Skip to main content
Fine-tuned (LoRA) models require a dedicated deployment to serve. Here’s what you need to know: What you pay for:
  • Deployment costs on a per-GPU-second basis for hosting the model
  • The fine-tuning process itself, if applicable
Deployment options:
  • Live-merge deployment: Deploy your LoRA model with weights merged into the base model for optimal performance
  • Multi-LoRA deployment: Deploy up to 100 LoRA models as addons on a single base model deployment
For more details on deploying fine-tuned models, see the Deploying Fine Tuned Models guide.