distribution · May 17, 2026

Fireworks AI Integrates as First-Party Inference Provider on Microsoft Azure AI Foundry

Fireworks AI became available as a first-party inference provider inside Microsoft Foundry enabling deployment and scaling of open-weight models with enterprise-grade infrastructure. The integration combines Fireworks inference engine with Azure enterprise control plane for high-throughput inference. Fireworks AI on Foundry supports Bring Your Own Weights and state-of-the-art open models with predictable performance via PTUs. The partnership was highlighted in Microsoft Build 2026 preparations with teams from both companies participating.