A100 PCIe 40GB rental price: from $1.99/hr
The cheapest on-demand A100 PCIe 40GB is $1.99 an hour at Lambda, in nodes of 4 GPUs ($7.96 per node-hour), checked 21 November 2026.
- Serverless $2.00 Cerebrium, per second
- Highest on-demand $1.99
- 3 offers
- 3 providers
- Cheapest unchanged since 6 July
- Source lambda.ai
A100 PCIe 40GB offers: 3 configurations from 3 providers
More filters: provider, memory, node size, stock, CPU and RAM, sort, price unit
“vCPUs per GPU” and “RAM per GPU” use the 1 of 3 offers whose provider publishes the machine's vCPUs or RAM for a stated number of GPUs (Lambda); an offer that does not publish them never matches a minimum. A GiB counts as 1.07 GB.
- Rent →
Lambda1 configuration$1.99on-demandNot reportedOn-demand $1.99
Configuration Billing $/GPU-hour Node Stock · checked A100 PCIe 40GB×3 listings on-demand $1.99 single GPU checked 21 November 2026 · source Lambda A100 PCIe 40GB pricing · Lambda: every GPU, fees and billing
- Rent →
Cerebrium1 configuration$2.00serverlessNot reportedServerless $2.00
Configuration Billing $/GPU-hour Node Stock · checked A100 PCIe 40GB serverless $2.00 node size not published checked 21 November 2026 · source Cerebrium A100 PCIe 40GB pricing · Cerebrium: every GPU, fees and billing
- Rent →
Modal1 configuration$2.10serverlessNot reportedServerless $2.10
Configuration Billing $/GPU-hour Node Stock · checked A100 PCIe 40GB serverless $2.10 node size not published checked 21 November 2026 · source Modal A100 PCIe 40GB pricing · Modal: every GPU, fees and billing
1 providers with on-demand offers, fresh prices first, then cheapest. Tap a provider for its configurations.
| GPU / provider | Billing | $/GPU-hour | Node · total per hour | Rent |
|---|---|---|---|---|
| A100 PCIe 40GB · Lambda40 GB · ×3 listings | on-demand | $1.99 | 1× $1.99 | Rent →checked 21 NovDetails
|
| A100 PCIe 40GB · Cerebrium40 GB | serverless | $2.00$0.000555/sec | – | Rent → |
| A100 PCIe 40GB · Modal40 GB | serverless | $2.10$0.000583/sec | – | Rent →checked 21 NovDetails
|
Try another provider or reduce the minimum memory.
Fresh prices come first. Within each billing type, prices run lowest first, with unavailable offers last. Commercial relationships never affect ordering. How we collect and rank prices.
Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
Cite this data
GPU Rental Prices, "A100 PCIe 40GB rental price: from $1.99/GPU-hour", prices checked 21 November 2026, https://gpurentalprices.com/a100-pcie-40
Quote it with a link to this page. Downloads of the whole dataset are on Data & API.
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.
A100 PCIe 40GB price history and range
- Cheapest on-demand$1.99(unchanged since 6 July)
A100 PCIe 40GB price range by billing type
Per GPU-hour, latest checked offers. Axis $0 to $4.
CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)
Price changes
- 30 days: unchanged across 3 matching on-demand configurations since 22 October 2026.
- 90 days: No matching dated observations for this comparison.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.
A100 PCIe 40GB daily figures (139 days)
| Date | Cheapest on-demand |
|---|---|
| 2026-11-21 | $1.99 |
| 2026-11-20 | $1.99 |
| 2026-11-19 | $1.99 |
| 2026-11-18 | $1.99 |
| 2026-11-17 | $1.99 |
| 2026-11-16 | $1.99 |
| 2026-11-15 | $1.99 |
| 2026-11-14 | $1.99 |
| 2026-11-13 | $1.99 |
| 2026-11-12 | $1.99 |
| 2026-11-11 | $1.99 |
| 2026-11-10 | $1.99 |
| 2026-11-09 | $1.99 |
| 2026-11-08 | $1.99 |
| 2026-11-07 | $1.99 |
| 2026-11-06 | $1.99 |
| 2026-11-05 | $1.99 |
| 2026-11-04 | $1.99 |
| 2026-11-03 | $1.99 |
| 2026-11-02 | $1.99 |
| 2026-11-01 | $1.99 |
| 2026-10-31 | $1.99 |
| 2026-10-30 | $1.99 |
| 2026-10-29 | $1.99 |
| 2026-10-28 | $1.99 |
| 2026-10-27 | $1.99 |
| 2026-10-26 | $1.99 |
| 2026-10-25 | $1.99 |
| 2026-10-24 | $1.99 |
| 2026-10-23 | $1.99 |
| 2026-10-22 | $1.99 |
| 2026-10-21 | $1.99 |
| 2026-10-20 | $1.99 |
| 2026-10-19 | $1.99 |
| 2026-10-18 | $1.99 |
| 2026-10-17 | $1.99 |
| 2026-10-16 | $1.99 |
| 2026-10-15 | $1.99 |
| 2026-10-14 | $1.99 |
| 2026-10-13 | $1.99 |
| 2026-10-12 | $1.99 |
| 2026-10-11 | $1.99 |
| 2026-10-10 | $1.99 |
| 2026-10-09 | $1.99 |
| 2026-10-08 | $1.99 |
| 2026-10-07 | $1.99 |
| 2026-10-06 | $1.99 |
| 2026-10-05 | $1.99 |
| 2026-10-04 | $1.99 |
| 2026-10-03 | $1.99 |
| 2026-10-02 | $1.99 |
| 2026-10-01 | $1.99 |
| 2026-09-30 | $1.99 |
| 2026-09-29 | $1.99 |
| 2026-09-28 | $1.99 |
| 2026-09-27 | $1.99 |
| 2026-09-26 | $1.99 |
| 2026-09-25 | $1.99 |
| 2026-09-24 | $1.99 |
| 2026-09-23 | $1.99 |
| 2026-09-22 | $1.99 |
| 2026-09-21 | $1.99 |
| 2026-09-20 | $1.99 |
| 2026-09-19 | $1.99 |
| 2026-09-18 | $1.99 |
| 2026-09-17 | $1.99 |
| 2026-09-16 | $1.99 |
| 2026-09-15 | $1.99 |
| 2026-09-14 | $1.99 |
| 2026-09-13 | $1.99 |
| 2026-09-12 | $1.99 |
| 2026-09-11 | $1.99 |
| 2026-09-10 | $1.99 |
| 2026-09-09 | $1.99 |
| 2026-09-08 | $1.99 |
| 2026-09-07 | $1.99 |
| 2026-09-06 | $1.99 |
| 2026-09-05 | $1.99 |
| 2026-09-04 | $1.99 |
| 2026-09-03 | $1.99 |
| 2026-09-02 | $1.99 |
| 2026-09-01 | $1.99 |
| 2026-08-31 | $1.99 |
| 2026-08-30 | $1.99 |
| 2026-08-29 | $1.99 |
| 2026-08-28 | $1.99 |
| 2026-08-27 | $1.99 |
| 2026-08-26 | $1.99 |
| 2026-08-25 | $1.99 |
| 2026-08-24 | $1.99 |
| 2026-08-23 | $1.99 |
| 2026-08-22 | $1.99 |
| 2026-08-21 | $1.99 |
| 2026-08-20 | $1.99 |
| 2026-08-19 | $1.99 |
| 2026-08-18 | $1.99 |
| 2026-08-17 | $1.99 |
| 2026-08-16 | $1.99 |
| 2026-08-15 | $1.99 |
| 2026-08-14 | $1.99 |
| 2026-08-13 | $1.99 |
| 2026-08-12 | $1.99 |
| 2026-08-11 | $1.99 |
| 2026-08-10 | $1.99 |
| 2026-08-09 | $1.99 |
| 2026-08-08 | $1.99 |
| 2026-08-07 | $1.99 |
| 2026-08-06 | $1.99 |
| 2026-08-05 | $1.99 |
| 2026-08-04 | $1.99 |
| 2026-08-03 | $1.99 |
| 2026-08-02 | $1.99 |
| 2026-08-01 | $1.99 |
| 2026-07-31 | $1.99 |
| 2026-07-30 | $1.99 |
| 2026-07-29 | $1.99 |
| 2026-07-28 | $1.99 |
| 2026-07-27 | $1.99 |
| 2026-07-26 | $1.99 |
| 2026-07-25 | $1.99 |
| 2026-07-24 | $1.99 |
| 2026-07-23 | $1.99 |
| 2026-07-22 | $1.99 |
| 2026-07-21 | $1.99 |
| 2026-07-20 | $1.99 |
| 2026-07-19 | $1.99 |
| 2026-07-18 | $1.99 |
| 2026-07-17 | $1.99 |
| 2026-07-16 | $1.99 |
| 2026-07-15 | $1.99 |
| 2026-07-14 | $1.99 |
| 2026-07-13 | $1.99 |
| 2026-07-12 | $1.99 |
| 2026-07-11 | $1.99 |
| 2026-07-10 | $1.99 |
| 2026-07-09 | $1.99 |
| 2026-07-08 | $1.99 |
| 2026-07-07 | $1.99 |
| 2026-07-06 | $1.99 |
A100 PCIe 40GB prices by provider and billing type
Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its A100 PCIe 40GB page with node sizes, fees and its own history.
A100 PCIe 40GB hardware specs
| Architecture | Ampere |
|---|---|
| VRAM | 40 GB |
| FP16 TFLOPS (dense) | 312 |
| Memory bandwidth | 1,555 GB/s |
| TDP | 250 W |
| Interconnect | PCIe Gen4 |
| Launched | 2020 |
Manufacturer datasheet figures for the A100 PCIe 40GB. Source: www.nvidia.com.
A100 PCIe 40GB variants
LLM memory estimates for this GPU
These models have an estimated inference footprint within 40 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.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Mixtral 8x7B v0.1 | 112.7 | 56.7 | 28.7 ✓ |
| Qwen2.5 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen2.5 Coder 32B | 79.9 | 40.6 | 20.9 ✓ |
| DeepSeek R1 Distill Qwen 32B | 79.9 | 40.6 | 20.9 ✓ |
| QwQ 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 | 37.1 ✓ | 18.8 ✓ |
| Qwen3 30B A3B 2507 | 73.8 | 37.1 ✓ | 18.8 ✓ |
| Qwen3 Coder 30B A3B | 73.8 | 37.1 ✓ | 18.8 ✓ |
| Mistral Small 3.2 24B 2506 | 58.4 | 29.6 ✓ | 15.2 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 ✓ | 14.9 ✓ |
| Devstral Small 2507 | 57.4 | 29.1 ✓ | 14.9 ✓ |
| Qwen2.5 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 Coder 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen3 14B | 36.2 ✓ | 18.5 ✓ | 9.7 ✓ |
| phi 4 | 36.2 ✓ | 18.6 ✓ | 9.8 ✓ |
| Phi 4 reasoning | 36.2 ✓ | 18.6 ✓ | 9.8 ✓ |
| Phi 4 reasoning plus | 36.2 ✓ | 18.6 ✓ | 9.8 ✓ |
| Mistral Nemo 2407 | 30.2 ✓ | 15.5 ✓ | 8.2 ✓ |
| Qwen3 8B | 20.4 ✓ | 10.6 ✓ | 5.6 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 ✓ | 10.3 ✓ | 5.5 ✓ |
| Qwen2.5 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Mistral 7B v0.3 | 18.0 ✓ | 9.3 ✓ | 5.0 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen3 4B 2507 | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
Models that need more than one A100 PCIe 40GB
- GLM 4.5 Air at 16-bit needs about 266 GB with the same context and headroom, so at least 7 cards. No provider we track publishes a A100 PCIe 40GB node of that size today. 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 5 cards. No provider we track publishes a A100 PCIe 40GB node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
- DeepSeek R1 Distill Llama 70B at 16-bit needs about 171 GB with the same context and headroom, so at least 5 cards. No provider we track publishes a A100 PCIe 40GB node of that size today. 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 A100 PCIe 40GB, and what to pick instead
Start from memory: your model, its context and your batch must fit in 40 GB (the model-fit table above estimates it). Then the A100 PCIe 40GB 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 70% less per hour.
- Pick the H100 (80 GB, from $1.80/hr) when the model or its cache does not fit in 40 GB, or finishing sooner is worth paying more: it has 3.2 times the A100 PCIe 40GB's 16-bit compute.
Rent or buy the A100 PCIe 40GB
Confirmed A100 PCIe 40GB purchase listings start at $7,800 (A100 40GB PCIe, NetworkOutlet, checked 21 November 2026). That sum rents about 3,920 GPU-hours at the cheapest on-demand rate of $1.99 (checked 21 November 2026), about 1.9 years at 40 hours a week, before electricity, hosting and resale.
Compare A100 PCIe 40GB 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.
A100 PCIe 40GB questions
- How much does it cost to rent an A100 PCIe 40GB?
- The cheapest A100 PCIe 40GB rental we have is $1.99 per GPU-hour on Lambda (on-demand), checked 21 November 2026.
- How much VRAM does an A100 PCIe 40GB have?
- 40 GB.
- Where is the A100 PCIe 40GB cheapest right now?
- Lambda has the cheapest checked on-demand rate on 21 November 2026 at $1.99 per GPU-hour.
GPUs near the A100 PCIe 40GB
- L40S48 GB$0.96/hrcheapest on-demand
- RTX PRO 500048 GB$0.96/hrcheapest on-demand
- H10080-94 GB$1.80/hrcheapest on-demand
- L4048 GB$0.79/hrcheapest on-demand
- GH20096 GB$2.59/hrcheapest on-demand
Related
All 24 GB+ GPUs · GPUs under $2/hr · Price movers this week · Lambda review