Use crane from 4D

Abstract

crane-oai is a Rust based alternative to llama.cpp, optimised for LLM, VLM, VLA, TTS, OCR inference. Embeddings or reranker models are not supported.

AI Kit compatibility

The API is compatible with Open AI.

Class	API	Availability
Models	/v1/models	✅
Chat	/v1/chat/completions	✅
Images	/v1/images/generations
Moderations	/v1/moderations
Embeddings	/v1/embeddings
Files	/v1/files