Run

Custom Checkpoints

on OctoAI at the industry's lowest cost-per-token

Get one simple per-token price for inferences against a model - whether it’s the built-in option or your choice of fine-tuned LLM. Make a choice based on your application needs, and don't let the 2x “fine-tuning tax” on other platforms skew your decision.

Custom LLMs on the OctoAI Text Gen Solution is available in private preview today. Fill out this form to connect with us and get the conversation started.