Using Llama 3.3 70B Instruct (free) on Microsoft Foundry

Implementation guide · Llama 3.3 · AI at Meta

ServerlessProvisionedOpen Weights

Microsoft Foundry exposes Llama 3.3 70B Instruct (free) through model ID llama-3.3-70b-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

Quick Start

1
Create an account at Microsoft Foundry and generate an API key.
2
Use the Microsoft Foundry SDK or REST API to call llama-3.3-70b-instruct — see the documentation for request format.
3
You'll be billed $0.71/1M input, $0.71/1M output tokens. See full pricing.