GPU model · price + stock · hourly snapshot

Nvidia H200 cloud rental prices

Name: Nvidia H200 cloud GPU rental
Brand: Nvidia
Availability: InStock

9 providers list the Nvidia H200, 3 have it in stock. Prices run from $3.59 to $6.38 per GPU hour — the same card, 1.8x apart.

Hopper 141 GB VRAM Q4 2023 31 configurations

LIVE Prices and stock checked 1 minute ago November 4, 2026 UTC

Cheapest in stock

$3.59

Runpod

Median

$4.00

across 9 providers

Most expensive

$6.38

same card, 1.8x the price

You overpay by

10%

if you take the median instead of the floor

Providers

Every provider renting the Nvidia H200

All providers →

Billing:

On-demandfrom $3.59/hr3 providers in stockPay as you go, stop any time.Spotfrom $2.63/hr1 provider in stockCheaper, but the provider can take the machine back.Reservednone listedPrepay a term for the lowest hourly rate.

Providers renting the Nvidia H200, in stock first, then cheapest first
Provider	Country	Configs	Scale	From	Stock	Days in stock	Grab
Runpod	United States of America	1	1x-1x	$3.59 per sec	In stock	60/60	Grab
Vast.ai	United States of America	2	1x-8x	$3.66 per sec	In stock	42/42	Grab
Lium	—	1	1x-1x	$4.00	In stock	28/28	Grab
Nebius	Netherlands	1	1x-1x	$5.40	Not reported	0/60	Grab
Verda	Finland	8	1x-8x	$6.38	Not reported	3/60	Grab
Horizon Compute	—	1	8x-8x	$3.00	Out of stock	0/60	Grab
Excess Supply	—	11	1x-8x	$4.00	Out of stock	41/60	Grab
BoostRun	—	2	8x-8x	$4.25	Out of stock	0/60	Grab
DigitalOcean	United States of America	4	1x-8x	$4.47	Out of stock	0/60	Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $3.59: $2,621. Lium publishes live counts: 170 GPUs at $4.00, 85% rented.

Price history

Price trend

Cheapest Nvidia H200 rate has risen 42.4% since Sep 6 — $2.11 → $3.00/GPU/hr.

$3.00 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 450 offers in the latest snapshot.

Configurations

All 31 configurations

In stock only31 of 31 configurations

Nvidia H200 configurations from every provider
Configuration	Provider	Region	VRAM	vCPU	RAM	Per GPU/hr	Total/hr	Stock
1x H200SpotVast.ai	Vast.ai	US	140 GB	24	341 GB	$2.63per sec	$2.63	In stock
1x H200 SXMRunpod	Runpod	—	141 GB	—	—	$3.59per sec	$3.59	In stock
8x H200Vast.ai	Vast.ai	JP	1123 GB	224	2015 GB	$3.66per sec	$29.25	In stock
1x NVIDIA H200Lium	Lium	—	—	—	—	$4.00	$4.00	In stock
8x H200Horizon Compute	Horizon Compute	blonduos-iceland-3	1128 GB	160	1536 GB	$3.00	$24.00	Out of stock
4x H200 SXM5 141GBSpotVerda	Verda	—	564 GB	—	—	$3.19	$12.75	Not reported
8x H200 SXM5 141GBSpotVerda	Verda	—	1128 GB	—	—	$3.19	$25.50	Not reported
1x H200 SXM5 141GBSpotVerda	Verda	—	141 GB	—	—	$3.19	$3.19	Not reported
2x H200 SXM5 141GBSpotVerda	Verda	—	282 GB	—	—	$3.19	$6.38	Not reported
8x H200Excess Supply	Excess Supply	tokyo-japan-5	1128 GB	208	1904 GB	$4.00	$32.00	Out of stock
8x H200SpotExcess Supply	Excess Supply	tokyo-japan-5	1128 GB	208	1904 GB	$4.00	$32.00	Out of stock
8x H200Excess Supply	Excess Supply	fukushima-japan-1	1128 GB	148	1904 GB	$4.00	$32.00	Out of stock
8x H200BoostRun	BoostRun	raleigh-usa-1	1128 GB	96	2048 GB	$4.25	$34.00	Out of stock
8x H200BoostRun	BoostRun	dallas-usa-4	1128 GB	96	2048 GB	$4.25	$34.00	Out of stock
8x H200Excess Supply	Excess Supply	raleigh-usa-2	1128 GB	96	2048 GB	$4.25	$34.00	Out of stock
8x H200Excess Supply	Excess Supply	dallas-usa-6	1128 GB	96	2048 GB	$4.25	$34.00	Out of stock
1x H200DigitalOcean	DigitalOcean	atlanta-usa-1	141 GB	24	240 GB	$4.47	$4.47	Out of stock
1x H200DigitalOcean	DigitalOcean	newyork-usa-2	141 GB	24	240 GB	$4.47	$4.47	Out of stock
8x H200DigitalOcean	DigitalOcean	newyork-usa-2	1128 GB	192	1920 GB	$4.47	$35.76	Out of stock
8x H200DigitalOcean	DigitalOcean	atlanta-usa-1	1128 GB	192	1920 GB	$4.47	$35.76	Out of stock
8x H200Excess Supply	Excess Supply	kansascity-usa-4	1128 GB	128	1600 GB	$4.52	$36.13	Out of stock
8x H200Excess Supply	Excess Supply	helsinki-finland-4	1128 GB	128	1600 GB	$4.52	$36.13	Out of stock
8x H200Excess Supply	Excess Supply	paris-france-3	1128 GB	128	1600 GB	$4.52	$36.13	Out of stock
1x H200Excess Supply	Excess Supply	paris-france-3	141 GB	16	200 GB	$4.63	$4.63	Out of stock
1x H200Excess Supply	Excess Supply	helsinki-finland-4	141 GB	16	200 GB	$4.63	$4.63	Out of stock
1x H200Excess Supply	Excess Supply	kansascity-usa-4	141 GB	16	200 GB	$4.63	$4.63	Out of stock
1x NVIDIA HGX H200Nebius	Nebius	—	—	—	—	$5.40	$5.40	Not reported
2x H200 SXM5 141GBVerda	Verda	—	282 GB	—	—	$6.38	$12.75	Not reported
4x H200 SXM5 141GBVerda	Verda	—	564 GB	—	—	$6.38	$25.50	Not reported
1x H200 SXM5 141GBVerda	Verda	—	141 GB	—	—	$6.38	$6.38	Not reported
8x H200 SXM5 141GBVerda	Verda	—	1128 GB	—	—	$6.38	$51.01	Not reported

Model fit

What fits in 141 GB

The question behind most rentals: will the model load. Sized against one Nvidia H200.

VRAM required to serve open-weight LLMs on a Nvidia H200, by quantization precision
Model	16-bit	8-bit	4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active	1,610 GB 12× · 82 GB free	805 GB 6× · 41 GB free	403 GB 3× · 20 GB free
Llama 3.1 405B Meta · 405B params	972 GB 7× · 15 GB free	486 GB 4× · 78 GB free	243 GB 2× · 39 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active	564 GB 4× · 0 GB free	282 GB 2× · 0 GB free	141 GB 1× · 0 GB free
Mixtral 8x22B Mistral · 141B params · 39B active	338 GB 3× · 85 GB free	169 GB 2× · 113 GB free	85 GB 1× · 56 GB free
Mistral Large 2 Mistral · 123B params	295 GB 3× · 128 GB free	148 GB 2× · 134 GB free	74 GB 1× · 67 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active	281 GB 2× · 1 GB free	140 GB 1× · 1 GB free	70 GB 1× · 71 GB free
Qwen2.5 72B Alibaba · 72.7B params	174 GB 2× · 108 GB free	87 GB 1× · 54 GB free	44 GB 1× · 97 GB free
Llama 3.3 70B Meta · 70.6B params	169 GB 2× · 113 GB free	85 GB 1× · 56 GB free	42 GB 1× · 99 GB free
Qwen3 32B Alibaba · 32.8B params	79 GB 1× · 62 GB free	39 GB 1× · 102 GB free	20 GB 1× · 121 GB free
Gemma 2 27B Google · 27.2B params	65 GB 1× · 76 GB free	33 GB 1× · 108 GB free	16 GB 1× · 125 GB free
Mistral Small 3 Mistral · 24B params	58 GB 1× · 83 GB free	29 GB 1× · 112 GB free	14 GB 1× · 127 GB free
Llama 3.1 8B Meta · 8B params	19 GB 1× · 122 GB free	10 GB 1× · 131 GB free	5 GB 1× · 136 GB free

Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia H200.

Specifications

Nvidia H200 specifications

Nvidia H200 hardware specifications
Architecture	Hopper
Memory per GPU	141 GB HBM3e
Memory bandwidth	4,800 GB/s
Release date	Q4 2023
GPU interconnect	NVLink 900 GB/s
FP8 compute rate	1,979 TFLOPS (dense), 3,958 with sparsity
FP16 / BF16 compute rate	989.5 TFLOPS (dense), 1,979 with sparsity
INT8 compute rate	1,979 TOPS (dense), 3,958 with sparsity
Process node	TSMC 4N
Board power	700 W
Partitioning	MIG, up to 7 instances

Alternatives

Every provider renting the Nvidia H200

Price trend

All 31 configurations

What fits in 141 GB

Nvidia H200 specifications

Alternatives to the Nvidia H200