Wafer-scale chip inference — among the fastest tokens-per-second in the industry.
Cerebras runs inference on their custom Wafer-Scale Engine, delivering some of the highest tokens-per-second throughput available on Llama and GPT-OSS class models. US-hosted. The default pick when output throughput dominates the workload and US hosting is acceptable.
Every model we route through Cerebras. Compare residency, zero data retention, training posture and price at a glance, with full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| US | No | 128K | $2.25 | $2.75 | ||
| US | No | 131K | $0.35 | $0.75 |
Cerebras hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.
