Engineering Insights

Service tiers now available on AI Gateway

AI Gateway now supports service tiering. Service tiers let you optimize for latency, throughput, and cost per request to match your use case. Pick a faster tier for interactive workloads (less queueing, higher token throughput), or a lower cost tier for background jobs that can tolerate more latency. At launch, service tiering is available for OpenAI and Gemini models. work across every AI Gateway API format: , , , , and . AI Gateway adjusts billing based on the tier each request used.Service t

This Week in Spring - July 21st, 2026

David Vélez and Robin Vince join the boards of the OpenAI Foundation and OpenAI Group PBC

David Vélez and Robin Vince join the boards of the OpenAI Foundation and OpenAI Group PBC, bringing global leadership in finance, technology, and governance.

Elastic Stack 9.4.3 released

Version 9.4.3 of the Elastic Stack was released today. We recommend you upgrade to this latest version. We recommend 9.4.3 over the previous versions 9.4.2 For details of the issues that have been fixed and a full list of changes for each product in this version, please refer to the release notes.

Elastic Stack 9.4.4 released

Version 9.4.4 of the Elastic Stack was released today. We recommend you upgrade to this latest version. We recommend 9.4.4 over the previous versions 9.4.3 For details of the issues that have been fixed and a full list of changes for each product in this version, please refer to the release notes.

Elastic Stack 9.3.8 released

Version 9.3.8 of the Elastic Stack was released today. We recommend you upgrade to this latest version. We recommend 9.3.8 over the previous versions 9.3.7 For details of the issues that have been fixed and a full list of changes for each product in this version, please refer to the release notes.

Elastic Stack 8.19.19 released

Version 8.19.19 of the Elastic Stack was released today. We recommend you upgrade to this latest version. We recommend 8.19.19 over the previous version 8.19.18 For details of the issues that have been fixed and a full list of changes for each product in this version, please refer to the release notes.

AI-native isn't a chatbot. It's an MCP server.

The chatbot trap Open any product changelog from the last year and you'll find the same move: a chat bubble in the corner, a sparkle icon, a launch post with the word AI in the headline. The widget answers questions about the product. Sometimes it drafts an email. Everyone ships it, everyone calls it AI-native, and almost everyone is solving the wrong layer. A chat widget is a conversation about your product. It sits on top of the UI and paraphrases your docs. The model never touches your doma