Mistral Made Crystal Clear · chapter 2: The Mental Model: API, App, or Your Own Hardware
Where Azure fits, the same weights, a fourth path, a different data boundary
2026-10-01
Below: the paragraph from the book that builds this idea, then the diagram itself (Figure 2.2), and a recap. About a minute of reading.
Setting it up follows the same shape either way. Azure's own documentation describes it as four steps: create a new deployment for the model you want inside Azure's own console, note the deployment's endpoint URL and secret key, set them as environment variables (AZUREAI_ENDPOINT and AZUREAI_API_KEY), and query the endpoint using Mistral's SDKs or the REST API directly (docs.mistral.ai, captured 2026-09-04). If Chapter 3's quickstart already felt familiar by the time you finish it, this will too: authenticate with an environment variable, call an endpoint, read the response. The vendor relationship changes; the shape of the call barely does.
Recap
- The idea: Where Azure fits, the same weights, a fourth path, a different data boundary.
- The picture: Figure 2.2, from chapter 2 ("The Mental Model: API, App, or Your Own Hardware") of Mistral Made Crystal Clear.
- Go deeper: the chapter builds this step by step, with recipes and sources at the end.
This diagram is one of many in Mistral Made Crystal Clear.
Every chapter opens with the gist, draws the hard ideas, and ends with recipes and sources.
Get the book
