aliteq.

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

Cheapest NVIDIA H100 PCIe right now

$0.67/hr

Vast.ai· spot · 80 GB · ≈ $160/mo at 8h/day

Cheapest NVIDIA GeForce RTX 5090 right now

$0.20/hr

Vast.ai· spot · 32 GB · ≈ $48/mo at 8h/day

New here?Is Vast.ai safe and worth it? What it really costs, and the hidden fees to check first →Is Runpod worth it? The real monthly bill, prices and storage costs →Making AI video: an app, an API or a rented GPU? What one clip really costs →The cheapest cloud GPU for ComfyUI with Flux or Wan 2.2 video →Can you run your own AI without buying a graphics card? →What is a cloud GPU? →Do you need your own GPU to build an AI app, or can you just use an API? →Want to make AI images but don't have a good GPU? Your two options, honestly →Do you actually need a GPU to use AI for your business? →Compare cards: every GPU by VRAM →

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.

USD per 1M tokens, Novita AI's published rates, read Oct 29, 2026. Bars show the output price.

Cost to run any model, both ways

Live 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.

GPUVRAMVast.ai · spotRunpod · on-demandRunpod · spotLiumCheapestRent
NVIDIA GeForce RTX 409024 GB$0.00 · med $0.39$0.89—$0.30 · spot$0.00/hrVast.ai
NVIDIA GeForce RTX 3060 12GB12 GB$0.03 · med $0.06——$0.09 · on-demand$0.03/hrVast.ai
NVIDIA L424 GB$0.03 · med $0.20$0.69——$0.03/hrVast.ai
NVIDIA RTX A500024 GB$0.04 · med $0.23$0.27——$0.04/hrVast.ai
NVIDIA Tesla T416 GB$0.05 · med $0.05——$0.22 · on-demand$0.05/hrVast.ai
NVIDIA GeForce RTX 5060 Ti 16GB16 GB$0.05 · med $0.11——$0.15 · spot$0.05/hrVast.ai
NVIDIA RTX A400016 GB$0.05 · med $0.09$0.25——$0.05/hrVast.ai
NVIDIA GeForce RTX 4060 Ti 16GB16 GB$0.05 · med $0.11——$0.14 · spot$0.05/hrVast.ai
NVIDIA GeForce RTX 407012 GB$0.07 · med $0.13———$0.07/hrVast.ai
NVIDIA GeForce RTX 3080 Ti12 GB$0.07 · med $0.12$0.18——$0.07/hrVast.ai
NVIDIA GeForce RTX 4070 Ti SUPER16 GB$0.08 · med $0.17——$0.20 · on-demand$0.08/hrVast.ai
NVIDIA GeForce RTX 4070 SUPER12 GB$0.08 · med $0.09——$0.36 · spot$0.08/hrVast.ai
NVIDIA GeForce RTX 507012 GB$0.08 · med $0.13——$0.18 · spot$0.08/hrVast.ai
NVIDIA GeForce RTX 309024 GB$0.09 · med $0.16$0.50—$0.18 · on-demand$0.09/hrVast.ai
NVIDIA GeForce RTX 408016 GB$0.11 · med $0.21$0.50—$0.20 · spot$0.11/hrVast.ai
NVIDIA GeForce RTX 5070 Ti16 GB$0.11 · med $0.19——$0.20 · on-demand$0.11/hrVast.ai
NVIDIA GeForce RTX 4080 SUPER16 GB$0.11 · med $0.20$0.50—$0.24 · on-demand$0.11/hrVast.ai
NVIDIA GeForce RTX 3090 Ti24 GB$0.12 · med $0.21$0.46—$0.25 · on-demand$0.12/hrVast.ai
NVIDIA GeForce RTX 4070 Ti12 GB$0.12 · med $0.14$0.50—$0.15 · on-demand$0.12/hrVast.ai
NVIDIA GeForce RTX 508016 GB$0.15 · med $0.23$0.59—$0.20 · spot$0.15/hrVast.ai
NVIDIA A4048 GB$0.17 · med $0.22$0.59——$0.17/hrVast.ai
NVIDIA DGX Spark (GB10 Grace Blackwell)128 GB$0.20 · med $0.24———$0.20/hrVast.ai
NVIDIA L40S48 GB$0.20 · med $0.53$1.09—$0.74 · on-demand$0.20/hrVast.ai
NVIDIA GeForce RTX 509032 GB$0.20 · med $0.53$1.39—$0.52 · spot$0.20/hrVast.ai
NVIDIA RTX A600048 GB$0.23 · med $0.33$0.69—$0.42 · spot$0.23/hrVast.ai
NVIDIA Tesla V100 32GB SXM232 GB—$0.23——$0.23/hrRunpod
NVIDIA RTX 5000 Ada Generation32 GB$0.27 · med $0.27$0.83——$0.27/hrVast.ai
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition96 GB$0.27 · med $0.93$1.64—$1.40 · spot$0.27/hrVast.ai
NVIDIA RTX 6000 Ada Generation48 GB$0.33 · med $0.47$1.09—$0.80 · on-demand$0.33/hrVast.ai
NVIDIA RTX PRO 6000 Blackwell Workstation Edition96 GB$0.53 · med $1.17$2.79—$1.60 · spot$0.53/hrVast.ai
NVIDIA H100 PCIe80 GB$0.67$2.89—$1.40 · spot$0.67/hrVast.ai
NVIDIA H100 SXM80 GB$0.67 · med $1.47$4.39—$1.85 · spot$0.67/hrVast.ai
NVIDIA A100 80GB PCIe80 GB—$2.09—$0.81 · on-demand$0.81/hrLium
NVIDIA A100 80GB SXM80 GB—$2.19—$1.00 · on-demand$1.00/hrLium
NVIDIA A100 40GB SXM40 GB—$1.00——$1.00/hrRunpod
NVIDIA RTX PRO 6000 Blackwell Server Edition96 GB———$1.29 · on-demand$1.29/hrLium
NVIDIA H200 SXM141 GB$1.32 · med $2.37$5.29—$3.80 · on-demand$1.32/hrVast.ai
AMD Instinct MI300X192 GB—$2.39——$2.39/hrRunpod
NVIDIA B200192 GB$5.94 · med $8.75$7.99—$5.00 · spot$5.00/hrLium

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.

ModelCheapest GPU that fitsQuant$/hr8h/day · mo24/7 · mo
Kimi K3 (MoE)Doesn't fit any single GPU we price at this context — see the model page for multi-GPU and unified-memory options.
DeepSeek V4 Pro (MoE)Doesn't fit any single GPU we price at this context — see the model page for multi-GPU and unified-memory options.
DeepSeek V4.1 Flash (MoE)Doesn't fit any single GPU we price at this context — see the model page for multi-GPU and unified-memory options.
GLM-5.3 (MoE)Doesn't fit any single GPU we price at this context — see the model page for multi-GPU and unified-memory options.
MiniMax-M3.1-Flash (MoE)Doesn't fit any single GPU we price at this context — see the model page for multi-GPU and unified-memory options.
MiniMax-M3 (MoE)AMD Instinct MI300X · 192 GBRunpodQ2_K169 GB$2.39$574$1721
Qwen3 235B-A22B (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiIQ4_XS120 GB$0.20$48$144
MiniMax-M2.5 (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiQ4_0126 GB$0.20$48$144
Qwen3.8-Flash-Next (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiQ5_K_M120 GB$0.20$48$144
Qwen3.5 122B-A10B (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiQ8_0125 GB$0.20$48$144
NVIDIA Nemotron 3.5 Super VL 120B-A12B (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiQ8_0124 GB$0.20$48$144
NVIDIA Nemotron 3 Super 120B-A12B (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiQ8_0123 GB$0.20$48$144
Mistral Small 4 119B (MoE)NVIDIA A40 · 48 GBVast.aiQ2_K48 GB$0.17$42$125
gpt-oss 120B (MoE)NVIDIA DGX Spark (GB10 Grace Blackwell) · 128 GBVast.aiMXFP463 GB$0.20$48$144
Llama 4 Scout 17B-16E (MoE)NVIDIA A40 · 48 GBVast.aiQ2_K44 GB$0.17$42$125
GLM-4.5-Air (MoE)NVIDIA A40 · 48 GBVast.aiQ2_K45 GB$0.17$42$125
Qwen3-Next 80B-A3B (MoE)NVIDIA A40 · 48 GBVast.aiQ4_K_M46 GB$0.17$42$125
Qwen3-Coder-Next 80B-A3B (MoE)NVIDIA A40 · 48 GBVast.aiQ4_K_M46 GB$0.17$42$125
Llama 3.3 70B InstructNVIDIA A40 · 48 GBVast.aiQ4_K_M46 GB$0.17$42$125
DeepSeek R1 Distill 70BNVIDIA A40 · 48 GBVast.aiQ4_K_M46 GB$0.17$42$125
Mixtral 8x7B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ2_K21 GB$0.00$0$1
Qwen3.5 35B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M21 GB$0.00$0$1
Qwen3.6 35B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M21 GB$0.00$0$1
Ornith-1.5 35B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M21 GB$0.00$0$1
DeepSeek R1 Distill 32BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M23 GB$0.00$0$1
Qwen2.5 32B InstructNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M23 GB$0.00$0$1
Qwen2.5 Coder 32BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M23 GB$0.00$0$1
Qwen3 32BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M23 GB$0.00$0$1
NVIDIA Nemotron 3 Nano 30B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M22 GB$0.00$0$1
Gemma 4 31BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M23 GB$0.00$0$1
GLM-4.7-Flash (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M22 GB$0.00$0$1
Qwen3-VL 30B-A3B Instruct (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M23 GB$0.00$0$1
Qwen3 30B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M22 GB$0.00$0$1
Qwen3-Coder 30B-A3B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ5_K_M22 GB$0.00$0$1
Qwen3.8 27BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K23 GB$0.00$0$1
Qwen3.5 27BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K23 GB$0.00$0$1
Qwen3.6 27BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K23 GB$0.00$0$1
Gemma 3 27BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K23 GB$0.00$0$1
Gemma 2 27BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ4_K_M22 GB$0.00$0$1
Gemma 4 26B-A4B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K21 GB$0.00$0$1
Devstral Small 2 24BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K22 GB$0.00$0$1
Mistral Small 24BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ6_K21 GB$0.00$0$1
gpt-oss 20B (MoE)NVIDIA GeForce RTX 4090 · 24 GBVast.aiMXFP414 GB$0.00$0$1
Qwen2.5-Coder 14BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ8_018 GB$0.00$0$1
DeepSeek R1 Distill 14BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ8_018 GB$0.00$0$1
Qwen3 14BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ8_018 GB$0.00$0$1
Phi-4 14BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ8_018 GB$0.00$0$1
Gemma 3 12BNVIDIA GeForce RTX 4090 · 24 GBVast.aiQ8_014 GB$0.00$0$1
Gemma 4 12BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1623 GB$0.00$0$1
Qwen3.5 9BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1619 GB$0.00$0$1
Gemma 2 9BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1623 GB$0.00$0$1
Qwen3 8BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1618 GB$0.00$0$1
Llama 3.1 8B InstructNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1618 GB$0.00$0$1
Gemma 4 E4BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1616 GB$0.00$0$1
Qwen2.5 7B InstructNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1616 GB$0.00$0$1
Mistral 7B Instruct v0.3NVIDIA GeForce RTX 4090 · 24 GBVast.aiF1616 GB$0.00$0$1
Gemma 4 E2BNVIDIA GeForce RTX 4090 · 24 GBVast.aiF1610 GB$0.00$0$1
Qwen3 4B Instruct 2507NVIDIA GeForce RTX 4090 · 24 GBVast.aiF1611 GB$0.00$0$1
Llama 3.2 3B InstructNVIDIA GeForce RTX 4090 · 24 GBVast.aiF169 GB$0.00$0$1

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.

Vast.ai

The cheapest spot marketplace

A marketplace of independent hosts — usually the lowest $/hr anywhere, with reliability that varies by host. Best for interruptible work.

Runpod

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.

Novita AI

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

Massed Compute

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.

GPUCheapest providerDearest providerGap
NVIDIA H100 SXM · 2 providers$1.73 Vast.ai$4.39 Runpod2.5×
NVIDIA H200 SXM · 3 providers$2.37 Vast.ai$5.29 Runpod2.2×
NVIDIA B200 · 3 providers$7.50 Vast.ai$8.89 Lium1.2×
NVIDIA GeForce RTX 5090 · 3 providers$0.21 Vast.ai$1.39 Runpod6.5×
NVIDIA GeForce RTX 4090 · 3 providers$0.27 Vast.ai$0.89 Runpod3.3×

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.