Geodd

Bare metal NVIDIA GPU instances and managed AI inference

Geodd is an AI infrastructure company founded in 2023. It provides serverless inference, single-tenant model deployments, and bare metal NVIDIA GPU infrastructure for teams running AI inference in production.

Geodd owns and operates a 500+ GPU fleet across US, EU, and APAC regions, colocated in Tier III datacenter facilities. EU serverless inference runs from Stavanger, Norway, and APAC capacity from Colombo, Sri Lanka.

Geodd Homepage

What's good about Geodd

Bare metal GPU access with no virtualization layer
EU serverless inference served from Norway
OpenAI-compatible API across 20+ open-weight models
Direct Slack or WhatsApp access to platform engineers

Geodd pricing examples

Here are some of the GPU configurations offered by Geodd:

6 GPU models

How this list works

Order

By GPU model: one card per GPU, the most looked-up models first, then the most widely offered ones.
By configuration: every configuration we track. What you can rent now comes first, and within that one row per GPU model before any repeats, so the opening rows cover the range rather than one model's sizes.

The price on a card

Each card leads with a per GPU per hour rate. We prefer configurations the provider reports as in stock, on-demand rates before reserved or spot, then take the lowest per-GPU rate among those.

Search

We match the GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Nvidia H100

Out of stock

5 configs 1x-8x checked <5m ago

On-Demand from $3.00

From $3.00 / GPU / hr On-Demand SXM Visit website


1x H100 SXM gpu_1x_h100	80GB	20	128GB	On-Demand	$3.00	$3.00	Out of stock
2x H100 SXM gpu_2x_h100	160GB	40	256GB	On-Demand	$3.00	$6.00	Out of stock
4x H100 SXM gpu_4x_h100	320GB	64	512GB	On-Demand	$3.00	$12.00	Out of stock
8x H100 SXM gpu_8x_h100	640GB	126	768GB	On-Demand	$3.00	$24.00	Out of stock
8x H100 SXM gpu_8x_H100_SXM5	640GB	126	1.8TB	On-Demand	$3.12	$25.00	Out of stock

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Nvidia H200

5 configs 1x-8x checked <5m ago

On-Demand from $3.39

From $3.39 / GPU / hr On-Demand NVL Visit website


1x H200 NVL gpu_1x_h200_nvl	141GB	16	180GB	On-Demand	$3.39	$3.39	Not reported
2x H200 NVL gpu_2x_h200_nvl	282GB	30	360GB	On-Demand	$3.39	$6.78	Not reported
4x H200 NVL gpu_4x_h200_nvl	564GB	62	720GB	On-Demand	$3.39	$13.56	Not reported
8x H200 SXM gpu_8x_h200_SXM5	1.1TB	190	1.8TB	On-Demand	$2.72	$21.76	Out of stock
8x H200 NVL gpu_8x_h200_nvl	1.1TB	120	1.7TB	On-Demand	$3.39	$27.12	Not reported

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Nvidia RTX PRO 6000

In stock

4 configs 1x-8x checked <5m ago

On-Demand from $2.14

From $2.14 / GPU / hr On-Demand PCIe Visit website


1x RTX PRO 6000 PCIe gpu_1x_pro_6000_blackwell	96GB	16	144GB	On-Demand	$2.14	$2.14	In stock
2x RTX PRO 6000 PCIe gpu_2x_pro_6000_blackwell	192GB	30	288GB	On-Demand	$2.14	$4.28	Out of stock
4x RTX PRO 6000 PCIe gpu_4x_pro_6000_blackwell	384GB	60	576GB	On-Demand	$2.14	$8.56	Out of stock
8x RTX PRO 6000 PCIe gpu_8x_pro_6000_blackwell	768GB	120	1.5TB	On-Demand	$2.14	$17.12	Out of stock

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Nvidia A100

In stock

4 configs 1x-8x checked <5m ago

On-Demand from $1.49

From $1.49 / GPU / hr On-Demand SXM Visit website


1x A100 SXM gpu_1x_a100	80GB	16	120GB	On-Demand	$1.49	$1.49	In stock
2x A100 SXM gpu_2x_a100	160GB	30	150GB	On-Demand	$1.49	$2.98	Not reported
4x A100 SXM gpu_4x_a100	320GB	60	300GB	On-Demand	$1.49	$5.96	Not reported
8x A100 SXM gpu_8x_a100	640GB	120	1.8TB	On-Demand	$1.49	$11.92	In stock

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Nvidia L40S

4 configs 1x-8x checked <5m ago

On-Demand from $1.00

From $1.00 / GPU / hr On-Demand PCIe Visit website


1x L40S PCIe gpu_1x_l40s	48GB	12	72GB	On-Demand	$1.00	$1.00	Not reported
2x L40S PCIe gpu_2x_l40s	96GB	24	144GB	On-Demand	$1.00	$2.00	Not reported
4x L40S PCIe gpu_4x_l40s	192GB	46	288GB	On-Demand	$1.00	$4.00	Not reported
8x L40S PCIe gpu_8x_l40s	384GB	94	576GB	On-Demand	$1.00	$8.00	Not reported

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Nvidia V100

3 configs 1x-4x checked <5m ago

On-Demand from $0.16

From $0.16 / GPU / hr On-Demand Visit website


1x V100 gpu_1x_v100	32GB	16	48GB	On-Demand	$0.16	$0.16	Out of stock
2x V100 gpu_2x_v100	64GB	32	96GB	On-Demand	$0.16	$0.32	Out of stock
4x V100 gpu_4x_v100	128GB	--	--	On-Demand	$0.16	$0.64	Not reported

In-stock and out-of-stock as of our last check at 2026-09-03T15:15Z. Not reported means we could not confirm availability.

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price. See Geodd's pricing.

Thunder Compute

Our sponsor

NVIDIA H100 from $1.38/hr, A100 80GB from $0.78/hr, RTX A6000 from $0.27/hr

No commitments, billed per minute, SOC 2 and GDPR compliant

Hot swappable hardware, templates for ComfyUI and Ollama

One-click connection to VS Code or Cursor, simple CLI to connect without SSH

Try now