Cerebras · OpenAI-Compatible Engines

Gemma 4 31B

Language Vision Tool use

Preview model on Cerebras — per-token pricing not yet published.

A fast, low-cost model — ideal at volume where speed and price beat maximum quality.

High-volume tasks Classification & extraction Routing & drafts Document & image understanding Tool use & function calling

Free

No per-token charge at present. Providers can change pricing — this page tracks the published rate.

Model id: gemma-4-31b

Wafer-scale inference for open-weight models — the same OpenAI-compatible format as the rest of the gateway, at ~1,000–3,000 tokens/second.

One Gateway, Every Model