OpenAI compatible API · Attested · Public status
Thinking Machines Lab performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Thinking Machines Lab.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
thinkingmachines
66 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 | 2150 ms |
|---|---|
| p95 TTFT | 7526 ms |
| p50 TTFB | 2706 ms |
| Effective throughput | 77 tok/s n=2 |
| Uptime | 98.48% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| thinkingmachines/inkling-small | 2150 ms | 2150 ms | 93 tok/s n=1 | 100.00% | — | 39 |
| thinkingmachines/inkling | 3701 ms | 3701 ms | 61 tok/s n=1 | 96.30% | — | 27 |