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

202 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 TTFT3786 ms
p95 TTFT3907 ms
Effective throughput126 tok/s n=4
Uptime64.36%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
x-ai/grok-4.1-fast-reasoning 3786 ms — 58.62% — 174
moonshotai/kimi-k2.5 1073 ms — 100.00% — 3
x-ai/grok-4.1-fast-non-reasoning 1079 ms — 100.00% — 1
cohere/command-a 1191 ms — 100.00% — 5
moonshotai/kimi-k2.6 1497 ms 133 tok/s n=2 100.00% — 5
x-ai/grok-4.20-reasoning 1573 ms — 100.00% — 1
x-ai/grok-4.20-non-reasoning 1577 ms — 100.00% — 6
openai/gpt-5-mini 2288 ms — 100.00% — 2
moonshotai/kimi-k2.7-code 2671 ms 118 tok/s n=2 100.00% — 5
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

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