Cerebras Inference

Model API

Hosted inference service that serves open-weight models on Cerebras wafer-scale hardware, billed per token.

Find alternatives to Cerebras Inference

TypeModel API
RoleHosted model API
AvailabilitySold
DeploymentSaaS
Intended forDeveloper, Enterprise
SecurityVendor-asserted
CertificationsSOC 2 Type II, GDPR DPA
Trains on customer dataNot recorded
Zero data retentionNot recorded
Data residencyNot recorded
Security featuresEncryption at rest, Audit logs
StatusActive
Sold withinSold on its own
PricingUsage-based, Enterprise quote

What it does

Features 12

cerebras.ai

How it compares

Sources

Pricing

Pricing page · 2 Oct 2026

Cerebras doesn't currently offer a no-cost tier that renews automatically

Constraints

Trust centre · 2 Oct 2026

Derived from the security facts on this page, from the same source.

Security

Trust centre · 2 Oct 2026

Company-wide Cerebras trust center (SafeBase, script-rendered; read in the in-app browser). Only the hosted services (Inference, Training Cloud) are listed, not the WSE hardware.

Sold within

Official documentation · 30 Sep 2026

"New accounts receive $5 in free credits", which "expire 30 days after they’re granted". "A Pay as You Go purchase reactivates access immediately and moves you to the Developer tier, which raises rate limits and removes hourly and daily token caps."

Deployment

Self-reported · 8 Sep 2026

Inferred 2026-09-08, not read off a page: every already-decided product of type 'model-api' in this catalogue includes "saas" in its deployment list, zero exceptions, per item 198's measured cross-tab. May be incomplete if this product also offers a self-hosted or private-cloud option; not wrong either way.

Interfaces

Official documentation · 12 Oct 2026

Page: 'Find everything you need to get started with our products, including technical guides, examples, and API references. / Build LLM applications with the world's fastest inference solution using the Cerebras Inference SDK'.

Modalities

Official documentation · 1 Oct 2026

Page: 'Vision-capable models can process objects, diagrams, screenshots, and text within images alongside a text prompt. / The model returns text only and does not generate images'.

Intended for

Self-reported · 8 Sep 2026

"OpenAI API compatibility lets developers build on Cerebras with just two code changes," plus a self-serve Developer tier and an Enterprise tier for "production-scale inference for high-volume applications."

Also from Cerebras Systems

Open Cerebras Systems in the directory

Something wrong here? Send a correction — quote this product id: cerebras-inference.