Offering overview
No GPUs are involved here: the Cerebras cloud runs on wafer-scale engines housed in CS-3 and the newer CS-4 rack systems, which the company positions as delivering far higher per-user token throughput than GPU clusters. Developers get an OpenAI-compatible endpoint, an API key in under a minute, and a free tier for evaluation; paid access starts with a pay-per-token deposit, and Cerebras Code subscriptions ($50 and $200 per month) bundle coding-model usage. Models on the shared service include OpenAI GPT-OSS 120B and Qwen 3.8 27B, with Qwen3 235B, Qwen3 Coder 480B, Kimi K2 and other open-weight checkpoints appearing across the dedicated tiers. Published per-token pricing for GPT-OSS 120B is $0.25 per million input tokens and $0.69 per million output tokens. The company also powers partner platforms such as Meta's Llama API, Hugging Face Inference Providers and OpenRouter. For enterprises, dedicated capacity can be run in-region for latency and data-residency reasons, or purchased as on-premises systems, and the same hardware supports fine-tuning and pre-training. Cerebras has announced data center expansion across North America and Europe and is headquartered in Sunnyvale, California.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- Model Inference, AI Applications, AI Agents, Model Training, Fine-Tuning
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- GPT-OSS 120B, Qwen 3.8 27B, Qwen3 235B, Qwen3 Coder 480B, Kimi K2
- AI frameworks
- Not stated
- Inference endpoints
- Unknown
- Fine-tuning
- Unknown
- Vector database
- Unknown
- Model catalog
- Unknown
- Monitoring
- Not stated
- Evaluation
- Not stated
Security & compliance
No controls are stated.
Geography
Provider headquarters are separate from offering infrastructure and availability.
Infrastructure regions
United States, North America
Data-residency jurisdictions
Not stated
Service availability
Not stated
Support coverage
Not stated
Available plans
Pricing can change. Promotional prices are shown separately from standard prices.
| Plan | Price | Compute | Storage | GPU | Price checked | Actions |
|---|---|---|---|---|---|---|
| Cerebras Inference CloudNot stated | $0.25Usage Only | Unknown — RAM | Unknown | No | 7 October 2026 |
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Unverified
- Primary source
- cerebras.ai
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 7 October 2026