Question 1

How do I use the Cerebras API?

Accepted Answer

Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to gpt-oss-120b. On pay-as-you-go keys, cerebras/gpt-oss-120b pins every request to Cerebras; DevPass coding plans do not support provider pinning. You do not need a separate Cerebras account or SDK.

Question 2

Which Cerebras models are available?

Accepted Answer

LLM Gateway serves 1 Cerebras model: GPT OSS 120B. Each model page lists per-token pricing, context window and capabilities.

Question 3

Does Cerebras train on API data?

Accepted Answer

No. Cerebras's published policy states that API traffic is not used for model training.

Question 4

Where is Cerebras based?

Accepted Answer

Cerebras is headquartered in United States. LLM Gateway shows each provider's location and data policy so you can route by compliance requirements.

Question 5

What happens if the Cerebras API is down?

Accepted Answer

When you request a model without a provider prefix, LLM Gateway retries failed requests on other providers that serve the same model, so an outage at Cerebras does not have to take your app down. Send X-No-Fallback: true with a provider-pinned model when every request must reach Cerebras.

Cerebras API

Data & Privacy

Available Models

GPT OSS 120B

Cerebras API questions

Stay ahead of the curve