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

189 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 TTFT3315 ms
p95 TTFT5242 ms
p50 TTFB3239 ms
Effective throughput
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
google/gemma-4-31b-it 2291 ms 2290 ms 100.00% 13
openai/gpt-4o 2738 ms 2738 ms 100.00% 11
openai/gpt-3.5-turbo 2747 ms 2747 ms 100.00% 18
google/gemini-2.5-flash 2784 ms 2784 ms 100.00% 12
openai/gpt-4 2854 ms 2854 ms 100.00% 12
openai/gpt-4.1 2879 ms 2879 ms 100.00% 20
google/gemini-3.1-flash-lite-preview 3315 ms 3314 ms 100.00% 16
google/gemini-3.5-flash 3437 ms 3437 ms 100.00% 23
google/gemini-3-flash-preview 3586 ms 3586 ms 100.00% 15
openai/gpt-4-turbo 3628 ms 3628 ms 100.00% 8
google/gemini-3.1-pro-preview 4468 ms 4468 ms 100.00% 22
google/gemini-2.5-pro 5242 ms 5242 ms 100.00% 19
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.