OpenAI compatible API · Attested · Public status
DeepInfra performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for DeepInfra.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
DeepInfradeepinfra
5 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 | 1779 ms |
|---|---|
| p95 TTFT | 1906 ms |
| p50 TTFB | 1778 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemma-4-26b-a4b-it | 1374 ms | 1374 ms | — | 100.00% | — | 2 |
| google/gemma-3-4b-it | 1779 ms | 1778 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 1786 ms | 1786 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.1-70b-instruct | 1906 ms | 1905 ms | — | 100.00% | — | 1 |