OpenAI compatible API · Attested · Public status

Lightning AI performance

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

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

Lightning AIlightning

41 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 TTFT1844 ms
p95 TTFT5092 ms
p50 TTFB2974 ms
Effective throughput48 tok/s n=4
Uptime97.56%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
lightning-ai/nemotron-3-ultra-550b-a55b 1078 ms 1078 ms 100.00% 1
lightning-ai/gpt-oss-120b 1399 ms 1399 ms 100.00% 3
openai/gpt-4 1588 ms 1588 ms 100.00% 2
openai/gpt-3.5-turbo 1659 ms 1659 ms 100.00% 6
lightning-ai/gpt-oss-20b 1738 ms 1738 ms 100.00% 1
openai/gpt-4.1 1844 ms 1844 ms 100.00% 2
google/gemini-3-flash-preview 2498 ms 2498 ms 100.00% 1
lightning-ai/deepseek-v4-pro 2856 ms 2856 ms 100.00% 2
openai/gpt-4o 3118 ms 3118 ms 100.00% 1
google/gemini-3.1-flash-lite-preview 3240 ms 3240 ms 100.00% 1
lightning-ai/nemotron-3-nano-omni-30b-a3b-reasoning 3879 ms 3879 ms 100.00% 3
google/gemini-2.5-flash-lite-preview-06-17 4385 ms 4383 ms 100.00% 1
google/gemini-3.5-flash 4766 ms 4765 ms 50 tok/s n=1 100.00% 1
openai/gpt-4-turbo 5066 ms 5066 ms 100.00% 1
google/gemini-2.5-pro 5092 ms 5092 ms 100.00% 4
google/gemini-2.5-flash 100.00% 1
google/gemma-4-31b-it 151 tok/s n=1 100.00% 9
google/gemini-3.1-pro-preview 45 tok/s n=2 0
openai/gpt-5-nano 0.00% 1 unsupported_route 1
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.