Microsoft Azure AI Foundry
Explore Microsoft Azure AI Foundry models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Microsoft Azure AI Foundryazure
No provider claim
| Provider | Microsoft Azure AI Foundry |
|---|---|
| Routing status | Active |
| Provider website | https://azure.microsoft.com/en-us/products/ai-foundry/ |
| Models | 9 public models |
| Prepaid routes | 9 |
| BYOK routes | 0 |
| Zero data retention | no |
| Confidential compute | no |
| Provider E2EE | no |
| Policy note | No provider-ZDR, confidential-compute, or E2EE claim is currently tracked for TrustedRouter's Microsoft Foundry account. Azure model availability and pricing are synchronized directly from the account. Policy source |
Measured performance
34 samplesContinuously sampled across Microsoft Azure AI Foundry's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2265 ms |
|---|---|
| Effective throughput | 83 tok/s n=3 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| cohere/command-a | 1563 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k2.6 | 2097 ms | 63 tok/s n=1 | 100.00% | — | 8 |
| x-ai/grok-4.20-reasoning | 2265 ms | — | 100.00% | — | 5 |
| x-ai/grok-4.1-fast-non-reasoning | 2792 ms | — | 100.00% | — | 4 |
| x-ai/grok-4.20-non-reasoning | 2876 ms | — | 100.00% | — | 5 |
| x-ai/grok-4.1-fast-reasoning | 3037 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 3684 ms | 83 tok/s n=2 | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 4209 ms | — | 100.00% | — | 3 |
Microsoft Azure AI Foundry performance history · Full provider & model leaderboard.
Models served by Microsoft Azure AI Foundry.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
cohere/command-acohere-command-a |
— | 0 | 1 | $2.6375/1M | $10.55/1M | prepaid |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
IQ 111#48 | 262,144 | 1 | $0.633/1M | $3.165/1M | prepaid |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#24 | 262,144 | 1 | $1.00225/1M | $4.22/1M | prepaid |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#29 | 262,144 | 1 | $1.00225/1M | $4.22/1M | prepaid |
openai/gpt-5-miniOpenAI: GPT-5 Mini |
— | 400,000 | 1 | $0.26375/1M | $2.11/1M | prepaid |
x-ai/grok-4.1-fast-non-reasoninggrok-4-1-fast-non-reasoning |
— | 0 | 1 | $0.211/1M | $0.5275/1M | prepaid |
x-ai/grok-4.1-fast-reasoninggrok-4-1-fast-reasoning |
— | 0 | 1 | $0.211/1M | $0.5275/1M | prepaid |
x-ai/grok-4.20-non-reasoninggrok-4-20-non-reasoning |
— | 0 | 1 | $1.31875/1M | $2.6375/1M | prepaid |
x-ai/grok-4.20-reasoninggrok-4.20-0309-reasoning |
— | 0 | 1 | $1.31875/1M | $2.6375/1M | prepaid |
Questions
Does Microsoft Azure AI Foundry have zero data retention?
TrustedRouter does not currently mark Microsoft Azure AI Foundry as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Microsoft Azure AI Foundry end-to-end encrypted?
TrustedRouter does not currently mark Microsoft Azure AI Foundry as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Microsoft Azure AI Foundry models are available through TrustedRouter?
This page currently lists 9 public Microsoft Azure AI Foundry models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.