OpenAI compatible API · Attested · Public status

OpenAI performance

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

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

OpenAIopenai

389 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 TTFT1924 ms
p95 TTFT4850 ms
Effective throughput
Uptime100.00%

Measured model routes

Modelp50 TTFTEffective throughputUptimeConfig excludedAvailability samples
openai/gpt-4o 3397 ms 100.00% 17
openai/gpt-4.1-mini 775 ms 100.00% 48
openai/gpt-4o-2024-05-13 876 ms 100.00% 1
openai/gpt-4.1-nano 1135 ms 100.00% 1
openai/gpt-4 1215 ms 100.00% 1
openai/gpt-4o-mini 1501 ms 100.00% 3
openai/gpt-4-turbo 1541 ms 100.00% 1
openai/gpt-3.5-turbo 1546 ms 100.00% 2
openai/gpt-5.6-luna 1557 ms 100.00% 9
openai/gpt-5.2 1800 ms 100.00% 2
openai/gpt-4.1 1924 ms 100.00% 106
openai/gpt-6-astra 2384 ms 100.00% 3
openai/gpt-3.5-turbo-1106 2476 ms 100.00% 1
openai/gpt-5-mini 3085 ms 100.00% 1
openai/gpt-4-0613 3329 ms 100.00% 3
openai/o4-mini 4064 ms 100.00% 2
openai/gpt-5 4210 ms 100.00% 3
openai/o3-mini 4520 ms 100.00% 1
openai/gpt-5-nano 100.00% 35
openai/text-embedding-3-large 100.00% 149
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.