Find a model

Browse the full catalog →

OpenAI compatible API · Attested · Public status

Microsoft Azure AI Foundry performance

Review measured TTFT, effective throughput, uptime, and sampled model routes for Microsoft Azure AI Foundry on TrustedRouter using metadata-only production probes.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

Microsoft Azure AI Foundryazure

16 samples

Provider overview

Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.

p50 TTFT1335 ms
p95 TTFT8982 ms
Effective throughput102 tok/s n=2
Uptime100.00%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
x-ai/grok-4.20-non-reasoning 1188 ms — 100.00% — 3
cohere/command-a 1215 ms — 100.00% — 3
x-ai/grok-4.20-reasoning 1335 ms — 100.00% — 4
moonshotai/kimi-k2.7-code 1617 ms 94 tok/s n=1 100.00% — 1
openai/gpt-5-mini 1943 ms — 100.00% — 1
x-ai/grok-4.1-fast-reasoning 3062 ms — 100.00% — 4
moonshotai/kimi-k2.6 — 110 tok/s n=1 — — 0
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

By continuing you agree to the terms of service and privacy policy.