Intel / article

Mercury 2 On Azure Foundry

Source: inceptionlabs.ai
Author: Inception
Date: Published Jun 24, 2026

Context

Inception's Mercury 2 deployment on Microsoft's Azure AI Foundry uses provisioned computing capacity. Developers select the model in the catalog and create an endpoint backed by allocated hardware. The deployment section specifies a flat hourly software-license charge, with compute billed separately through the customer's Azure account. The same announcement lists per- prices elsewhere but does not say how they apply to this licensing arrangement, so they should not be read as the cost of running a provisioned endpoint. Deployment details

Terms in this piece · Glossary

token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.

Read the source www.inceptionlabs.ai