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.
Basetenbaseten
18 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 | 1460 ms |
|---|---|
| p95 TTFT | 2131 ms |
| p50 TTFB | 1460 ms |
| Effective throughput | — |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| thinkingmachines/inkling-1m | 1130 ms | 1129 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k2.6 | 1214 ms | 1214 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1242 ms | 1242 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 1460 ms | 1460 ms | — | 100.00% | — | 2 |
| z-ai/glm-4.7 | 1487 ms | 1487 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.7-code | 1541 ms | 1541 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 1675 ms | 1675 ms | — | 100.00% | — | 2 |
| nvidia/nemotron-3-ultra-550b-a55b | 1946 ms | 1946 ms | — | 100.00% | — | 1 |