OpenAI compatible API · Attested · Public status
Cerebras performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Cerebras.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
cerebras
71 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 | 1292 ms |
|---|---|
| p95 TTFT | 4740 ms |
| p50 TTFB | 1478 ms |
| Effective throughput | 126 tok/s n=5 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-4.7 | 1016 ms | 1016 ms | — | 100.00% | — | 12 |
| cerebras/gpt-oss-120b | 1292 ms | 1111 ms | 377 tok/s n=1 | 100.00% | — | 29 |
| openai/gpt-oss-120b | 1424 ms | 1424 ms | 163 tok/s n=1 | 100.00% | — | 6 |
| cerebras/gemma-4-31b | 1478 ms | 1478 ms | — | 100.00% | — | 6 |
| cerebras/zai-glm-4.7 | 1491 ms | 1491 ms | 69 tok/s n=1 | 100.00% | — | 8 |
| google/gemma-4-31b-it | 3246 ms | 3246 ms | 126 tok/s n=2 | 100.00% | — | 10 |