Cerebras
Explore Cerebras models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Cerebrascerebras
ZDR
| Provider | Cerebras |
|---|---|
| Routing status | Active |
| Provider website | https://www.cerebras.ai/ |
| Models | 4 public models |
| Credits routes | 4 |
| Zero data retention | yes All routes |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Tracked as provider-ZDR. Cerebras documents zero-retention inference and ZDR-compliant ephemeral prompt caching that is never persisted. Policy source |
Measured performance
110 samplesContinuously sampled across Cerebras's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2111 ms |
|---|---|
| Effective throughput | 232 tok/s n=1 |
| Uptime | 99.09% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| cerebras/gpt-oss-120b | 984 ms | 232 tok/s n=1 | 90.00% | — | 10 |
| qwen/qwen3.8-27b | 2111 ms | — | 100.00% | 16 probe_config_error |
75 |
| openai/gpt-oss-120b | 881 ms | — | 100.00% | — | 7 |
| cerebras/qwen-3.8-27b | 13131 ms | — | 100.00% | 9 probe_config_error |
18 |
Cerebras performance history · Full provider & model leaderboard.
Models served by Cerebras.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
cerebras/gpt-oss-120bOpenAI GPT OSS |
IQ 105#69 | 131,072 | $0.36925/1M | Not published | $0.79125/1M |
cerebras/qwen-3.8-27bQwen 3.8 27B |
— | 65,536 | $0.01/1M | Not published | $0.01/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#69 | 131,072 | $0.36925/1M | Not published | $0.79125/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 112#52 | 1,000,000 | $0.01/1M | Not published | $0.01/1M |
Questions
Does Cerebras have zero data retention?
TrustedRouter records Cerebras as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Cerebras end-to-end encrypted?
TrustedRouter does not currently mark Cerebras as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Cerebras models are available through TrustedRouter?
This page currently lists 4 public Cerebras models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.