If you're a builder, you likely keep sending your LLM credentials on every request from your agents and applications. But if you operate in an enterprise environment, you'll want to store your credentials in a secure third-party like HashiCorp Vault or IDP provider and have the infrastructure inject the credentials for you dynamically. By doing so, you'll have:
✅ No leaks of credentials into agents
✅ Strong governance of LLM credentials in secure storage
✅ Ability to switch credentials on the fly without having to redeploy your agents
In this case, the infrastructure that secures the communication between the agents and the LLMs is an [AI gateway](https://konghq.com/blog/enterprise/what-is-an-ai-gateway)AI gateway, and the capability that allows you to manage and configure this behavior is our [Kong Konnect AI Manager](https://konghq.com/blog/product-releases/kong-ai-manager)Kong Konnect AI Manager.
Today, we're introducing the ability to configure dynamic authentication using a third-party like HashiCorp Vault in our AI Manager product.
***💡 Note: ***[Kong AI Gateway 2.0 ](https://konghq.com/blog/tag/ai-gateway)Kong AI Gateway 2.0 *is now available! The new release moves at the speed of the AI ecosystem, delivering rapid upgrades like MCP Server Bundling and dynamic cost management.*
As we ramp up the creations of AI-powered agents, it's important to keep them lean and focused while we delegate as much as we can to our infrastructure.
Kong’s AI Gateway does just that. It removes 50+ capabilities that we usually would have built ourselves — like observability, security, semantic acceleration, RAG pipelines, and more — and allows us to instead focus on our agentic business logic and intelligence by leveraging all these capabilities out of the box from the AI Gateway itself.
One of these capabilities is certainly authentication to the models themselves:
You can get started with Kong AI Gateway and AI Manager by [signing up on Konnect](https://konghq.com/products/kong-konnect/register)signing up on Konnect.
MCP ACLs, Claude Code Support, and New Guardrails New providers, smarter routing, stronger guardrails — because AI infrastructure should be as robust as APIs We know that successful AI connectivity programs often start with an intense focus on how
Today, we're excited to announce the general availability of AI Manager in Kong Konnect, the platform to manage all of your API, AI, and event connectivity across all modern digital applications and AI agents. Kong already provides the fastest and m
Today at API Summit , we're introducing one of the biggest new releases of our AI Gateway technology : a new class of intelligent semantic plugins, new advanced load balancing capabilities for LLMs, and the official support for AWS Bedrock and GCP
We’re pleased to announce the new LLM Usage reporting feature in Advanced Analytics, which aims to help organizations better manage their large language model (LLM) usage. This feature offers insights into token consumption, costs, and latency, allo
Most AI cost management starts with infrastructure. A provider can tell you that you consumed a certain number of input and output tokens on a particular model. An observability platform can show requests, latency, tokens, and traces. A cloud cost p
Bring Financial Accountability to Enterprise LLM Usage with Konnect Metering and Billing Showback and chargeback are not the same thing. Most organizations conflate these two concepts, and that conflation delays action. Understanding the LLM showb
