OpenAI compatible API · Attested · Public status

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.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Microsoft Azure AI Foundryazure

No provider claim

All providers

These privacy labels describe Microsoft Azure AI Foundry, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	Microsoft Azure AI Foundry
API operator country	US Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://azure.microsoft.com/en-us/products/ai-foundry/
Models	12 public models
Credits routes	12
Zero data retention	no
Verified confidential inference	Not verified
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

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

28 samples

Continuously 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	2173 ms
Effective throughput	116 tok/s n=3
Uptime	100.00%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
cohere/command-a	1280 ms	—	100.00%	—	4
x-ai/grok-4.20-reasoning	1556 ms	—	100.00%	—	2
moonshotai/kimi-k2.7-code	1631 ms	137 tok/s n=1	100.00%	—	3
x-ai/grok-4.1-fast-non-reasoning	1836 ms	—	100.00%	—	2
x-ai/grok-4.20-non-reasoning	2105 ms	—	100.00%	—	2
moonshotai/kimi-k2.5	2173 ms	—	100.00%	—	5
openai/gpt-5-mini	2337 ms	—	100.00%	—	4
x-ai/grok-4.1-fast-reasoning	2483 ms	—	100.00%	—	5
moonshotai/kimi-k2.6	3605 ms	116 tok/s n=2	100.00%	—	1

Microsoft Azure AI Foundry performance history · Full provider & model leaderboard.

Provider models

Models served by Microsoft Azure AI Foundry.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Input	Cached input	Output
`cohere/command-a` cohere-command-a	—	0	$2.6375/1M	Not published	$10.55/1M
`microsoft/mai-voice-2.1` Microsoft: MAI-Voice-2.1	—	5000 characters	$23.21/M characters	Not applicable	Included
`microsoft/mai-voice-2.1-flash` Microsoft: MAI-Voice-2.1-Flash	—	5000 characters	$15.825/M characters	Not applicable	Included
`microsoft/microsoft-decision-1` Microsoft Decision-1	—	32,768	$0.04431/1M	Not published	selected route
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5	IQ 110#74	262,144	$0.633/1M	$0.1055/1M	$3.165/1M
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks	IQ 115#52	262,144	$1.00225/1M	$0.1688/1M	$4.22/1M
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks	IQ 112#66	262,144	$1.00225/1M	$0.20045/1M	$4.22/1M
`openai/gpt-5-mini` OpenAI: GPT-5 Mini	—	400,000	$0.26375/1M	$0.026375/1M	$2.11/1M
`x-ai/grok-4.1-fast-non-reasoning` grok-4-1-fast-non-reasoning	—	0	$0.211/1M	Not published	$0.5275/1M
`x-ai/grok-4.1-fast-reasoning` grok-4-1-fast-reasoning	—	0	$0.211/1M	Not published	$0.5275/1M
`x-ai/grok-4.20-non-reasoning` grok-4-20-non-reasoning	—	0	$1.31875/1M	Not published	$2.6375/1M
`x-ai/grok-4.20-reasoning` grok-4.20-0309-reasoning	—	0	$1.31875/1M	Not published	$2.6375/1M

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 12 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.