⚡Under $0.50/hr🧠VRAM Estimator⚖Compare GPUs🎁Free LLM APIs🎯Model Index
Updated Daily UTC

Cheapest Cloud GPU Prices Today

Real-time index of the lowest spot and on-demand GPU rental rates across Spheron, RunPod, Vast.ai, Lambda Labs, and CoreWeave.

Lowest Cost Entry Dev GPU

$0.34/hr

Vast.ai · RTX 4090

Lowest Cost Mid-Tier

$0.69/hr

Vast.ai · L40S

Lowest Cost Enterprise

$1.89/hr

Vast.ai · H100 SXM5

Absolute Floor (Any GPU)

$0.34/hr

Vast.ai · RTX 4090

All GPU Pricing (Sorted by Spot Rate)

Every tracked GPU across all providers, sorted cheapest first.

ProviderGPU & VRAMInterconnectSpot RateOn-DemandMonthlyStatusAction
Vast.ai
Community
RTX 409024GB GDDR6X
Llama 8B ✅Qwen 32B (INT4) ✅FLUX.1 (FP8) ✅70B Models ⚠️ (INT3/Offload)
PCIe 4.0 (64 GB/s)$0.34 / hr$0.85 / hr$208 / moInstant
Deploy →
Spheron
Bare Metal
RTX 409024GB GDDR6X
Llama 8B ✅Qwen 32B (INT4) ✅FLUX.1 (FP8) ✅70B Models ⚠️ (INT3/Offload)
PCIe 4.0 (64 GB/s)$0.69 / hr$1.73 / hr$422 / moInstant
Deploy →
Vast.ai
Community
L40S48GB GDDR6
Llama 8B ✅Qwen 24B ✅FLUX.1 (FP8) ✅70B Models ❌
PCIe 4.0 (64 GB/s)$0.69 / hr$1.73 / hr$422 / moInstant
Deploy →
RunPod
Cloud
RTX 409024GB GDDR6X
Llama 8B ✅Qwen 32B (INT4) ✅FLUX.1 (FP8) ✅70B Models ⚠️ (INT3/Offload)
PCIe 4.0 (64 GB/s)$0.74 / hr$1.85 / hr$453 / moInstant
Deploy →
Lambda Labs
Dedicated
RTX 409024GB GDDR6X
Llama 8B ✅Qwen 32B (INT4) ✅FLUX.1 (FP8) ✅70B Models ⚠️ (INT3/Offload)
PCIe 4.0 (64 GB/s)$0.89 / hr$2.23 / hr$545 / moInstant
Deploy →
RunPod
Cloud
L40S48GB GDDR6
Llama 8B ✅Qwen 24B ✅FLUX.1 (FP8) ✅70B Models ❌
PCIe 4.0 (64 GB/s)$1.09 / hr$2.73 / hr$667 / moInstant
Deploy →
Spheron
Bare Metal
L40S48GB GDDR6
Llama 8B ✅Qwen 24B ✅FLUX.1 (FP8) ✅70B Models ❌
PCIe 4.0 (64 GB/s)$1.19 / hr$2.97 / hr$728 / moInstant
Deploy →
Lambda Labs
Dedicated
L40S48GB GDDR6
Llama 8B ✅Qwen 24B ✅FLUX.1 (FP8) ✅70B Models ❌
PCIe 4.0 (64 GB/s)$1.49 / hr$3.73 / hr$912 / moInstant
Deploy →
Lambda Labs
Dedicated
A100N/A
Llama 70B (FP8) ✅Qwen 32B ✅Production vLLM Cluster ✅DeepSeek R1 ✅
N/A$1.59 / hr$3.98 / hr$973 / moInstant
Deploy →
Vast.ai
Community
H100 SXM580GB HBM3
Llama 70B (FP8) ✅DeepSeek R1 (INT4 Multi-GPU) ✅Production vLLM Cluster ✅
NVLink 4.0 (900 GB/s)$1.89 / hr$4.72 / hr$1,157 / moInstant
Deploy →
Spheron
Bare Metal
H100 SXM580GB HBM3
Llama 70B (FP8) ✅DeepSeek R1 (INT4 Multi-GPU) ✅Production vLLM Cluster ✅
NVLink 4.0 (900 GB/s)$2.29 / hr$5.73 / hr$1,401 / moInstant
Deploy →
Vast.ai
Community
H200141GB HBM3e
Llama 70B (FP8) ✅DeepSeek R1 ✅Production vLLM Cluster ✅Qwen 32B ✅
NVLink 4.0 (900 GB/s)$2.79 / hr$6.98 / hr$1,707 / moInstant
Deploy →
Lambda Labs
Dedicated
H100 SXM580GB HBM3
Llama 70B (FP8) ✅DeepSeek R1 (INT4 Multi-GPU) ✅Production vLLM Cluster ✅
NVLink 4.0 (900 GB/s)$2.99 / hr$7.48 / hr$1,830 / moInstant
Deploy →
Spheron
Bare Metal
H200141GB HBM3e
Llama 70B (FP8) ✅DeepSeek R1 ✅Production vLLM Cluster ✅Qwen 32B ✅
NVLink 4.0 (900 GB/s)$3.19 / hr$7.98 / hr$1,952 / moInstant
Deploy →
RunPod
Cloud
H100 SXM580GB HBM3
Llama 70B (FP8) ✅DeepSeek R1 (INT4 Multi-GPU) ✅Production vLLM Cluster ✅
NVLink 4.0 (900 GB/s)$3.49 / hr$8.73 / hr$2,136 / moInstant
Deploy →
Vast.ai
Community
B200192GB HBM3e
Llama 70B ✅DeepSeek R1 ✅Production vLLM Cluster ✅70B Models ✅
NVLink 5.0 (1.8 TB/s)$3.99 / hr$9.98 / hr$2,442 / moInstant
Deploy →
Lambda Labs
Dedicated
H200141GB HBM3e
Llama 70B (FP8) ✅DeepSeek R1 ✅Production vLLM Cluster ✅Qwen 32B ✅
NVLink 4.0 (900 GB/s)$3.99 / hr$9.98 / hr$2,442 / moInstant
Deploy →
RunPod
Cloud
H200141GB HBM3e
Llama 70B (FP8) ✅DeepSeek R1 ✅Production vLLM Cluster ✅Qwen 32B ✅
NVLink 4.0 (900 GB/s)$4.31 / hr$10.77 / hr$2,638 / moInstant
Deploy →
Spheron
Bare Metal
B200192GB HBM3e
Llama 70B ✅DeepSeek R1 ✅Production vLLM Cluster ✅70B Models ✅
NVLink 5.0 (1.8 TB/s)$4.49 / hr$11.23 / hr$2,748 / moInstant
Deploy →
Lambda Labs
Dedicated
B200192GB HBM3e
Llama 70B ✅DeepSeek R1 ✅Production vLLM Cluster ✅70B Models ✅
NVLink 5.0 (1.8 TB/s)$5.49 / hr$13.73 / hr$3,360 / moInstant
Deploy →
RunPod
Cloud
B200192GB HBM3e
Llama 70B ✅DeepSeek R1 ✅Production vLLM Cluster ✅70B Models ✅
NVLink 5.0 (1.8 TB/s)$5.99 / hr$14.98 / hr$3,666 / moInstant
Deploy →
Data Freshness: Public Cloud APIs & Market Scraping | Refreshed Daily (UTC)Benchmark Baseline: Ubuntu 24.04, CUDA 12.4, vLLM v0.6.x, PagedAttention v2, FlashAttention-3

H100 Price Tracker

Live H100 SXM5 rates across 4+ providers

RTX 4090 Price Tracker

Budget GPU spot rates and availability

VRAM Calculator

Estimate your workload VRAM needs

Token Pricing Index

API vs self-host break-even analysis

Data Freshness: Verified via Public Cloud APIs & Market Scraping | Refreshed Daily (UTC)Spot rates are preemptible. On-demand rates guarantee availability. Monthly = on-demand × 720 hours.Methodology →