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

48 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 TTFT2530 ms
p95 TTFT4284 ms
p50 TTFB2538 ms
Effective throughput46 tok/s n=5
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
google/gemma-4-31b-it 1047 ms 1047 ms 102 tok/s n=2 100.00% 1
openai/gpt-3.5-turbo 1112 ms 1112 ms 100.00% 4
openai/gpt-4o 1572 ms 1572 ms 100.00% 5
openai/gpt-4.1 1849 ms 1849 ms 100.00% 6
google/gemini-3-flash-preview 2033 ms 2033 ms 100.00% 2
google/gemini-2.5-pro 2438 ms 2438 ms 100.00% 2
google/gemini-3.5-flash 2530 ms 2529 ms 40 tok/s n=1 100.00% 4
google/gemini-3.1-flash-lite-preview 2587 ms 2587 ms 100.00% 4
openai/gpt-4-turbo 2733 ms 2732 ms 100.00% 3
google/gemini-2.5-flash 3119 ms 3118 ms 100.00% 10
google/gemini-3.1-pro-preview 3257 ms 3257 ms 46 tok/s n=2 100.00% 4
openai/gpt-4 3474 ms 3474 ms 100.00% 3
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.