GPU Price Index
Language / English

How to choose a GPU cloud for LLM inference

Start with model memory, then compare the billable allocation, region and price type. A low GPU-hour rate alone does not establish whether a model fits or what the full instance costs.

Current means eligible observations in this build’s dated database snapshot, not a new availability check or a market-wide minimum. Whole-GPU USD quotes only; standard and unspecified regions, tax excluded or unknown. Spot stays separate. Stale, fractional, advertised starting prices and GPU-only components do not enter the calculations. Source, tax, marketplace, FX and billing qualifiers remain on the offer cards.

Price observations dated: 2026-11-18

The table computes ideal weight storage from nominal model-card parameter counts stored as database references. FP16 uses two bytes per parameter; packed four-bit weights use half a byte. Results are decimal GB, not GiB. These are nominal-size arithmetic estimates, not measured VRAM requirements: quantization metadata, KV cache, activations and runtime memory add overhead. Context length and concurrency change the requirement. Extra GPU memory does not prove throughput, and memory across multiple GPUs requires a supported sharding setup. Check the linked estimator and cache documentation before choosing capacity.

Calculated weight-storage estimates from cited database references
GPU modelNominal parameters (billions)FP16 weights only (GB)Packed four-bit weights only (GB)
Llama 2 7B7143.5
Llama 2 13B13266.5
Llama 2 70B7014035

Keep headroom above weight storage and test the intended context, batch and precision. The classes below are non-overlapping memory bands per GPU. Their cheapest observed quotes are a shortlist, not a recommendation or proof that a named model fits. Compare the linked exact-model and provider pages for allocation, location and source conditions.

Current eligible offers by memory band, price types separate
VRAM band per GPUPrice typeLowest observed USD/GPU-hour
16 GB – < 24 GBOn-demandRTX A4000 16GB · clore · $0.062 · On-demand
16 GB – < 24 GBSpotRTX A4000 16GB · clore · $0.062 · Spot
24 GB – < 48 GBOn-demandV100 SXM2 32GB · clore · $0.074 · On-demand
24 GB – < 48 GBSpotRTX 3090 24GB · clore · $0.067 · Spot
48 GB – < 80 GBOn-demandCMP 170HX 64GB · clore · $0.231 · On-demand
48 GB – < 80 GBSpotCMP 170HX 64GB · clore · $0.231 · Spot
80 GB+On-demandA100 PCIe 80GB · clore · $0.354 · On-demand
80 GB+SpotA100 PCIe 80GB · clore · $0.250 · Spot

Live-data examples and quote conditions

RTX A4000 16GB 1×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

JP

USD (stablecoin) • platform fees may apply

USD $0.062/hr

$0.062 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.062/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 113131 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX A4000

Reported VRAM: 16 GB

Hourly amount in source scope: USD $0.062/hr · Instance
Source billing unit: Instance-hour
2/2
16 GB
16 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX A4000 16GB 1×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

JP

USD (stablecoin) • platform fees may apply

USD $0.062/hr

$0.062 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.062/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 113131 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX A4000

Reported VRAM: 16 GB

Hourly amount in source scope: USD $0.062/hr · Instance
Source billing unit: Instance-hour
2/2
16 GB
16 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX 3090 24GB 1×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

PL

USD (stablecoin) • platform fees may apply

USD $0.067/hr

$0.067 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.067/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 112743 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 3090

Reported VRAM: 24 GB

Hourly amount in source scope: USD $0.067/hr · Instance
Source billing unit: Instance-hour
16/32
64 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

V100 SXM2 32GB 4×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

RU

USD (stablecoin) • platform fees may apply

USD $0.295/hr

$0.074 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.295/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 122717 · Availability: Available · A · Official API

Reported GPU name: Tesla V100SXM232GB

Reported VRAM: 32 GB

Hourly amount in source scope: USD $0.295/hr · Instance
Source billing unit: Instance-hour
24/48
192 GB
32 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

CMP 170HX 64GB 9×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

FI

USD (stablecoin) • platform fees may apply

USD $2.08/hr

$0.231 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.08/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 115963 · Availability: Available · A · Official API

Reported GPU name: NVIDIA CMP 170HX

Reported VRAM: 64 GB

Hourly amount in source scope: USD $2.08/hr · Instance
Source billing unit: Instance-hour
4/8
32 GB
64 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

CMP 170HX 64GB 9×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

FI

USD (stablecoin) • platform fees may apply

USD $2.08/hr

$0.231 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.08/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 115963 · Availability: Available · A · Official API

Reported GPU name: NVIDIA CMP 170HX

Reported VRAM: 64 GB

Hourly amount in source scope: USD $2.08/hr · Instance
Source billing unit: Instance-hour
4/8
32 GB
64 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

A100 PCIe 80GB 1×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $0.250/hr

$0.250 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.250/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 124543 · Availability: Available · A · Official API

Reported GPU name: NVIDIA A100 80GB PCIe

Reported VRAM: 80 GB

Hourly amount in source scope: USD $0.250/hr · Instance
Source billing unit: Instance-hour
24/24
216 GB
80 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

A100 PCIe 80GB 1×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $0.354/hr

$0.354 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.354/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 124543 · Availability: Available · A · Official API

Reported GPU name: NVIDIA A100 80GB PCIe

Reported VRAM: 80 GB

Hourly amount in source scope: USD $0.354/hr · Instance
Source billing unit: Instance-hour
24/24
216 GB
80 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

Official sources

Know the full job cost before you rent: GPU Budget Kit ($12)

Related guides and comparisons

Methodology & sources