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 | 2364 ms |
|---|---|
| p95 TTFT | 7425 ms |
| p50 TTFB | 2315 ms |
| Effective throughput | 360 tok/s n=7 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-4.7 | 1276 ms | 1276 ms | — | 100.00% | — | 10 |
| openai/gpt-oss-120b | 1424 ms | 1424 ms | 360 tok/s n=2 | 100.00% | — | 7 |
| cerebras/zai-glm-4.7 | 1734 ms | 1734 ms | 69 tok/s n=2 | 100.00% | — | 8 |
| cerebras/gemma-4-31b | 2315 ms | 2315 ms | — | 100.00% | — | 7 |
| cerebras/gpt-oss-120b | 2364 ms | 2735 ms | 462 tok/s n=2 | 100.00% | — | 29 |
| google/gemma-4-31b-it | 2700 ms | 2699 ms | 79 tok/s n=1 | 100.00% | — | 10 |