Rent NVIDIA H200
Hopper datacenter GPU with 141 GB of HBM3e. Server sizes from 1 to 8 GPUs, billed by the hour. Pay in crypto, no KYC, root over SSH.
Live price by server size
Loading live data…| GPUs | Per GPU-hour | Server, per hour | Availability | Action |
|---|
Interruptible (spot)
| GPUs | Per GPU-hour | Server, per hour | Action |
|---|
Price history
Use the left and right arrow keys to read values at each point in time.
| Time (UTC) | Best 1-GPU hourly price | Free cards |
|---|
What you can run on the H200
The NVIDIA H200 is a Hopper-generation datacenter GPU with 141 GB of HBM3e memory per card and hardware FP8 support. The larger memory leaves room for bigger models, longer contexts and larger batches on each card. Rent it here by the hour, paid in crypto, with root access over SSH.
Typical tasks
- Serving large language models with room for long contexts and big batches
- Long-context inference, where the KV cache takes much of the memory
- Models that need more than 80 GB per card
- Full fine-tuning and training runs
- FP8 inference and training, where your framework supports it
What fits
A rough inference guide, in billions of parameters: weights only, about 20% left for context; real limits depend on context length and the serving engine. It assumes the weights take up to 80% of the total memory, at 2 bytes per parameter for BF16, 1 byte for FP8 and half a byte for 4-bit. With several cards, the serving engine splits the model across them.
| GPUs | BF16 | FP8 | 4-bit |
|---|---|---|---|
| 1 GPU | 56B | 112B | 225B |
| 2 GPUs | 112B | 225B | 451B |
| 4 GPUs | 225B | 451B | 902B |
| 8 GPUs | 451B | 902B | 1.8T |
Based on 141 GB per card.
How to rent the H200
- Sign inSign in with your e-mail. No KYC: you pay from your own wallet.
- QuoteWe confirm the machine and the price within 1 hour, 03:00–23:00 UTC.
- PayYou approve a quote before anything is charged. Pay in USDC on Ethereum today; more tokens are coming.
- KeysAfter payment we test the server and send you SSH access.
Billed by the hour, no minimum term. Reserved terms for a month, a quarter or a year are quoted by hand and cost less per hour.
Open the order formBuilding for clients? See the partner program. AI agent? llms.txt describes the public price file and the order link.
H200 FAQ
What size of model fits on one H200?
As a rough guide for inference, with the weights taking up to 80% of the 141 GB: about 56B parameters at BF16, 112B at FP8 and 225B at 4-bit on a single card. Real limits depend on the context length and the serving engine. The What fits table on this page also covers 2, 4 and 8 cards.
How much memory does the H200 have?
141 GB of HBM3e per card. The Specs section on this page shows the memory the cards on offer report right now.
How is the H200 different from the H100?
Both are Hopper GPUs with hardware FP8 support. The H200 has 141 GB of HBM3e memory per card; the H100 has 80 GB of HBM3 on SXM5 boards.
Can I rent more than one H200 in a server?
Yes. Servers come with 1, 2, 4 or 8 GPUs. The live table at the top of this page shows which sizes are offered right now; a size that is not offered can be asked for and is quoted by hand.
Do I need KYC?
No. You sign in with your e-mail and pay from your own wallet.