The AI governance problem in higher education and how to solve it
From cost control to safe tool access, managing GenAI across campus isn’t simple. This post breaks down the operational challenges and what a centralized AI gateway should solve.
Latest
Everything We Know About Claude Code Limits
Last updated - March 2026
TL;DR
* For Claude.ai Users:
The core limit is a 5-hour rolling session that begins with your first prompt. Weekly quotas (introduced August 28, 2025) now apply to heavy users on Claude Pro and Claude Max plans. All Claude.ai plans share a common
Scaling LibreChat for enterprise use: tracking, visibility, and governance
LibreChat is powerful, but lacks the control and visibility enterprises need. Learn how Portkey makes LibreChat production-ready with governance, observability, and security guardrails.
Making Claude Code work for enterprise-scale use with an AI Gateway
Learn how to make Claude Code enterprise-ready with Portkey. Add visibility, access control, logging, and multi-provider routing to scale safely across teams.
Retries, fallbacks, and circuit breakers in LLM apps: what to use when
Retries and fallbacks aren’t enough to keep AI systems stable under real-world load. This guide breaks down how circuit breakers work, when to use them, and how to design for failure across your LLM stack.
How to add enterprise controls to OpenWebUI: cost tracking, access control, and more
Learn how to add enterprise features like cost tracking, access control, and observability to your OpenWebUI deployment using Portkey.
Building the world's fastest AI Gateway - stream transformers
In January of this year, we released unified routes for file uploads and batching inference requests. With these changes, users on Portkey can now:
1. Upload a single file for asynchronous batching and use it across different providers without having to transform the file to the model-specific format
2. Upload