LLMs in Prod 2025: Insights from 2 Trillion+ Tokens
Real-world analysis of 2Trillion+ production tokens across 90+ regions on Portkey's AI Gateway. Get the full LLMs in Prod'25 report today.
Siddharth Sambharia
Jamming on Event-Driven Architecture and MCP for Multi-Agentic Systems
Insights from Portkey's AI Practitioners Meetup on building scalable multi-agent systems. Learn about Event-Driven Architecture patterns, Model Context Protocol implementation, and real-world experiences building multi-agents system.
LLMs in Prod: The Reality of AI Outages, No LLM is Immune
This is Part 2 of our series analyzing Portkey's critical insights from production LLM deployments. Today, we're diving deep into provider reliability data from 650+ organizations, examining outages, error rates, and the real impact of downtime on AI applications. From the infamous OpenAI outage to the daily challenges of rate
LLMs In Prod: Day 1
This is Part 1 of our analysis diving into Portkey's year-end LLM production data. Over the next few days, we'll be unpacking insights from over 2 trillion tokens worth of production data to reveal how the AI ecosystem evolved in 2024.
Today, we're starting with the most crucial aspect: who's
LibreChat vs Open WebUI: Choose the Right ChatGPT UI for Your Organization
Looking to harness AI while keeping your data in-house? Dive into our comprehensive comparison of LibreChat and Open WebUI – two powerful open-source platforms that let you build secure ChatGPT-like systems.
7 Ways to Make Your Vercel AI SDK App Production-Ready
Learn how to make your Vercel AI SDK app production-ready with Portkey.
Step-by-step guide covers 5 key techniques: implementing guardrails, conditional routing, interoperability, reliability features, and observability.
Bridging the Gap: How Portkey AI Gateway Connected with MongoDB Helps Productionize AI Apps
Portkey’s open-source AI Gateway is used by thousands of AI companies to take their apps to production. Learn how these companies tackle crucial LLM challenges and build apps that delight users.