Our take
Microsoft Azure AI is an enterprise-grade cloud host with the broadest tracked catalogue of model offers and a strong compliance stack. Buyers can trade a small price premium for markedly higher throughput on the same model.
Use this for regulated workloads that need SOC 2, EU data residency, zero-retention guarantees, and a no-training-on-prompts commitment. Pick it when throughput matters and you want to optimise latency per dollar within one bill. Skip it if you need the absolute cheapest tier for every model, or if your workload is price-sensitive rather than latency-sensitive.
- Widest tracked catalogue — 80 offers.
- Strong compliance and data-sovereignty stack: SOC 2 attestation, EU-region endpoint, no training on prompts, and a zero-retention option.
- Tiered throughput pricing on identical models lets buyers optimise latency per dollar. On one Nano model, 10% higher price buys 6.4x higher throughput; on another, 10% higher price buys 5.1x higher throughput.
- Highest-throughput tier for one Luna Pro model at 225 tokens/s.
- Premium pricing on some Nano-class models versus cheaper tiers of the same model family. One larger Nano variant starts at 4x the input price of the cheapest Nano tier.
- DeepSeek V4 Flash is not the cheapest tracked offer for that model.
Point your tools here
We have not recorded what a router needs for Microsoft Azure AI yet — no base URL and no docs link on file. That is our gap, not a sign Microsoft Azure AI has no API; its own documentation is the place to look until we close it.
Privacy & data handling
These answers cover requests sent to Microsoft Azure AI through OpenRouter, as OpenRouter records them, last read 58 min ago. For Microsoft Azure AI's own API we hold no answer: check its terms. SOC 2 and the data processing agreement below are hand-checked, not part of that sync.
We have not dated this attestation or linked the report yet.
Prompt retention: none.