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
209 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 | 2336 ms |
|---|---|
| p95 TTFT | 4488 ms |
| p50 TTFB | 2345 ms |
| Effective throughput | — |
| Uptime | 97.13% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 2332 ms | 2332 ms | — | 100.00% | — | 32 |
| cerebras/zai-glm-4.7 | 2353 ms | 2353 ms | — | 97.73% | — | 44 |
| z-ai/glm-4.7 | 2336 ms | 2335 ms | — | 97.37% | — | 38 |
| cerebras/gemma-4-31b | 2383 ms | 2383 ms | — | 96.97% | — | 33 |
| google/gemma-4-31b-it | 2322 ms | 2322 ms | — | 95.24% | — | 21 |
| cerebras/gpt-oss-120b | 2316 ms | 2316 ms | — | 95.12% | — | 41 |