311+ curated AI tools and growing

Cerebras Inference

Ultra-fast LLM inference API on Cerebras wafer-scale chips.

About this tool

Cerebras Inference Ultra-fast LLM inference API on Cerebras wafer-scale chips.

A go-to option in API & Models, Cerebras Inference suits individuals and teams via its website or API integrations.

Open model hub with Inference API and Spaces deployment.

CLI to run open LLMs locally for self-hosting and developer integration.

AWS Nova multimodal foundation models for chat and content.

Ray-based model deployment and LLM inference platform.