TrustedRouter

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

29 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 TTFT2173 ms
p95 TTFT3638 ms
Effective throughput112 tok/s n=4
Uptime100.00%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
cohere/command-a 1476 ms — 100.00% — 5
x-ai/grok-4.20-reasoning 1556 ms — 100.00% — 2
moonshotai/kimi-k2.7-code 1631 ms 109 tok/s n=2 100.00% — 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
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.