Predibase Plans Pricing
Predibase uses usage-based pricing across three meters: serverless inference billed per token, fine-tuning (training) billed per token of training data scaled by base-model size, and dedicated deployments billed per GPU-hour by accelerator type. A free tier provides serverless inference up to a daily and monthly token cap; the Developer tier adds self-serve dedicated A10/A100 deployments; the Enterprise tier adds VPC / multi-GPU (A100/H100) deployments and negotiated terms.
Predibase Plans Pricing is the machine-readable pricing-plan profile for Predibase on the APIs.io network, conforming to the API Commons Plans specification.
It defines 4 plans, covering free, usage, and enterprise tiers, with named plans including Free, Pay-as-you-go, Developer (Dedicated Deployments), Enterprise.
Tagged areas include AI, LLM, Fine-Tuning, Inference, and LoRA.
Plans
Serverless inference on shared endpoints up to a daily and monthly token cap, with no cost to start.
- Shared Endpoints
- OpenAI-Compatible Inference
Token-metered serverless inference, token-metered fine-tuning, and GPU-hour-metered dedicated deployments with no monthly minimum beyond usage.
- Serverless Inference
- Batch Inference
- Supervised Fine-Tuning
- Reinforcement Fine-Tuning (GRPO)
Self-serve dedicated deployments billed per GPU-hour on A10 and A100 accelerators for production traffic.
- Dedicated Deployments
- LoRA / Turbo LoRA Serving
VPC / private cloud deployments, multi-GPU and H100 deployments, dedicated support, and negotiated terms. Contact Predibase sales.
- VPC / Private Deployments
- H100 and Multi-GPU
- Custom Volume Pricing