OpenAI compatible API · Attested · Public status
Baseten performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Baseten.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
baseten
160 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 | 2605 ms |
|---|---|
| p95 TTFT | 3962 ms |
| p50 TTFB | 2734 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| thinkingmachines/inkling-1m | 2484 ms | 2483 ms | — | 100.00% | — | 17 |
| openai/gpt-oss-120b | 2542 ms | 2542 ms | — | 100.00% | — | 27 |
| moonshotai/kimi-k2.7-code | 2583 ms | 2583 ms | — | 100.00% | — | 20 |
| nvidia/nemotron-3-ultra-550b-a55b | 2605 ms | 2605 ms | — | 100.00% | — | 22 |
| deepseek/deepseek-v4-pro | 2717 ms | 2717 ms | — | 100.00% | — | 18 |
| z-ai/glm-4.7 | 2761 ms | 2761 ms | — | 100.00% | — | 15 |
| moonshotai/kimi-k2.6 | 2951 ms | 2951 ms | — | 100.00% | — | 21 |
| z-ai/glm-5.2 | 3509 ms | 3509 ms | — | 100.00% | — | 20 |