# Wafer-Scale
1 tools tagged
showing 1 of 1 tools
Wafer-scale inference at thousands of tokens per second
Cerebras Inference serves open-weight LLMs such as GPT OSS 120B and Qwen 3.8 27B on Cerebras wafer-scale hardware through an OpenAI-compatible API. The self-serve Developer tier is pay-as-you-go with a one-time $5 promotional credit and is meant for development and evaluation, while Enterprise covers production workloads with all supported models, higher priority and rate limits, and fine-tuning services.
freemium