Fireworks AI & Open Models — Azure AI Foundry Architecture & Agent Service

[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3
SEQ. 4
SEQ. 5

Fireworks AI & Open Models

🚀 Azure AI Foundry Architecture & Agent Service 10 min 80 BASE XP⌨ HANDS-ON LAB

High-Performance Inference

Azure Foundry has partnered with Fireworks AI to provide ultra-fast inference for the latest open-weight models directly within the Foundry Open Models Catalog.

Supported Architectures

You can instantly deploy frontier open-weight and partner models like Meta Llama 4 Maverick & Llama 4 Scout, DeepSeek-R1, DeepSeek V4, DeepSeek V3.2, Mistral Large, Kimi 2.6, Grok 4.7, MiniMax M2.5, and gpt-oss-120b directly from Foundry Models using Serverless APIs (Models-as-a-Service) and Fireworks' ultra-low-latency inference engine.

This allows enterprises to use the absolute cutting edge of the open-source world with the same security, RBAC, and SLA guarantees as first-party Azure models.

⌨ HANDS-ON LABDeploy Open Model via Fireworks Serverless API
⭐ +200 XP

Provision a low-latency serverless endpoint for DeepSeek-R1 / Llama-3.3 backed by Fireworks AI on Foundry.

1Create a serverless deployment using the Fireworks partner catalog in Foundry.
lab-sandbox — simulated environment
INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$
OBJECTIVE 1 / 1 — type "hint" if stuck
FOUNDRY VERIFICATION
QUERY 1 // 1
What role does Fireworks AI play in Azure Foundry?
It provides the UI
It provides ultra-fast inference for deploying the latest open-weight models like DeepSeek V4
It is a vector database
It monitors billing