Price floor Every GPU at least 30% below the market median — re-checked against the marketplace weekly.

See the proof

Use case · LLM training

LLM training on cloud GPUs: the same silicon, no auction

Pre-training and continued pre-training live on HBM parts: H100 SXM at $1.587/GPU-hr fixed (market median $2.27), NVLink in-node, InfiniBand across nodes, and interruptible capacity at half price for every checkpointed epoch.

The training cards, ranked

Full comparison in the H100 vs H200 vs B200 guide.

TierGPUVRAMOn-demandInterruptibleWhy this cardAction
GoodA100 SXM480 GB$0.583$0.291Proven 80 GB HBM2e workhorse — unbeatable $/step for ≤13B experiments and LoRA-heavy labs.Deploy
BetterH100 SXM80 GB$1.587$0.793The default: FP8 transformer engine, 3.35 TB/s, deep supply in every major region.Deploy
BestB200192 GB$4.204$2.102192 GB HBM3e and Blackwell FP4/FP8 — shortest wall-clock when the deadline is the budget.Deploy

Cost of a real run, line by line

Continued pre-training, 8× H100 SXM, 72 hours, interruptible with volume checkpoints:

GPU time8 × 72 h × $0.793 =$456.77
Checkpoint volume 500 GB3 days × $40.00/mo =$4.00
Dataset ingress 400 GB400 × $0.01 =$4.00
Total $465

The market-median equivalent of the GPU line alone: about $653 at spot auctions you have to babysit — or $1,306 on-demand.

Patterns that make it cheap

  • Checkpoint to a volume every N steps — interruptions restart free, from disk.
  • Tune on 1×, train on 8× — debug the config at one-eighth the burn rate.
  • Pack with FP8/BF16 — the H100/H200 transformer engine is the discount nobody uses.
  • Destroy, keep the volume — datasets stay warm at $0.08/GB/mo, GPUs bill zero.

Templates: PyTorch, axolotl (FSDP-ready) — or your own image with a full VM for exotic stacks.

LLM training GPUs: FAQ

Sizing math: VRAM requirements guide.

Which GPU should I train an LLM on?

For serious runs: H100 SXM ($1.587/hr) is the price-performance default, H200 adds 141 GB for longer context and bigger micro-batches, B200 leads when wall-clock time is the constraint. For sub-13B experiments, 8× A100 nodes at $0.583/GPU-hr are hard to beat.

On-demand or interruptible for training?

Interruptible, almost always — training checkpoints anyway, and −50% compounds over hundreds of GPU-hours. A 72-hour run on 8× H100 costs about $457 interruptible vs $914 on-demand. Keep on-demand for the final, deadline-bound run.

How do multi-node runs connect?

Single machines scale to 8× with NVLink. Past that, clusters connect 8-GPU nodes over InfiniBand with NCCL pre-tuned — see the clusters page for pod pricing and all-reduce figures.

Deploy your first GPU in under a minute

Top up in crypto, benchmark us against your current provider. Per-second billing, fixed prices ≥ 30% below market — cancel by just stopping the instance.