OpenAI compatible API · Attested · Public status
Thinking Machines Lab performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Thinking Machines Lab on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Thinking Machines Labthinkingmachines
31 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 | 1474 ms |
|---|---|
| p95 TTFT | 2389 ms |
| Effective throughput | 159 tok/s n=2 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| thinkingmachines/inkling-small | 1535 ms | — | 100.00% | 3 provider_error |
14 |
| z-ai/glm-5.3 | 1189 ms | 159 tok/s n=2 | 100.00% | — | 8 |
| thinkingmachines/inkling | 1474 ms | — | 100.00% | 1 provider_error |
9 |