Live · refreshed hourly
Cloud GPU prices right now
What it actually costs to rent each GPU this hour, and further down, the cheapest card that genuinely runs each open model. Real offers from the providers we track, not a marketing rate card.
Some links on this page are referral links: we may earn a commission, at no cost to you.
- GPUs priced
- 39
- live offers
- 320
- providers tracked
- 3
Captured
Before you rent
Rent a GPU, or just call an API?
If you only want answers from an open model, a per-token API can cost less than an hour of GPU time. If you need private data, fine-tuning or image and video models, rent the card.
Option A
Rent a GPU by the hour
For private data, fine-tuning, image and video models, or long sessions. You pay while it runs.
- 16–24 GBNVIDIA GeForce RTX 4090 · Vast.ai$0.00/hr
- 32–48 GBNVIDIA A40 · Vast.ai$0.17/hr
- 80 GB+NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · Vast.ai$0.27/hr
Cheapest listed hourly price per VRAM tier, updated . 3 providers tracked.
Option B
Just call an API, pay per token
For chat, coding and agents on open models, with no GPU to manage. You pay for what you send and get back.
- OpenAI GPT OSS 120B$0.05 in · $0.25 out
- Llama 3.3 70B Instruct$0.135 in · $0.40 out
- Qwen3.6 35B A3B$0.248 in · $1.485 out
USD per 1M tokens, Novita AI's published rates, read Oct 29, 2026. Bars show the output price.
Cost to run any model, both waysLive price table
Every GPU we price, cheapest first
Minimum live $/hr per provider (median in grey when it differs). Spot is interruptible; on-demand is reserved while you run it.
| GPU | VRAM | Vast.ai · spot | Runpod · on-demand | Runpod · spot | Lium | Cheapest | Rent |
|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4090 | 24 GB | $0.00 · med $0.39 | $0.89 | — | $0.30 · spot | $0.00/hr | Vast.ai |
| NVIDIA GeForce RTX 3060 12GB | 12 GB | $0.03 · med $0.06 | — | — | $0.09 · on-demand | $0.03/hr | Vast.ai |
| NVIDIA L4 | 24 GB | $0.03 · med $0.20 | $0.69 | — | — | $0.03/hr | Vast.ai |
| NVIDIA RTX A5000 | 24 GB | $0.04 · med $0.23 | $0.27 | — | — | $0.04/hr | Vast.ai |
| NVIDIA Tesla T4 | 16 GB | $0.05 · med $0.05 | — | — | $0.22 · on-demand | $0.05/hr | Vast.ai |
| NVIDIA GeForce RTX 5060 Ti 16GB | 16 GB | $0.05 · med $0.11 | — | — | $0.15 · spot | $0.05/hr | Vast.ai |
| NVIDIA RTX A4000 | 16 GB | $0.05 · med $0.09 | $0.25 | — | — | $0.05/hr | Vast.ai |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16 GB | $0.05 · med $0.11 | — | — | $0.14 · spot | $0.05/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 | 12 GB | $0.07 · med $0.13 | — | — | — | $0.07/hr | Vast.ai |
| NVIDIA GeForce RTX 3080 Ti | 12 GB | $0.07 · med $0.12 | $0.18 | — | — | $0.07/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16 GB | $0.08 · med $0.17 | — | — | $0.20 · on-demand | $0.08/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 SUPER | 12 GB | $0.08 · med $0.09 | — | — | $0.36 · spot | $0.08/hr | Vast.ai |
| NVIDIA GeForce RTX 5070 | 12 GB | $0.08 · med $0.13 | — | — | $0.18 · spot | $0.08/hr | Vast.ai |
| NVIDIA GeForce RTX 3090 | 24 GB | $0.09 · med $0.16 | $0.50 | — | $0.18 · on-demand | $0.09/hr | Vast.ai |
| NVIDIA GeForce RTX 4080 | 16 GB | $0.11 · med $0.21 | $0.50 | — | $0.20 · spot | $0.11/hr | Vast.ai |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | $0.11 · med $0.19 | — | — | $0.20 · on-demand | $0.11/hr | Vast.ai |
| NVIDIA GeForce RTX 4080 SUPER | 16 GB | $0.11 · med $0.20 | $0.50 | — | $0.24 · on-demand | $0.11/hr | Vast.ai |
| NVIDIA GeForce RTX 3090 Ti | 24 GB | $0.12 · med $0.21 | $0.46 | — | $0.25 · on-demand | $0.12/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 Ti | 12 GB | $0.12 · med $0.14 | $0.50 | — | $0.15 · on-demand | $0.12/hr | Vast.ai |
| NVIDIA GeForce RTX 5080 | 16 GB | $0.15 · med $0.23 | $0.59 | — | $0.20 · spot | $0.15/hr | Vast.ai |
| NVIDIA A40 | 48 GB | $0.17 · med $0.22 | $0.59 | — | — | $0.17/hr | Vast.ai |
| NVIDIA DGX Spark (GB10 Grace Blackwell) | 128 GB | $0.20 · med $0.24 | — | — | — | $0.20/hr | Vast.ai |
| NVIDIA L40S | 48 GB | $0.20 · med $0.53 | $1.09 | — | $0.74 · on-demand | $0.20/hr | Vast.ai |
| NVIDIA GeForce RTX 5090 | 32 GB | $0.20 · med $0.53 | $1.39 | — | $0.52 · spot | $0.20/hr | Vast.ai |
| NVIDIA RTX A6000 | 48 GB | $0.23 · med $0.33 | $0.69 | — | $0.42 · spot | $0.23/hr | Vast.ai |
| NVIDIA Tesla V100 32GB SXM2 | 32 GB | — | $0.23 | — | — | $0.23/hr | Runpod |
| NVIDIA RTX 5000 Ada Generation | 32 GB | $0.27 · med $0.27 | $0.83 | — | — | $0.27/hr | Vast.ai |
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | 96 GB | $0.27 · med $0.93 | $1.64 | — | $1.40 · spot | $0.27/hr | Vast.ai |
| NVIDIA RTX 6000 Ada Generation | 48 GB | $0.33 · med $0.47 | $1.09 | — | $0.80 · on-demand | $0.33/hr | Vast.ai |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | 96 GB | $0.53 · med $1.17 | $2.79 | — | $1.60 · spot | $0.53/hr | Vast.ai |
| NVIDIA H100 PCIe | 80 GB | $0.67 | $2.89 | — | $1.40 · spot | $0.67/hr | Vast.ai |
| NVIDIA H100 SXM | 80 GB | $0.67 · med $1.47 | $4.39 | — | $1.85 · spot | $0.67/hr | Vast.ai |
| NVIDIA A100 80GB PCIe | 80 GB | — | $2.09 | — | $0.81 · on-demand | $0.81/hr | Lium |
| NVIDIA A100 80GB SXM | 80 GB | — | $2.19 | — | $1.00 · on-demand | $1.00/hr | Lium |
| NVIDIA A100 40GB SXM | 40 GB | — | $1.00 | — | — | $1.00/hr | Runpod |
| NVIDIA RTX PRO 6000 Blackwell Server Edition | 96 GB | — | — | — | $1.29 · on-demand | $1.29/hr | Lium |
| NVIDIA H200 SXM | 141 GB | $1.32 · med $2.37 | $5.29 | — | $3.80 · on-demand | $1.32/hr | Vast.ai |
| AMD Instinct MI300X | 192 GB | — | $2.39 | — | — | $2.39/hr | Runpod |
| NVIDIA B200 | 192 GB | $5.94 · med $8.75 | $7.99 | — | $5.00 · spot | $5.00/hr | Lium |
Lium: decentralized GPU marketplace; spot nodes can be interrupted. Its column shows the cheaper of spot and on-demand nodes rentable as a single GPU right now; we list it as price data only — plain link, no referral.
By model
Cheapest way to run each model in the cloud
The cheapest live-priced GPU each model fits on at 16k context, computed from the model's own config, and what a month of it costs.
Monthly figures are the live $/hr × 240h (8h/day) or × 720h (24/7). Whether renting beats buying depends on your own usage — the rent-vs-buy break-even walks through it honestly.
Price alerts
Get a note when H100 or 5090 rentals drop
Prices have fallen 60–75% from their 2024 peak and still move week to week. We watch them hourly; you get the drops that matter, not the noise.
The Aliteq brief
The tech worth knowing — hardware, AI, gaming, deals. No spam, unsubscribe anytime.
The cheapest spot marketplace
A marketplace of independent hosts — usually the lowest $/hr anywhere, with reliability that varies by host. Best for interruptible work.
Managed pods + serverless
Predictable on-demand pods, one-click templates and per-second serverless — the easiest way to go from zero to a running GPU.
New to Runpod? Sign up with Google through this link and load $10: Runpod adds a bonus credit, random between $5 and $500 outside Europe ($5 in Europe), valid 90 days.
Per-token model APIs + GPU instances
Call open models like Llama, Qwen, Gemma and gpt-oss by API and pay per token — no GPU to set up. It also rents GPU instances.
Lium
Lium: decentralized GPU marketplace; spot nodes can be interrupted. Price data only — no referral.
Other providers · not in the price table yet
Hourly GPU VMs + bare metal
GPU virtual machines rented by the hour (their site: "No contracts, no surprises"), plus single-tenant bare-metal servers.
Open data
Download the data
The hourly price log behind this page, free to reuse under CC BY 4.0. Credit “Aliteq — aliteq.com/cloud-gpu” with a link. Every price is a provider's own quote with the time we read it; nothing is estimated or filled in.
CSV · New snapshot every hour
Latest GPU rental prices (CSV)The latest price for every GPU, provider and price type we track: lowest, 25th-percentile and median $/hr per GPU, offer count and the capture time of each row.
aliteq.com/data/gpu-prices.csv
JSON · New snapshot every hour
Latest GPU rental prices (JSON)The same snapshot as JSON, with the license, attribution and column notes in the file.
aliteq.com/data/gpu-prices.json
CSV · Adds the previous day every day
Daily GPU rental price history, last 90 days (CSV)One row per day, GPU, provider and price type for the last 90 complete UTC days: the day's lowest $/hr, the median of the hourly medians, the most offers seen and how many hourly snapshots the day had.
aliteq.com/data/gpu-prices-daily.csv
Prices are US dollars per GPU per hour (a multi-GPU listing is divided by its GPU count), captured every hour from Vast.ai, Runpod, Lium and Novita AI. The history file covers Aug 16, 2026 to Nov 13, 2026 (14,670 rows; the last 90 complete UTC days). Newest capture: . How the figures are made, and the two recording errors we correct in the files: methodology.
What the log shows
From Nov 2, 2026 to Nov 13, 2026, on the 336 card-days where at least two providers listed the same GPU on-demand (32 cards), Vast.ai had the lowest price on 299 (89%) and Lium had the lowest price on 37 (11%). Novita AI and Runpod never had the lowest price.
The same card right now: the lowest on-demand price at the cheapest provider and at the dearest one, from the newest hourly snapshot. A marketplace minimum is one host's listing.
| GPU | Cheapest provider | Dearest provider | Gap |
|---|---|---|---|
| NVIDIA H100 SXM · 2 providers | $1.73 Vast.ai | $4.39 Runpod | 2.5× |
| NVIDIA H200 SXM · 3 providers | $2.37 Vast.ai | $5.29 Runpod | 2.2× |
| NVIDIA B200 · 3 providers | $7.50 Vast.ai | $8.89 Lium | 1.2× |
| NVIDIA GeForce RTX 5090 · 3 providers | $0.21 Vast.ai | $1.39 Runpod | 6.5× |
| NVIDIA GeForce RTX 4090 · 3 providers | $0.27 Vast.ai | $0.89 Runpod | 3.3× |
FAQ
How to read this page
How often are these cloud GPU prices updated?
Hourly. Our worker pulls live offers from each provider's API and stores the minimum, 25th-percentile and median $/hr per GPU. The capture time is shown on the page — never quote a price without its timestamp.
Which cloud GPU providers are tracked?
3 with live prices right now, out of four we pull from: Vast.ai (a spot marketplace of independent hosts — cheapest, variable reliability), Runpod (managed on-demand pods and spot), Lium (a decentralized GPU marketplace; its spot nodes can be interrupted) and Novita AI (its public GPU list: about five single-GPU products, shown only while in stock). Vast.ai, Runpod and Novita AI links are referral links; Lium is listed as price data only, with a plain link and no referral. We add providers to the price table only where a live, legally usable price feed exists; we don't scrape. Massed Compute (hourly GPU VMs) is linked further down through a referral link, without prices in the table yet.
What's the difference between spot and on-demand GPU pricing?
Spot (interruptible) capacity is cheaper but can be reclaimed by the provider mid-job — fine for inference and checkpointed training. On-demand is reserved while you run it and costs more. The table shows both where a provider offers them.
How is 'cheapest GPU that runs a model' calculated?
From each model's own config (layers, hidden size, heads) we compute the VRAM it needs at each quantisation at 16k context (bits-per-weight constants validated to a 0.7% median error), then pick the cheapest live-priced GPU it fits on. It is an estimate of fit and cost, not a benchmark.
Can I download these GPU prices?
Yes. The latest snapshot is at aliteq.com/data/gpu-prices.csv (and .json), refreshed every hour, and the daily history of the last 90 days is at aliteq.com/data/gpu-prices-daily.csv. They are free to reuse under CC BY 4.0; credit "Aliteq — aliteq.com/cloud-gpu" with a link.
Disclosure:Vast.ai, Runpod, Novita AI and Massed Compute links are referral links — if you sign up through one we may earn a commission at no cost to you. Lium links are plain links with no referral. That never changes the ranking: every price on this page is the live figure from the provider's API, cheapest first. Sponsored placements are labelled. Provider names and logos are their owners' trademarks, used to identify the services compared; no partnership or endorsement is implied. Prices are pulled hourly; VRAM fit is an estimate from each model's config, not a benchmark.