Container Compute pricing
Real prices from our pricing API
CPU
$0.012 / hour
Memory
$0.004 / GB / hour
GPU
$0.45 / hour
Small container (1 CPU, 2GB RAM)
Running continuously for 30 days
Estimated monthly
$11.52 / mo
More services coming soon
Pricing for upcoming services will be published when each launches.
GPU Compute
Train models, run inference, render frames on consumer GPUs. RTX 3090, 4090, A6000 available on demand.
Batch Jobs
Run containers to completion with automatic retries. Ideal for video encoding, scientific computing, dataset preprocessing.
Object Storage
Standard S3 API backed by erasure-coded storage across peer nodes. Compatible with aws-cli, mc, and any S3 SDK.
Block Volumes
Attach block storage to any compute pod. Replicated across peers. For databases, build caches, and stateful workloads.
Public Endpoints
TLS termination, certificate provisioning, HTTP routing, and custom domains. Production URLs in seconds.
Private Networking
Private networks for your projects with automatic service discovery and end-to-end mTLS encryption.
AI Inference Endpoints
Wrap any model in a container and get a stable HTTPS URL with request-level metering and automatic scaling.
Fine-tuning Jobs
Fine-tune open-weight models with your dataset. Supports LoRA, full fine-tuning, and instruction tuning.
Inference Gateway
Request routing, per-key rate limiting, usage logs, and a uniform API across different model runtimes.
Frequently asked questions
Pricing for upcoming services will be published when each launches. Pricing across all services will follow the same per-second-per-resource model.