> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# December

**Ending the year with MCP, intelligence, and enterprise controls! 🛠️**

This month we [announced our MCP(Model Context Protocol)](https://portkey.ai/mcp) product - enabling LLMs to leverage 800+ tools through a unified interface. We've also added dynamic usage limits on keys, integrated OpenAI's realtime API, and some new Guardrails. OpenAI's o1, Llama 3.3 models, Gemini & Perplexity's grounding features, and the entire HuggingFace model garden on Vertex AI are also available on Portkey now.

For enterprises, we're introducing comprehensive SSO/SCIM support, enhanced usage controls, and more.

Let's explore what's new!

## Summary

| Area | Key Updates |
| :- | :- |
| Platform | • Announced Portkey MCP Client with support for 800+ tools • Set Usage & budget limits for keys • New strict OpenAI compliance mode |
| Integrations | • Support for o1 and Llama 3.3  • Full HuggingFace model garden on Vertex AI • Support for Amazon Nova models • Gemini grounding mode for search-backed responses • Anthropic's new PDF input capabilities • Microsoft Semantic Kernel integration • Realtime API support |
| Enterprise | • Flexible SSO/SCIM for any OIDC/SAML provider • New workspace management APIs |
| Guardrail | • New guardrail integrations with Promptfoo, and Mistral Moderations • Enhanced regex guardrail capabilities |

## Model Context Protocol

[YouTube video player](https://www.youtube.com/embed/g2_vcYVB4Ig?si=oYkkE-5u7Wn4pLIb)

Portkey's Model Context Protocol client enables your AI agents to seamlessly interact with hundreds of tools while maintaining enterprise-grade observability and control.

* Connect to any database or data source
* Build and integrate custom tools
* Execute code safely in controlled environments
* Maintain complete observability and control

All while radically simplifying the complexity of tool calling with MCP.

> [card] [Join the MCP waitlist →](https://portkey.ai/mcp)

***

## Platform

**Dynamic Usage Limits**

![](https://mintcdn.com/portkey-docs/QFjngWBmb6CT7QXC/images/changelog/usage-limits.png?fit=max\&auto=format\&n=QFjngWBmb6CT7QXC\&q=85\&s=5fc135890a55bdaecd1f3ebe0272b160)

We're introducing comprehensive usage controls for both Virtual Keys and API Keys, giving platform teams precise control over LLM access and resource consumption. This release introduces:

* **Time-based Access Control**: Create short-lived keys that automatically expire after a specified duration – perfect for temporary access needs like POCs or time-limited projects

* **Resource Consumption Limits**: Set granular limits including:
  * Requests per minute (RPM) / Request per hour / Request per day
  * Tokens per minute (TPM) / Tokens per hour / Tokens per day
  * Budget caps based on cost incurred or tokens consumed, with periodic reset options (weekly/monthly)

**Enhanced Provider Features**

* Perplexity Integration: Full support for Perplexity API's advanced features including search domain filtering, related questions generation, and citation capabilities

> [card] [Browse Docs →](https://docs.portkey.ai/docs/integrations/llms/perplexity-ai.md#perplexity-specific-features)

**And, there's more!**

* **Bulk Prompt Management**: Move & Delete multiple prompt templates efficiently
* **Enhanced Logging**: Automatic language detection in logs view
* [**Local Gateway Console**](https://github.com/portkey-ai/gateway): Complete request logging with key statistics on the open source Gateway
* [**Virtual Key API**](https://docs.portkey.ai/docs/api-reference/admin-api/control-plane/virtual-keys/create-virtual-key.md): Programmatically create virtual keys for cloud deployments

> [card] [Gemini Grounding](https://docs.portkey.ai/docs/integrations/llms/gemini.md)
>
> Ground LLM responses with real-world data through Google search integration

> [card] [Anthropic PDF](https://docs.portkey.ai/docs/integrations/llms/anthropic.md)
>
> Native support for PDF processing in Anthropic models, with OpenAI's `image_url` field

> [card] [Realtime API](https://docs.portkey.ai/docs/product/ai-gateway/realtime-api.md)
>
> Complete request and response logging for OpenAI realtime API, including model response, cost, and guardrail violations

> [card] [Flag for Strict OpenAI Compliance](https://docs.portkey.ai/docs/product/ai-gateway/strict-open-ai-compliance.md)
>
> New flag to toggle provider-specific features while maintaining OpenAI API compatibility

## Enterprise

![](https://mintcdn.com/portkey-docs/QFjngWBmb6CT7QXC/images/changelog/sso.webp?fit=max\&auto=format\&n=QFjngWBmb6CT7QXC\&q=85\&s=600e4524a3182584d38428fd7ae782cd)

**Universal Identity Management**

* **SSO Integration**: Support for all major identity providers through OIDC/SAML standards, enabling seamless enterprise authentication
* **Automated User Management**: SCIM provisioning for automatic user lifecycle management - from onboarding to role changes and offboarding
* **Granular Access Control**: Define precise access patterns and manage permissions at both user and workspace levels
* **Workspace Management API**: Programmatically manage workspaces, user invites, and access controls

**Private Deployments**

Updated documentation for fully private Portkey installations with enhanced security configurations [(*Docs*)](https://github.com/Portkey-AI/helm/tree/main/charts)

## Integrations

**New Providers**

> [card] HuggingFace on Vertex
>
> Access the complete HuggingFace model garden through Vertex AI

> [card] Self-deployed models on Vertex
>
> You can now call your self-deployed models on Vertex AI through Portkey

> [card] Amazon Nova
>
> Support for Nova models in prompt playground

> [card] Azure AI Inference
>
> Full integration with Azure AI platform

> [card] Qdrant
>
> Route your Qdrant vector DB queries through Portkey

> [card] Additional Providers
>
> Nebius AI, Inference.net, Voyage AI, Recraft AI

**Model & Framework Updates**

> [card] OpenAI o1
>
> Integrated OpenAI's latest o1 model across OpenAI & Azure OpenAI

> [card] Llama 3.3
>
> Integration with Meta's latest Llama 3.3 model across multiple providers

> [card] [Microsoft Semantic Kernel](https://docs.portkey.ai/docs/api-reference/inference-api/sdks/c-sharp.md#microsoft-semantic-kernel-example)
>
> First-class C# support for Microsoft's Semantic Kernel framework

## Guardrails

> [card] Mistral Content Moderation
>
> Content moderation powered by Mistral's latest model

> [card] Promptfoo
>
> Comprehensive evals for jailbreak detection, harmful content, and PII identification

All guardrail responses now include detailed explanations for check results, helping you understand why specific checks passed or failed.

## Resources

Essential reading for your AI infrastructure:

* [Prompt Injection Attacks](https://portkey.ai/blog/prompt-injection-attacks-in-llms-what-are-they-and-how-to-prevent-them/): Understanding and preventing security risks
* [Real-time vs Batch Evaluation](https://portkey.ai/blog/real-time-guardrails-vs-batch-evals/): Choosing the right guardrail strategy

## Improvements

* Fixed Cohere streaming on Bedrock
* Improved media support in moderations API
* Enhanced regex guardrail functionality

***

## Support

> [card] [Need Help?](https://github.com/Portkey-AI/gateway/issues)
>
> Open an issue on GitHub

***

> [card] [Portkey is now PRISMA AIRS AI Gateway. See it in action.](https://www.paloaltonetworks.in/ai-security/ai-gateway?utm_source=portkey\&utm_medium=referral\&utm_campaign=prisma_airs\&utm_content=docs_nav#contact)
>
> Contact Us


## Related topics

- [December](https://docs.portkey.ai/docs/changelog/2025/december.md)
- [December '23 Migration](https://docs.portkey.ai/docs/support/portkeys-december-migration.md)
- [November](https://docs.portkey.ai/docs/changelog/2025/november.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.