OpenAI compatible API · Attested · Public status
Baseten performance
Review measured TTFT, TTFB, 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
55 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 | 1767 ms |
|---|---|
| p95 TTFT | 4034 ms |
| p50 TTFB | 1766 ms |
| Effective throughput | 86 tok/s n=18 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| thinkingmachines/inkling-small | 725 ms | 725 ms | 182 tok/s n=2 | 100.00% | — | 3 |
| moonshotai/kimi-k2.7-code | 892 ms | 892 ms | 178 tok/s n=2 | 100.00% | — | 3 |
| deepseek/deepseek-v4-pro | 1267 ms | 1266 ms | 59 tok/s n=1 | 100.00% | — | 6 |
| openai/gpt-oss-120b | 1365 ms | 1365 ms | 82 tok/s n=2 | 100.00% | — | 4 |
| moonshotai/kimi-k3 | 1385 ms | 1385 ms | 17 tok/s n=1 | 100.00% | — | 5 |
| z-ai/glm-4.7 | 1573 ms | 1573 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash-0731 | 1767 ms | 1766 ms | 177 tok/s n=2 | 100.00% | — | 6 |
| moonshotai/kimi-k2.6 | 2165 ms | 2165 ms | 92 tok/s n=2 | 100.00% | — | 5 |
| nvidia/nemotron-3-ultra-550b-a55b | 2186 ms | 2186 ms | 83 tok/s n=2 | 100.00% | — | 7 |
| z-ai/glm-5.2-fast | 2220 ms | 2220 ms | 86 tok/s n=2 | 100.00% | — | 2 |
| thinkingmachines/inkling-1m | 2474 ms | 2474 ms | 71 tok/s n=1 | 100.00% | — | 4 |
| z-ai/glm-5.2 | 2918 ms | 2917 ms | 49 tok/s n=1 | 100.00% | — | 7 |