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.
deepinfra
32 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 | 2773 ms |
|---|---|
| p95 TTFT | 4744 ms |
| p50 TTFB | 2827 ms |
| Effective throughput | — |
| Uptime | 90.62% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| qwen/qwen3.5-27b | 2643 ms | 2642 ms | — | 100.00% | — | 4 |
| google/gemma-3-12b-it | 2651 ms | 2651 ms | — | 100.00% | — | 7 |
| google/gemma-4-26b-a4b-it | 2773 ms | 2773 ms | — | 100.00% | — | 6 |
| z-ai/glm-5.2 | 2827 ms | 2827 ms | — | 100.00% | — | 2 |
| google/gemma-3-4b-it | 2888 ms | 2888 ms | — | 100.00% | — | 1 |
| google/gemma-3-27b-it | 2992 ms | 2991 ms | — | 100.00% | — | 5 |
| meta-llama/llama-3.1-70b-instruct | 2716 ms | 2716 ms | — | 66.67% | — | 3 |
| google/gemma-4-31b-it | 4744 ms | 4744 ms | — | 50.00% | — | 4 |