OpenAI compatible API · Attested · Public status
Baseten performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Baseten on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Basetenbaseten
233 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 | 1238 ms |
|---|---|
| p95 TTFT | 3375 ms |
| Effective throughput | 125 tok/s n=8 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4.1-flash-1017-fast | 795 ms | — | 100.00% | — | 84 |
| deepseek/deepseek-v4.1-flash-fast | 1238 ms | — | 100.00% | — | 39 |
| reflection/beam-1.0 | 778 ms | — | 100.00% | 3 provider_error |
2 |
| deepseek/deepseek-v4.1-flash | 886 ms | — | 100.00% | — | 3 |
| nvidia/nemotron-3-ultra-550b-a55b | 904 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 923 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.3 | 1087 ms | 129 tok/s n=2 | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash-0731 | 1198 ms | — | 100.00% | 1 provider_error |
4 |
| meta-models/muse-spark-open | 1217 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1347 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3.5-super-vl-120b-a12b | 1495 ms | — | 100.00% | 1 provider_error |
1 |
| deepseek/deepseek-v4-pro-0813 | 1509 ms | 87 tok/s n=2 | 100.00% | — | 10 |
| z-ai/glm-5.2 | 2634 ms | 121 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.2-fast | 2954 ms | 133 tok/s n=2 | 100.00% | — | 78 |
| moonshotai/kimi-k3 | — | 71 tok/s n=1 | — | — | 0 |