Cerebras

Cloud PlatformOpenAI compatible

Ultra-fast inference powered by wafer-scale compute chips, offering the fastest LLM speeds.

Active models
4+ 12 deprecated
Families
6
Headquarters🇺🇸 Sunnyvale, CA
Founded2016
API Base URL
Modelsinference-docs.cerebras.ai/introduction
Model
Gemma 4 31B🌍gemma-4-31b
Qwen 3 235B Instruct🌍OSSqwen-3-235b-a22b-instruct
Z.ai GLM 4.7🌍zai-glm-4.7
OpenAI GPT OSS🌍OSSgpt-oss-120b