NVIDIA A10 rental pricing
Ampere architecture · 24 GB GDDR6 memory · 0.6 TB/s bandwidth · 150 W board power · Released 2021
Price history
Weekly median price per GPU per hour
At a glance
prices checked 3h ago- Cheapest in stock
- $1.10/hr
- On-demand · 1× A10 24GB · Modal
- Median price
- $1.20/hr
- On-demand · 4 providers
- 90-day trend
- Flat
- Weekly median on-demand, 5 weeks
- Coverage
- 4 providers
- 6 price points
- $ per FP16 PFLOP-hour
- $8.81
- Rank 11 of 18 priced GPUs · lower is better
Every provider we track
Cheapest listing per provider and pricing type. Sold-out rows stay so you can see who normally carries it.
Per GPU-hour. Spot, reserved and community pricing differ from on-demand; click through for the provider's current figure.
What can the NVIDIA A10 run?
Memory for the weights plus one 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 |
|---|---|---|---|---|
| gpt-oss-20b OpenAI | 20.9B· 3.6B active | 20 GiB | 1 | $1.10 |
| Gemma 3 27B Google | 27.4B | 26 GiB | 2 | $2.20 |
| Qwen3-32B Alibaba | 32.8B | 32 GiB | 2 | $2.20 |
| Llama 3.3 70B Instruct Meta | 70.6B | 67 GiB | 4 | $4.41 |
| gpt-oss-120b OpenAI | 117B· 5.1B active | 109 GiB | 8 | $8.81 |
| Qwen3-235B-A22B Alibaba | 235B· 22.0B active | 220 GiB | 16 | $17.63 |
| DeepSeek-R1 DeepSeek | 684B· 37.0B active | 638 GiB | Over 16 | — |
| Kimi K3 Moonshot AI | 2.78T· 104B active | 2.53 TiB | Over 16 | — |
Sized for one sequence at 4K context with 16-bit KV cache and 10% of memory held back. Serving many users at once needs more; the LLM GPU calculator sizes for concurrency and throughput.
NVIDIA A10 pricing questions
How much does it cost to rent a NVIDIA A10 per hour?
The cheapest NVIDIA A10 in stock right now is $1.10 per GPU-hour on-demand from Modal for the 1× A10 24GB configuration. The median on-demand rate across 4 providers is $1.20 per GPU-hour.
How much does a NVIDIA A10 cost per month?
Running one NVIDIA A10 around the clock for a month (730 hours) costs about $804 at the cheapest in-stock rate of $1.10 per hour. At the median on-demand rate it is about $873 a month. Reserved terms usually come in below that; ask the provider for a quote.
Which provider has the cheapest NVIDIA A10?
Modal has the cheapest NVIDIA A10 in stock right now at $1.10 per GPU-hour on-demand for the 1× A10 24GB configuration. Rates change often, so check the provider table for today's figure before you commit.
Are NVIDIA A10 rental prices going up or down?
The weekly median on-demand rate for the NVIDIA A10 has been flat, moving 0.0% over the last 5 weeks, from $1.20 to $1.20 per GPU-hour.
How many cloud providers rent the NVIDIA A10?
We track 4 providers with 6 live prices for the NVIDIA A10. Sold-out listings stay in the table so you can see who normally carries it, but never set the cheapest figure.
What LLMs can you run on one NVIDIA A10?
With 8-bit weights and a single sequence of context, one NVIDIA A10 holds gpt-oss-20b (20.9B). See the model fit table for the full ladder.
How does the NVIDIA A10 compare on price per PFLOP-hour?
At its cheapest in-stock on-demand rate the NVIDIA A10 delivers dense FP16 compute at $8.81 per PFLOP-hour, which ranks 11 of 18 priced GPUs we cover on that basis. Lower is better: it is the rental price divided by peak FP16 throughput.
Where does this NVIDIA A10 pricing data come from?
Prices are read daily from each provider's public price list or API and recorded whenever they change. Listings are shown per GPU-hour on-demand unless marked otherwise, and the chart covers the last 30 days. The newest listing was checked 3h ago.