Welcome to the OctoAI compute service! 🐙

OctoML is on a mission to offer easy access to efficient compute and enable users to integrate their choice of AI models into applications. The OctoAI compute service helps you run, tune, and scale AI applications easily:

Run: We give you pre-optimized endpoints for popular open source models that you can immediately use to prototype your app for free, as well as a CLI to easily build endpoints from your custom models.
Tune: We enable you to fine-tune popular open-source models to build your private data moat (early access -- contact us on Discord for this).
Scale: We automatically scale you endpoints anywhere between 0 hardware replicas to as many as you need. We support customers in scaling to 100,000 monthly active users this year and millions of fine-tuned combinations of Stable Diffusion simultaneously.

New users get $11 worth of free compute credits for signing up; the credits expire within about one month. $11 is equivalent to 2+ hours of compute on our large tier hardware, 9+ hours of compute on our medium tier hardware, or 27+ hours of compute on our small tier hardware. The credits expire in about one month.

Join our Discord community to learn about the applications other customers are building, get help, or just tell us what you are excited about!

In order to get started you can:

Try our quickstart template endpoints

Install our CLI/SDK and start building endpoints for your custom models