OpenAI compatible API · Attested · Public status
Lightning AI performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Lightning AI.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
lightning
193 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 3309 ms |
|---|---|
| p95 TTFT | 5242 ms |
| p50 TTFB | 3204 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemma-4-31b-it | 2291 ms | 2290 ms | — | 100.00% | — | 14 |
| openai/gpt-3.5-turbo | 2649 ms | 2648 ms | — | 100.00% | — | 20 |
| openai/gpt-4o | 2773 ms | 2773 ms | — | 100.00% | — | 11 |
| google/gemini-2.5-flash | 2794 ms | 2793 ms | — | 100.00% | — | 12 |
| openai/gpt-4 | 2868 ms | 2868 ms | — | 100.00% | — | 15 |
| openai/gpt-4.1 | 2879 ms | 2879 ms | — | 100.00% | — | 20 |
| google/gemini-3.1-flash-lite-preview | 3309 ms | 3309 ms | — | 100.00% | — | 15 |
| google/gemini-3.5-flash | 3437 ms | 3437 ms | — | 100.00% | — | 24 |
| google/gemini-3-flash-preview | 3586 ms | 3586 ms | — | 100.00% | — | 15 |
| openai/gpt-4-turbo | 3699 ms | 3699 ms | — | 100.00% | — | 8 |
| google/gemini-3.1-pro-preview | 4468 ms | 4468 ms | — | 100.00% | — | 20 |
| google/gemini-2.5-pro | 5242 ms | 5242 ms | — | 100.00% | — | 19 |