Compute
NVIDIA L40S
As of 2026-11-15, renting one NVIDIA L40S on demand costs $0.79 to $3.766 per hour across 5 providers. The lowest price of any kind is $0.774 (Vast.ai, Market (median ask)). Source: AuraMatrix; list and market prices, not invoices.
Every price, cheapest first
| Provider | Kind | Per GPU-hour | Details | Course | Seen |
|---|---|---|---|---|---|
| Vast.aiMarketplace | Market (median ask) | 0.774 | from a machine-readable price list34 asks, from $0.467 to $1.014 | 2026-11-15 | |
| RunPod Community CloudCommunity hosts | On demand | 0.79 | from a machine-readable price list | · | 2026-11-15 |
| AWSCloud · g6e.xlarge | Reserved, 3 years | 0.804 | one GPU in the machine at $0.804 per hourper GPU: 4 vCPUs and 32 GB memoryfrom a machine-readable price list | · | 2026-11-15 |
| AWSCloud · g6e.48xlarge | Spot | 0.933 | 8 GPUs in the machine at $7.464 per hourper GPU: 24 vCPUs and 192 GB memorylowest in us-east-1a; 11 zones, up to $3.766from a machine-readable price list | 2026-11-15 | |
| RunPod Secure CloudGPU cloud | On demand | 1.09 | from a machine-readable price list | · | 2026-11-15 |
| AWSCloud · g6e.12xlarge | Reserved, 3 years | 1.133 | 4 GPUs in the machine at $4.533 per hourper GPU: 12 vCPUs and 96 GB memoryfrom a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.xlarge | Reserved, 1 year | 1.172 | one GPU in the machine at $1.172 per hourper GPU: 4 vCPUs and 32 GB memoryfrom a machine-readable price list | · | 2026-11-15 |
| AWSCloud · g6e.12xlarge | Spot | 1.319 | 4 GPUs in the machine at $5.275 per hourper GPU: 12 vCPUs and 96 GB memorylowest in us-east-2c; 11 zones, up to $2.623from a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.xlarge | Spot | 1.551 | one GPU in the machine at $1.551 per hourper GPU: 4 vCPUs and 32 GB memorylowest in us-east-1a; 11 zones, up to $1.861from a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.48xlarge | Reserved, 3 years | 1.627 | 8 GPUs in the machine at $13.02 per hourper GPU: 24 vCPUs and 192 GB memoryfrom a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.12xlarge | Reserved, 1 year | 1.653 | 4 GPUs in the machine at $6.61 per hourper GPU: 12 vCPUs and 96 GB memoryfrom a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.xlarge | On demand | 1.861 | one GPU in the machine at $1.861 per hourper GPU: 4 vCPUs and 32 GB memoryfrom a machine-readable price list | · | 2026-11-15 |
| CoreWeaveGPU cloud · L40S | On demand | 2.25 | 8 GPUs in the machine at $18.00 per hourper GPU: 16 vCPUs and 128 GB memoryread from the page; two independent readers agree | 2026-11-15 | |
| AWSCloud · g6e.48xlarge | Reserved, 1 year | 2.373 | 8 GPUs in the machine at $18.98 per hourper GPU: 24 vCPUs and 192 GB memoryfrom a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.12xlarge | On demand | 2.623 | 4 GPUs in the machine at $10.49 per hourper GPU: 12 vCPUs and 96 GB memoryfrom a machine-readable price list | 2026-11-15 | |
| AWSCloud · g6e.48xlarge | On demand | 3.766 | 8 GPUs in the machine at $30.13 per hourper GPU: 24 vCPUs and 192 GB memoryfrom a machine-readable price list | 2026-11-15 |
A cloud that sells whole machines is divided by its GPU count, so its price also covers the CPUs, memory and disk of the machine. A market price is the median of the asks on offer when the snapshot was taken.
Same GPU, different machine
Think of the GPU as the stove in a rented kitchen. The stove is the same everywhere. What differs is how many cooks prepare food for it (the vCPUs) and how much counter space there is (the memory). A strong stove with one cook and a small counter still serves slowly, so two prices for the same GPU are not always prices for the same thing.
| Provider | Per GPU-hour | vCPUs per GPU | Memory per GPU | Network | GPUs in the machine |
|---|---|---|---|---|---|
| AWSg6e.xlarge | 1.861 | 4 | 32 GB | — | 1 |
| CoreWeaveL40S | 2.25 | 16 | 128 GB | — | 8 |
| AWSg6e.12xlarge | 2.623 | 12 | 96 GB | 100 GbpsEFA | 4 |
| AWSg6e.48xlarge | 3.766 | 24 | 192 GB | 400 GbpsEFA | 8 |
Not stated on the price list or page of: RunPod Community Cloud, RunPod Secure Cloud. Their rows above carry a price only. Network is the road to the kitchen: it decides how well several machines can work as one, which matters for training across many GPUs. These are the figures the providers state, not measurements.
The market, hour by hour
A list price is a menu. A marketplace is a street market: stalls come and go, and the going price moves through the day. We look once an hour and write down what is on offer.
| Variant | Median ask now | Median, hour by hour | Median ranged | Lowest ask now | Asks |
|---|---|---|---|---|---|
| L40S | 0.774 | 0.67 – 0.801 | 0.467 | 3494 GPUs |
Can you get one right now?
What RunPod’s API says it has in stock for one GPU, asked once an hour. A price on a list does not mean a machine is free. This is the provider’s own statement, not a test purchase; recording began 2026-11-13.
- L40Slowof 68 hourly checks: medium 1, low 55, none to rent 12
Check a priceHolding a quote for this GPU?See where your price stands →
In your AIAsk your assistant: “What does an L40S cost on demand at each provider?”Connect in one click →
Sources
Vast.ai marketplace: on-demand offers
- URL
- https://console.vast.ai/api/v0/bundles/
- Fetched
- 2026-11-15 22:15 UTC
- SHA-256
- 8 files; first a705ddbf75b31e7217a6c8b4be6744deb7a3efd7e8fb00cba46a5175e566452a
RunPod API: GPU types and prices
- URL
- https://api.runpod.io/graphql
- Fetched
- 2026-11-11 08:38 UTC
- SHA-256
- 87bad28672fc2bc93295946259c0d35144d2dbcf56db6ee2645858c6c493a4c2
AWS APIs: EC2 instance types, Price List (us-east-1) and spot prices
- URL
- https://docs.aws.amazon.com/AWSEC2/latest/APIReference/API_DescribeSpotPriceHistory.html
- Fetched
- 2026-11-11 12:28 UTC
- SHA-256
- 13 files; first 3cc02bda7f5d6569db00d92819d6394477a60420f0832cec855d05479908878a
AWS APIs: EC2 instance types, Price List (us-east-1) and spot prices
- URL
- https://docs.aws.amazon.com/AWSEC2/latest/APIReference/API_DescribeSpotPriceHistory.html
- Fetched
- 2026-11-15 22:16 UTC
- SHA-256
- 16 files; first 1d2d04d9cb57b738a1dc244102acc02a83b8a195e484f7fd744d480a48bd7062
AWS APIs: EC2 instance types, Price List (us-east-1) and spot prices
- URL
- https://docs.aws.amazon.com/AWSEC2/latest/APIReference/API_DescribeSpotPriceHistory.html
- Fetched
- 2026-11-13 05:18 UTC
- SHA-256
- 13 files; first 82619f5a6dd22c9d6b56082ac0613fb225e51d5232c7cb21e1afee5c28ae51e7
CoreWeave: pricing page (GPU instances)
- URL
- https://www.coreweave.com/pricing
- Fetched
- 2026-11-13 03:44 UTC
- SHA-256
- 8c0aae555514038f65be6b94cff772f992489bde9baf1dcb3bd933c48526168e