Aion Labs builds a layer on top of existing LLMs to improve performance and accuracy. They achieve this by leveraging the ability of LLMs to communicate with each other. Aion Labs is using a combination of DeepSeek R1 671B, as well as the distilled variant of DeepSeek, Llama models, and even their own fine-tuned models.
Read more about Aion Labs and how they use the SambaNova cloud here: