L40 rental price: from $0.79/hr today

L40 offers: 8 configurations from 6 providers

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

L40 price history and range

L40 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its L40 page with node sizes, fees and its own history.

L40 hardware specs

Manufacturer datasheet figures for the L40. Source: www.nvidia.com.

LLM memory estimates for this GPU

These models have an estimated inference footprint within 48 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Models that need more than one L40

• Mixtral 8x22B v0.1 at 16-bit needs about 339 GB with the same context and headroom, so at least 8 cards. The cheapest L40 node with a published size that holds it: 8× at $10.00/hr (CoreWeave, $1.25 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• GLM 4.5 Air at 16-bit needs about 266 GB with the same context and headroom, so at least 6 cards. The cheapest L40 node with a published size that holds it: 8× at $10.00/hr (CoreWeave, $1.25 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• Qwen2.5 72B at 16-bit needs about 176 GB with the same context and headroom, so at least 4 cards. The cheapest L40 node with a published size that holds it: 8× at $10.00/hr (CoreWeave, $1.25 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the L40, and what to pick instead

Start from memory: your model, its context and your batch must fit in 48 GB (the model-fit table above estimates it). Then the L40 is the right card unless one of these fits your job better.

• Pick the A40 (48 GB, from $0.59/hr) when your model fits in 48 GB and you can wait longer: it costs 25% less per hour.
• Pick the A100 (80 GB, from $1.09/hr) when the model or its cache does not fit in 48 GB.
• Pick the L40S (48 GB, from $0.96/hr) when finishing sooner is worth paying more: it has 2.0 times the L40's 16-bit compute.

Rent or buy the L40

We have no confirmed L40 purchase price from the stores we check; renting starts at $0.79 per GPU-hour. A seller quote entered in the calculator gives the break-even.

Compare L40 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

L40 questions

How much does it cost to rent a L40?

The cheapest L40 rental we have is $0.79 per GPU-hour on Thunder Compute (on-demand), checked 22 October 2026. The median of each provider's cheapest on-demand rate is $0.91 across 6 providers.

How much VRAM does a L40 have?

48 GB.

Where is the L40 cheapest right now?

Thunder Compute has the cheapest checked on-demand rate today at $0.79 per GPU-hour; interruptible spot or community capacity starts at $0.69 (RunPod).

GPUs near the L40

• RTX 6000 Ada48 GB$0.75/hrcheapest on-demand
• L40S48 GB$0.96/hrcheapest on-demand
• RTX PRO 500048 GB$0.96/hrcheapest on-demand
• A4048 GB$0.59/hrcheapest on-demand
• A10040-80 GB$0.89/hrcheapest on-demand

Related

All 48 GB+ GPUs · GPUs under $1/hr · Price movers this week · Thunder Compute review · A10 vs L40 · A30 vs L40 · A40 vs L40