Loading prices…
A16 rental prices
NVIDIA · Ampere · 16 GB GDDR6 · PCIe · 2021
1 providers · 2 configurations · prices as of Nov 11, 2026, 07:02 UTC
Lowest on-demand
$0.52per GPU·h · ≈ $380/month
at GPU.aiMedian on-demand
$0.52/GPU·h
across 1 providers
Lowest spot
—
interruptible
FP16/BF16 cost
$28.9/PFLOP·h
#73 of 75 GPUs for value
Providers
1
2 configurations
Price history
Daily A16 prices per GPU-hour. The shaded period is reconstructed from public archives: the version history of SkyPilot's price catalogs, Internet Archive copies of providers' pricing pages and the open gpu-price-feed project (fewer providers than live data). After that, PetaPrice's own tracking.
Lowest on-demandMedian on-demand
Price by provider
Cheapest On-demand A16 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
GPU.ai🇺🇸$0.52best
Thin vertical line = median across providers ($0.52).
Every provider we track
Pricing
Size
Host
Provider HQ
1 providers · 2 configurations
Sort
- GPU.aiOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demandCheapest$0.52/GPU·hCheapest
What can the A16 run?
Memory for the weights plus one 32K-token sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr | $/mo |
|---|---|---|---|---|---|
gpt-oss-20b OpenAI · 20.9B | 20.9B · 3.6B active | 20 GiB | 2 | $1.04 at GPU.ai | $759 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $1.04 at GPU.ai | $759 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 4 | $2.08 at GPU.ai | $1,518 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 8 | $4.16 at GPU.ai | $3,037 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $4.16 at GPU.ai | $3,037 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $8.32 at GPU.ai | $6,074 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64 | $33.28 at GPU.ai | $24,294 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64+ | — | — |
Assumes 90% of each GPU's memory is usable and rounds up to 1, 2, 4, 8… GPUs for tensor parallelism (up to 64). $/hr is the GPU count times the cheapest in-stock on-demand rate per GPU; check that the provider rents instances that large. Serving many requests at once needs more memory for context.
Alternatives to the A16
GPUs with similar compute and memory, and their lowest on-demand price right now.
A16 pricing questions
How much does it cost to rent an A16?
On-demand A16 prices start at $0.52 per GPU-hour (GPU.ai). The median across 1 providers is $0.52, and the most expensive is $0.52. Running one GPU around the clock costs about $380 per month at the lowest price.
How much compute do you get per dollar with the A16?
At $0.52 per hour and 0.018 PF of dense FP16/BF16, the A16 costs $28.9 per PFLOP-hour. That ranks 73 of 75 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the A16's key specs?
16 GB GDDR6 with 200 GB/s of memory bandwidth, Ampere architecture (2021), PCIe form factor, 63 W. Dense peak: 0.018 PF FP16 / BF16, 0.036 PF INT8, 0.009 PF TF32, 0.0045 PF FP32.
How current are these prices?
Prices were collected on Nov 11, 2026, 07:02 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.