OpenAI compatible API · Attested · Public status
Lightning AI performance
Review measured TTFT, 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
29 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 | 2003 ms |
|---|---|
| p95 TTFT | 4214 ms |
| Effective throughput | 47 tok/s n=4 |
| Uptime | 82.76% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| lightning-ai/deepseek-v4-pro | 1285 ms | — | 100.00% | — | 2 |
| lightning-ai/nemotron-3-ultra-550b-a55b | 1496 ms | — | 100.00% | — | 2 |
| google/gemini-2.5-flash | 1587 ms | — | 100.00% | — | 2 |
| lightning-ai/gpt-oss-20b | 1626 ms | — | 100.00% | — | 1 |
| google/gemini-3-flash-preview | 1716 ms | — | 100.00% | — | 2 |
| openai/gpt-4o | 1769 ms | — | 100.00% | — | 1 |
| openai/gpt-4 | 2003 ms | — | 100.00% | — | 3 |
| openai/gpt-4-turbo | 2198 ms | — | 100.00% | — | 3 |
| google/gemini-3.5-flash | 2269 ms | 35 tok/s n=1 | 100.00% | — | 1 |
| google/gemini-3.1-pro-preview | 2757 ms | 47 tok/s n=2 | 100.00% | — | 1 |
| openai/gpt-3.5-turbo | 3541 ms | — | 100.00% | — | 2 |
| google/gemini-2.5-pro | 3633 ms | — | 100.00% | — | 3 |
| google/gemini-3.1-flash-lite-preview | 4214 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | — | 382 tok/s n=1 | — | — | 0 |
| openai/gpt-5-nano | — | — | 0.00% | — | 1 |
| openai/gpt-5.4-2026-03-05 | — | — | 0.00% | — | 2 |
| openai/gpt-5.4-mini-2026-03-17 | — | — | 0.00% | — | 1 |
| openai/gpt-5.4-nano-2026-03-17 | — | — | 0.00% | — | 1 |