Always-on LLM inferencing engines available in alpha

2025-03-07

For most of our customers, the cost-benefit of running LLMs in production has been too unpredictable. Industry standard per-request or per-token pricing leaves them with too many unknowns–even before bandwidth charges are imposed.

Last month’s DeepSeek releases paved the way for an open ecosystem of efficient engines for mainstay production inference–the kind of models that businesses operating in competitive industries can deploy with a positive return on investment.

Our first LLM product is available in alpha. It’s free to use while supplies last. API, Terraform, web portal, and CLI integrations are ready.

Here’s a quick starter video:

Docs are available. Your feedback is welcome.

Go back to the list of blog entries. RSS feed.