Fireworks AI in Microsoft Foundry for Open Model Inference
⚡ Microsoft announced the public preview of Fireworks AI on Microsoft Foundry, bringing high‑performance, low‑latency inference for open models to Azure. The integration provides day‑zero access to optimized open models (including MiniMax M2.5), serverless and provisioned pricing options, and bring‑your‑own‑weights support for quantized or fine‑tuned models. Foundry supplies a unified control plane for evaluation, deployment, governance, and observability so teams can operationalize open models without assembling bespoke stacks.
