Skip to content

NVIDIA H200 Price in 2026: Specs, Hourly Rates and Buy vs Rent

NVIDIA H200 price in 2026: about $30,000-$34,000 to buy, $6.00 per GPU-hour on fal, billed per second. Specs, H100 and B200 comparison, buy vs rent.

Jim Cai6 min read
NVIDIA H200 Price in 2026: Specs, Hourly Rates and Buy vs Rent

An NVIDIA H200 costs about $30,000 to $34,000 per GPU at US online prices (March 2026), and large buyers negotiate lower. Renting one on fal costs $6.00 per GPU-hour at list price, billed per second, and as low as $2.99. Because a 70B model at FP8 fits on one H200 instead of two H100s, the H200 is often the cheaper GPU per model replica. Buying only wins if you can keep H200s busy around the clock for years and already run the servers, power and cooling.

The H200 is the GPU that made memory, not compute, the headline spec. It runs the same Hopper compute as the H100 but carries 76% more memory, which changes how many GPUs a large model needs. For inference, that makes the price of one model replica a better guide than the price of one GPU.

What the NVIDIA H200 is

The H200 is NVIDIA's Hopper-generation data-center GPU. It keeps the H100's compute and power profile, up to 700 W per GPU, but has 141 GB of HBM3e instead of 80 GB, and 4.8 TB/s of memory bandwidth, about 1.4 times the H100.12 The H200 SXM goes into 4- and 8-GPU HGX servers. The H200 NVL is a PCIe card for air-cooled servers, at up to 600 W.1

SpecH200 (SXM)H100 (SXM)B200
ArchitectureHopperHopperBlackwell
GPU memory141 GB HBM3e80 GB HBM3192 GB HBM3e
Memory bandwidth4.8 TB/s3.35 TB/s8 TB/s
FP8 dense (TFLOPS)~1,979~1,979~4,500
FP16/BF16 dense (TFLOPS)~989~989~2,250
NVLink per GPUNVLink 4 (900 GB/s)NVLink 4 (900 GB/s)NVLink 5 (1.8 TB/s)
Max powerUp to 700 W per GPUUp to 700 W per GPU~14.3 kW per 8-GPU DGX B200

Hopper dense figures halve NVIDIA's with-sparsity numbers. B200 throughput is NVIDIA's 8-GPU figure divided by eight; B200 memory is fal's GPU-B200 machine type.12345

With the same compute, the H200 beats the H100 only on memory-bound work, which covers most inference. NVIDIA reports up to 1.9 times faster Llama 2 70B inference.1

When an H200 is the right GPU

  • 70B-class models on one GPU. At FP8, a 70B model's weights take about 70 GB. That leaves an 80 GB H100 little room for KV cache, so long contexts push the model onto two GPUs. On an H200 it fits on one.
  • Long-context and high-batch LLM serving. The extra 61 GB holds more KV cache, and the bandwidth reads it faster. This is where the H200 earns its premium over the H100.
  • Not for most image or video work. Image models rarely need 141 GB and run well on cheaper GPUs such as the L40 or RTX PRO 6000. Video pipelines benefit from hardware video encoders, which the H200 lacks.4

What an H200 costs to buy

Reseller and negotiated prices move with supply.

SourcePrice per H200Date
US online market prices~$30,000 to $34,000March 2026
Reported price offered to buyers in China~$27,000December 2025 to March 2026
Lowest prices reported by industry sources~$17,000 to $19,000March 2026

All three come from one policy analysis, which notes that large buyers negotiate discounts.6 A December 2025 news report gave the same ~$27,000 China price.7 The GPU is only part of the cost. You also pay for the 4- or 8-GPU server, networking, power, cooling and operations staff.

Rental prices have not fallen. Across 28 cloud providers, the median on-demand H200 rate rose from about $3.20 per GPU-hour at the end of 2024 to about $4.00 at the end of 2025.6

What an H200 costs to rent

On fal, an H200 lists at $6.00 per GPU-hour, from fal.ai/pricing:8

GPUVRAMList priceAs low as
H200141 GB$6.00/h$2.99/h

$6.00 is the per-GPU list rate, billed per second while a runner is alive, idle keep-alive included.9 To compare per-second platforms, see how to choose a serverless GPU platform.

At list price, an H200 second costs about $0.00167.

WorkloadRateBilled GPU timeCost
10-minute test run on 1 GPUList600 GPU-seconds$1.00
1 hour on an 8-GPU runnerList8 GPU-hours$48.00
Bursty traffic: 3 runner-hours a day for 30 daysList90 GPU-hours$540.00
1 GPU kept warm for a 30-day monthList720 GPU-hours$4,320.00
1 GPU held for a 30-day monthAs low as, $2.99/h720 GPU-hours$2,152.80

The "as low as" rate is about half the list rate, so holding a GPU all month at that rate beats per-second billing at list only when the GPU is busy more than about half the time. The break-even guide works through that line.

What a 70B model replica costs on H100, H200 and B200

Memory sets how many GPUs one copy of a model needs. For a 70B model at FP8 with long contexts:48

GPUMemory per GPUGPUs per replicaList price per replica-hourAs low as per replica-hour
H10080 GB2$9.00$4.98
H200141 GB1$6.00$2.99
B200192 GB1$7.99$5.49

H200 vs H100. An H200 replica costs a third less than two H100s at list price, and 40% less at "as low as" rates. For a small model that fits on one H100, the H200 lists at 1.33 times the price for 1.43 times the bandwidth, so it wins only if the model is bandwidth-bound. For the H100 side, see the NVIDIA H100 price guide.

H200 vs B200. A B200 replica costs 1.33 times an H200 replica at list price and 1.84 times at "as low as" rates, for 1.67 times the bandwidth. The B200 wins on cost per token only if its extra bandwidth turns into at least that much more throughput. If your model fits in 141 GB, benchmark both. The NVIDIA B200 price guide covers that GPU.

Buy or rent an H200?

The purchase price divided by the hourly rate gives the rental hours the same money buys:

Purchase price per GPURent at $6.00/h (list)Rent at $2.99/h (as low as)
$27,0004,500 h (~188 days of 24/7 use)9,030 h (~376 days)
$30,0005,000 h (~208 days)10,033 h (~418 days)
$34,0005,667 h (~236 days)11,371 h (~474 days)

The purchase price covers the GPU alone, so this flatters buying.68 Buy only if you can keep H200s busy for years and already run data-center hardware.

Running a model on H200s with fal

On fal Serverless the H200 is the GPU-H200 machine type, with 141 GB of VRAM, 112 GB of system RAM and 12 CPU cores.4 Set machine_type = "GPU-H200" in your app, or list ["GPU-H200", "GPU-B200"] so fal falls back to the next type when H200s have no capacity.4 fal approves Serverless access per account. Request it on the Serverless get-started page, then follow the Quick Start.10 Keep-alive settings drive most of an H200 bill; see What Is a Serverless GPU Cold Start?

FAQ

How much does an NVIDIA H200 cost?

About $30,000 to $34,000 per GPU at US online prices in March 2026, and negotiated deals go lower.6 On fal Serverless it rents for $6.00 per GPU-hour at list price, or as low as $2.99 per GPU-hour.

What is the H200 price per hour?

On fal, $6.00 per GPU-hour at list price, billed per second, which is about $0.00167 per second. It goes as low as $2.99 per GPU-hour.

What is the H200 vs B200 price?

On fal the B200 lists at $7.99/h and the H200 at $6.00/h. At "as low as" rates, the gap widens to $5.49/h against $2.99/h. Choose a B200 when the model needs more than 141 GB, is strongly bandwidth-bound, or can run in FP4.

References

References

  1. NVIDIA H200 GPU, NVIDIA. ↩ ↩2 ↩3 ↩4

  2. NVIDIA H100 GPU, NVIDIA. ↩ ↩2

  3. NVIDIA DGX B200, NVIDIA. ↩

  4. fal Docs: Machine Types. ↩ ↩2 ↩3 ↩4 ↩5

  5. NVIDIA HGX Platform, NVIDIA. ↩

  6. Georgia Adamson and Tim Fist, When Do More AI Chips for China Mean Fewer for the United States?, Institute for Progress, March 27, 2026. ↩ ↩2 ↩3 ↩4

  7. Reuters, Nvidia sounds out TSMC on new H200 chip order as China demand jumps, sources say, via The Standard (Hong Kong), December 31, 2025. ↩

  8. fal Pricing. ↩ ↩2 ↩3

  9. fal Docs: Serverless Pricing. ↩

  10. fal Docs: Quick Start. ↩

Run your own models on fal Serverless

Run any AI workload on managed, autoscaling GPUs.