OpenAI compatible API · Attested · Public status

Lightning AI performance

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Lightning AI.

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

Lightning AIlightning

47 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 TTFT2169 ms
p95 TTFT4885 ms
p50 TTFB2474 ms
Effective throughput48 tok/s n=4
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
google/gemma-4-31b-it 583 ms 583 ms 128 tok/s n=1 100.00% 3
openai/gpt-4o 1442 ms 1442 ms 100.00% 5
google/gemini-2.5-flash 1751 ms 1751 ms 100.00% 7
openai/gpt-4.1 1815 ms 1815 ms 100.00% 1
openai/gpt-4 1867 ms 1867 ms 100.00% 3
openai/gpt-3.5-turbo 1892 ms 1892 ms 100.00% 4
google/gemini-3.5-flash 2169 ms 2168 ms 45 tok/s n=2 100.00% 7
google/gemini-3-flash-preview 2602 ms 2602 ms 100.00% 3
openai/gpt-4-turbo 2674 ms 2673 ms 100.00% 2
google/gemini-3.1-pro-preview 2774 ms 2774 ms 51 tok/s n=1 100.00% 2
google/gemini-3.1-flash-lite-preview 3756 ms 3755 ms 100.00% 4
google/gemini-2.5-pro 3797 ms 3797 ms 100.00% 6
Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

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