Free to start

Cerebras

Try Cerebras on us. Starter credit covers your first requests, then one key reaches all 3 Cerebras models, with the privacy posture shown on every route.

Cerebrascerebras

ZDR

All providers

These privacy labels describe Cerebras, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	Cerebras
API operator country	US Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://www.cerebras.ai/
Models	3 public models
Credits routes	3
Zero data retention	yes All routes
Verified confidential inference	Not verified
Policy note	Tracked as provider-ZDR. Cerebras documents zero-retention inference and ZDR-compliant ephemeral prompt caching that is never persisted. Policy source

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

29 samples

Continuously 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	1077 ms
Effective throughput	284 tok/s n=2
Uptime	96.55%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
openai/gpt-oss-120b	1188 ms	284 tok/s n=2	100.00%	—	12
cerebras/qwen-3.8-27b	509 ms	—	100.00%	—	3
cerebras/gpt-oss-120b	1033 ms	—	83.33%	2 `provider_error`	6
qwen/qwen3.8-27b	1077 ms	—	100.00%	—	8

Cerebras performance history · Full provider & model leaderboard.

Provider models

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-120b` OpenAI GPT OSS	IQ 98#132	131,072	$0.36925/1M	Not published	$0.79125/1M
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b	IQ 98#132	131,072	$0.36925/1M	Not published	$0.79125/1M
`qwen/qwen3.8-27b` Qwen: Qwen3.8 27B	IQ 116#52	65,536	$1.04445/1M	Not published	$1.57195/1M

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 3 public Cerebras models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.