OpenAI compatible API. Attested gateway. Public status.
Cerebras performance
Measured TTFT, TTFB, throughput, uptime, and sampled model routes for Cerebras.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
cerebras
320 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 | 895 ms |
|---|---|
| p95 TTFT | ms |
| p50 TTFB | ms |
| Throughput | — |
| Uptime | 99.69% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 626 ms | 602 ms | — | 100.00% | — | 72 |
| cerebras/gpt-oss-120b | 735 ms | 649 ms | — | 100.00% | — | 80 |
| z-ai/glm-4.7 | 895 ms | 814 ms | — | 100.00% | — | 80 |
| cerebras/zai-glm-4.7 | 954 ms | 859 ms | — | 98.86% | — | 88 |