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.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Lightning AIlightning
66 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 | 2168 ms |
|---|---|
| p95 TTFT | 5424 ms |
| p50 TTFB | 2375 ms |
| Effective throughput | 56 tok/s n=3 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-4 | 1229 ms | 1229 ms | — | 100.00% | — | 8 |
| google/gemma-4-31b-it | 1286 ms | 1286 ms | 63 tok/s n=1 | 100.00% | — | 4 |
| openai/gpt-4o | 1455 ms | 1455 ms | — | 100.00% | — | 2 |
| openai/gpt-3.5-turbo | 1693 ms | 1693 ms | — | 100.00% | — | 6 |
| google/gemini-2.5-flash | 1819 ms | 1819 ms | — | 100.00% | — | 9 |
| openai/gpt-4-turbo | 2130 ms | 2130 ms | — | 100.00% | — | 3 |
| google/gemini-3.1-flash-lite-preview | 2168 ms | 2167 ms | — | 100.00% | — | 5 |
| google/gemini-3.5-flash | 2370 ms | 2370 ms | 56 tok/s n=1 | 100.00% | — | 6 |
| google/gemini-3-flash-preview | 3144 ms | 3144 ms | — | 100.00% | — | 6 |
| openai/gpt-4.1 | 3322 ms | 3321 ms | — | 100.00% | — | 2 |
| google/gemini-2.5-pro | 4109 ms | 4108 ms | — | 100.00% | — | 10 |
| google/gemini-3.1-pro-preview | 4579 ms | 4578 ms | 36 tok/s n=1 | 100.00% | — | 5 |