RTX 4070 rentals from Vast.ai

1 provider with 16 offers. Sorted by most reliable. Updated 2026-11-13 03:46 UTC.

Vast.ai

marketplace16 offers

★★★★★★★★★★ 5.0

From host reliability5.0

From$0.116per GPU-hour · median $0.167

16 offers in stock · 51 GPUs free99.8% host reliabilityIn stock 100.0% of 30 days
  • 1× GPU · 12 GBAlberta, CA
    1 GPU free now
    $0.116per GPU-hour · about $85/mo
    View deal
  • 1× GPU · 12 GBQuebec, CA
    1 GPU free now
    $0.130per GPU-hour · about $95/mo
    View deal
  • 2× GPU · 12 GBWashington, US
    2 GPUs free now
    $0.135per GPU-hour · about $197/mo
    View deal
  • 1× GPU · 12 GBWashington, US
    1 GPU free now
    $0.136per GPU-hour · about $99/mo
    View deal
  • 1× GPU · 12 GBMissouri, US
    1 GPU free now
    $0.149per GPU-hour · about $109/mo
    View deal
See all 16 offers from Vast.ai ›

Where to find RTX-4070

Every provider we track, by region. 3 of 36 providers have it in stock now.

ProviderAmericas2 in stock · from $0.116Europe1 in stock · from $0.088Asia-Pacific2 in stock · from $0.087Elsewhere1 in stock · from $0.092Region not statedNone in stock
Clore.ai★★★★★★★★★★ 4.3 (1,055)Sold out4 listedFrom $0.08818 in stockFrom $0.0875 in stockFrom $0.09211 in stockNot offered
Vast.ai★★★★★★★★★★ 5.0From $0.11614 in stockNot offeredFrom $0.2202 in stockNot offeredNot offered
SimplePodNot ratedFrom $0.1402 in stockNot offeredNot offeredNot offeredNot offered
NosanaNot ratedNot offeredNot offeredNot offeredNot offeredListed $0.072Stock not published
2 more providers list RTX-4070 on their own site, no live price yet

Regions as each provider states them. Open their pricing page for a price.

ProviderAmericasEuropeAsia-PacificElsewhereRegion not stated
OctaSpacePricing pageNot offeredNot offeredNot offeredNot offeredOfferedNo live price yet
SaladCloudPricing pageNot offeredNot offeredNot offeredNot offeredOfferedNo live price yet

Not offered by: RunPod, Akash, Cudo Compute, io.net, Koyeb, Thunder Compute, Akamai Linode, Microsoft Azure, Oracle Cloud, AWS, OVHcloud, Lium, Exoscale, GPU.ai, IMWT (via Shadeform), Massed Compute (via Shadeform), Lambda (via Shadeform), Crusoe (via Shadeform), Paperspace (via Shadeform), Hyperstack (via Shadeform), Boost Run (via Shadeform), Latitude.sh (via Shadeform), Scaleway (via Shadeform), Voltage Park (via Shadeform), Denvr (via Shadeform), Excess Supply (via Shadeform), Horizon (via Shadeform), Verda (via Shadeform), DigitalOcean (via Shadeform), Nebius (via Shadeform), Vultr, Phyntec (via Shadeform).

For agents

Free to use from code: a JSON API, an MCP server, and every page as Markdown. No API key.

curl "https://gpuscout.cc/api/v1/providers/ranking?gpu=h100&count=8"

llms.txt · OpenAPI · MCP endpoint: https://gpuscout.cc/mcp