Home/Pricing/A100 Node

A100 Node

Production-grade A100 capacity for fine-tuning and batch inference.

Compute Plans billed per month

A dedicated NVIDIA A100 80 GB node with NVLink and a high-bandwidth fabric — the sweet spot for fine-tuning 13B–70B models and running high-throughput batch inference. Shipped with a pre-configured PyTorch image, or bring your own.

What is included

  • Dedicated NVIDIA A100 80 GB (SXM)
  • 32 vCPU · 256 GB RAM · 2 TB NVMe
  • NVLink & high-bandwidth interconnect
  • 99.9% uptime SLA
  • Pre-configured PyTorch or bring your own image

Specification

GPU
NVIDIA A100 SXM
VRAM
80 GB HBM2e
CPU
32 vCPU
Memory
256 GB
Storage
2 TB NVMe

Other Compute Plans

RTX 4090 Instance $349.00

A dedicated RTX 4090 for inference, LoRA fine-tuning, and development work.
H100 Node $1,499.00

Flagship Hopper performance for frontier training and low-latency serving.
H100 8-GPU Cluster $9,999.00

An 8×H100 NVLink cluster for distributed training at scale.

Start routing in minutes

One endpoint. Every frontier model.

Create an account, pick a plan, and point your existing OpenAI client at our base URL. No SDK rewrite, no lock-in.

Browse plans Talk to sales