ai-agents/get-agent-default-config
+---
+
+# Google Gemini 2.5 Flash
+
+**Google Gemini 2.5 Flash** is a multimodal model, offering well-rounded capabilities. It features thinking capabilities, which lets you see the thinking process the model goes through when generating its response. 
+
+## Model details
+
+| Item  | Value | Description |
+|-----------|----------|----------|
+|Model name|**Google Gemini 2.5 Flash**| The name of the model. | 
+| Model category | Standard | The category of the model - standard or premium. |
+|API model name|`google__gemini_2_5_flash`| The name of the model that is used in the [Box AI API for model overrides][overrides]. The user must provide this exact name for the API to work. |
+|Hosting layer| **Google** | The trusted organization that securely hosts the LLM. |
+|Model provider|**Google**| The organization that provides this model. |
+|Release date|**June 17th 2025** | The release date for the model.|
+|Knowledge cutoff date| **January 2025**| The date after which the model does not get any information updates. |
+|Input context window |**1m tokens**| The number of tokens supported by the input context window.| 
+|Maximum output tokens |**64k tokens** |The number of tokens that can be generated by the model in a single request.| 
+|Empirical throughput| **Estimated between 163 - 300** | The number of tokens the model can generate per second.|
+|Open source | **No** | Specifies if the model's code is available for public use.|
+
+## Additional documentation
+
+For additional information, see [official Google Gemini 2.5 Flash documentation][vertex-ai-gemini-models].
+
+[vertex-ai-gemini-models]: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models
+[overrides]: g://box-ai/ai-agents/ai-agent-overrides

content/guides/box-ai/ai-models/ibm-mistral-medium-3-model-card.md

@@ -26,6 +26,7 @@ related_guides:
 | Maximum output tokens | **Not specified** | The number of tokens that can be generated by the model in a single request. | 
 | Empirical throughput| **Not specified** | The number of tokens the model can generate per second. |
 | Open source | **No** | Specifies if the model's code is available for public use. |
+| IP infringement protection | **No** | Use of this model does not come with any intellectual property rights assurances or protections from Box. Please consider any potential IP issues that might arise from using the model’s outputs. |
 
 ## Additional documentation
 

content/guides/box-ai/ai-models/ibm-mistral-small-3-1-model-card.md

@@ -26,6 +26,7 @@ related_guides:
 | Maximum output tokens | **Not specified** | The number of tokens that can be generated by the model in a single request.| 
 | Empirical throughput | **150** | The number of tokens the model can generate per second. |
 | Open source | **Yes** | Specifies if the model's code is available for public use. |
+| IP infringement protection | **No** | Use of this model does not come with any intellectual property rights assurances or protections from Box. Please consider any potential IP issues that might arise from using the model’s outputs. |
 
 ## Additional documentation
 

content/guides/box-ai/ai-models/index.md

@@ -59,6 +59,14 @@ Models offered in **Beta** mode have not been fully performance-tested at scale
 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.
 
 <TileGrid rows="2">
+    <Tile type="gpt" title="openai__gpt_5_1" href="/guides/box-ai/ai-models/openai-gpt-5-1-model-card">
+			A multimodal model with enterprise-grade performance and adaptive reasoning.
+   		<div>
+   			<strong style="background-color: #e8e8e8">Chat</strong>
+				<strong style="background-color: #e1ffe7">Available</strong>
+				<strong style="background-color: #f8d59b">Premium</strong>
+			</div>
+		</Tile> 
     <Tile type="gpt" title="openai__gpt_5" href="/guides/box-ai/ai-models/openai-gpt-5-model-card">
 			A multimodal model with advanced reasoning and long-context understanding.
    		<div>
@@ -69,7 +77,7 @@ Box AI is powered by the following AI models. These models are integrated with B
 				<strong style="background-color: #e1ffe7">Available</strong>
 				<strong style="background-color: #f8d59b">Premium</strong>
 			</div>
-		</Tile>
+		</Tile>   
 		<Tile type="gpt" title="azure__openai__gpt_4_1_mini" href="/guides/box-ai/ai-models/azure-openai-gpt-4-1-mini-model-card">
 			A multimodal model designed to handle lightweight tasks.
 			<div>
@@ -137,8 +145,20 @@ Box AI is powered by the following AI models. These models are integrated with B
         <strong style="background-color: #e1f8ff">DOD IL5</strong>        
 			</div>
 		</Tile>
+    <Tile type="gemini" title="google__gemini_2_5_flash" href="/guides/box-ai/ai-models/google-gemini-2-5-flash-model-card">
+		Gemini multimodal model offering well-round capabilites, including thinking capabilities.
+		  <div>
+		    <strong style="background-color: #e8e8e8">Default for Box AI Extract</strong>
+        <strong style="background-color: #e8e8e8">Chat</strong>
+		    <strong style="background-color: #e1ffe7">Available</strong>
+		    <strong style="background-color: #fdfad8">Standard</strong>
+        <strong style="background-color: #e1f8ff">FedRAMP Moderate</strong>
+        <strong style="background-color: #e1f8ff">FedRAMP High</strong>
+        <strong style="background-color: #e1f8ff">DOD IL5</strong>            
+		</div>
+	</Tile>
 	<Tile type="gemini" title="google__gemini_2_0_flash_001" href="/guides/box-ai/ai-models/google-gemini-2-0-flash-001-model-card">
-		Gemini multimodal model designed for optimal for high-volume, high-frequency tasks at scale.
+		Gemini multimodal model designed for optimal high-volume, high-frequency tasks at scale.
 		<div>
 		<strong style="background-color: #e8e8e8">Chat</strong>
 		<strong style="background-color: #e1ffe7">Available</strong>
@@ -151,7 +171,6 @@ Box AI is powered by the following AI models. These models are integrated with B
 	<Tile type="gemini" title="google__gemini_2_0_flash_lite_preview" href="/guides/box-ai/ai-models/google-gemini-2-0-flash-lite-preview-02-05">
 			Gemini multimodal model designed to handle lightweight tasks.
 			<div>
-				<strong style="background-color: #e8e8e8">Default for Box AI Extract</strong>
 				<strong style="background-color: #e8e8e8">Chat</strong>
 				<strong style="background-color: #e1ffe7">Available</strong>
 				<strong style="background-color: #fdfad8">Standard</strong>