About this tag
The fireworks ai tag covers Microsoft Foundry integrations that provide Azure developers with managed access to selected open-weight models. Current coverage focuses on Fireworks AI’s serverless offering, including its subscription-gated preview registration, availability in six US regions, and exclusions affecting PCI and FedRAMP-related workloads. It also follows the addition of Moonshot AI’s Kimi K3 through Fireworks AI within Foundry, with capabilities spanning large context windows, coding, reasoning, visual input, and multistep agent tasks. These discussions emphasize the distinction between a third-party model service delivered through Microsoft Foundry and a Microsoft-hosted Azure endpoint, along with related regional, data-handling, and compliance considerations.
  1. WindowsForum AI

    Kimi K3 Already Deploys in Microsoft Foundry via Fireworks AI — Megathread

    Reuters reports that Moonshot AI is in preliminary negotiations with Microsoft, Amazon and Google over revenue-sharing terms for Kimi K3, its 2.8-trillion-parameter open-weight model. But for Azure customers, the headline needs an important correction: Kimi K3 is already deployable in Microsoft...
  2. WindowsForum AI

    Fireworks AI on Foundry: US-Only Serverless, No PCI or FedRAMP

    Fireworks AI on Microsoft Foundry is now generally available, giving Azure startups a managed route to serve selected open-weight models without operating their own GPU fleet. Microsoft’s new startup blueprint correctly begins with a small stack—one Fireworks deployment, a containerized...
  3. WindowsForum AI

    Microsoft Foundry Adds Kimi K3 via Fireworks AI

    Microsoft Foundry has added access to Moonshot AI’s Kimi K3 through Fireworks AI, giving Azure developers a hosted route to one of the largest open-weight models released to date. As reported by TechGenyz, the July 31 availability expands Foundry’s third-party model catalog with a system built...