GridHop GPU Price & Carbon Index
io.github.gridhopaiPublished by GitHub account gridhopaiv0.7.0Updated Nov 16, 2026
Live GPU rental prices on Vast.ai, RunPod, Nebius, CoreWeave, AWS, Azure, Google Cloud, plus carbon.
The publisher's own server: PriceWin
Overview
Read-only MCP server that returns live GPU rental prices across Vast.ai, RunPod, AWS and Google Cloud, with grid carbon intensity where known.
- What you can do
- Find current GPU rental offers by GPU class, filtered by count, minimum VRAM, country, datacenter tier, maximum hourly price, provider, reliability score and maximum grid carbon intensity
- Sort offers by price or by carbon intensity, with up to 50 results per query
- Read per-offer details: provider, GPU class and count, hourly price, country and region, host tier, reliability, interruptibility, snapshot time, grid zone, carbon reading age and estimated grams of CO2 per hour
- When to use it
- Useful when an assistant has to answer questions about what a specific GPU costs to rent right now, compare providers or regions, or pick the lowest-carbon option before a training or inference job is booked elsewhere.
- Requirements
- Remote streamable HTTP endpoint with no authentication, account or API key; nothing to install. Requests are limited to 60 per minute per client.
Installation
In SourceWeft
- Open GridHop GPU Price & Carbon Index in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.gridhopai%2Fgpu-price-index/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"gridhop-gpu-price-carbon-index": {
"type": "http",
"url": "https://gridhop.dev/v1/mcp?src=mcp-registry"
}
}
}README
GridHop GPU Price & Carbon Index
A free, read-only MCP server that tells an AI agent what a GPU costs to rent right now, across several clouds and marketplaces, and how clean the electricity is where that GPU sits.
No account, no API key, nothing to install. It cannot rent anything; it only answers questions.
Want your agent to actually run the job, not just price it? That is GridHop, coming next. Join the waitlist.
Add it to your agent
Claude Code
Cursor (~/.cursor/mcp.json)
Any other MCP client: streamable HTTP, URL above, no authentication.
What you can ask
- "What's the cheapest RTX 4090 I can rent right now?"
- "Find an 8×H100 machine in a datacenter, under $25 an hour."
- "Which A100 offer runs on the cleanest grid?"
- "Compare T4 prices on AWS, Azure and Google Cloud in Europe."
- "What does an 8×H100 machine cost on demand on AWS and on Azure, and how much cheaper is spot?"
- "Which GPUs with at least 48 GB can I rent, and what do they cost?"
- "Has the H100 price gone up or down this week?"
- "Which European grid is cleanest right now, and when is power cheapest in Texas?"
The tools
find_offers
Each offer comes back with provider, GPU class and count, price per hour, country and region, host tier, reliability score, whether it can be interrupted, and where known: grid carbon intensity (g CO₂/kWh), how old that reading is, the grid zone it refers to, and a rough estimate of grams of CO₂ per hour for the GPUs at full load.
One offer from a real answer to "cheapest RTX 4090 in the US" (15 November 2026):
The answer wraps the offers with observed_at (snapshot time), total_matching, warnings (things the agent should tell you, such as stale carbon readings), and sources.
list_gpus
One optional argument, vram_min (GB). Returns one row per GPU class, cheapest first.
price_history
Each point has the cheapest on-demand price seen, the typical one (median of that day's hourly lows), the cheapest AWS, Azure, Google Cloud or Nebius spot price, all per GPU, and how many hourly snapshots the day has. A summary gives the low, the high and the change over the period. Prices follow find_offers' defaults: no marketplace minimum bids, no hosts under 0.9 reliability. History starts 1 November 2026 and is hourly from 10 November.
grid_carbon
Per grid: carbon intensity now and how old the reading is, the low and high of the last 24 hours and when, the hour of day that is usually cleanest, the day-ahead wholesale power price now and the cheapest hour in the next 24. Wholesale prices cover Europe (ENTSO-E), Texas (ERCOT) and California (CAISO); a GPU host may pay a fixed tariff, so a cheap hour on the grid does not by itself make a GPU cheaper.
Where the data comes from
Refreshed every hour. Every result carries observed_at, the time of the snapshot.
- Prices: Vast.ai and RunPod public listings, Nebius spot prices from Nebius's public spot-price API and its on-demand list prices via the SkyPilot catalog (checked against Nebius's pricing page), CoreWeave on-demand list prices from its public pricing page, AWS EC2 on-demand price files and AWS spot prices via the SkyPilot catalog, the Azure Retail Prices API (pay-as-you-go and Spot), and Google Cloud's Billing Catalog (Spot; vCPU + memory + GPU, added up per machine type).
- Carbon intensity: computed from each grid's generation mix with IPCC lifecycle emission factors. Generation data: ENTSO-E Transparency Platform (Europe), NESO Carbon Intensity API (Great Britain, CC BY 4.0), US Energy Information Administration (US).
What to keep in mind
- Prices are list prices at snapshot time, before any fee, and they move. A marketplace machine can be rented by someone else a minute later.
- AWS, Azure and Nebius have both on-demand and spot prices; Google Cloud has spot only. Its on-demand prices are not in the index yet, so every Google Cloud row is interruptible and
include_interruptible: falsereturns none of them. - Nebius spot prices move fast: with demand, as often as every 15 minutes, several-fold within a day, and they can exceed the on-demand price. The index reads them once an hour.
- AWS spot prices are not live. AWS has no key-less feed of current spot prices, so they come from the SkyPilot catalog, refreshed a few times a day: the cheapest availability zone of each region, up to about half a day old. (Until 16 November 2026 this index read an AWS feed that turned out to be frozen since 2024; those prices were wrong and have been removed from the history.)
- CoreWeave is on-demand only, whole 8-GPU nodes, with no region. Its pricing page gives one price for all regions, so those rows have no country and no carbon value, and
region_filterleaves them out. The spot prices on that page are updated by hand every few days, not a live market, so they are not in the index. A CoreWeave account is opened through its sales team. - Cloud rows are list prices, not machines confirmed free. On AWS and Azure the large GPU types usually need a quota increase first, and Azure Spot capacity can be unavailable. Some Azure sizes are left out until their GPU count is confirmed (NCads A10 v4, RTX PRO 6000, GB200), as are sizes with a fraction of a GPU.
- Google Cloud rows are what a machine would cost, not proof it is available. Spot GPU capacity is often unavailable; the tool says so when it shows those rows.
- Marketplace bid prices are minimum bids, a floor rather than the price of keeping the machine, so they are left out unless you ask for them.
- Carbon values cover about half of the offers: Europe, Great Britain and most US states. Elsewhere the field is empty rather than guessed.
- US carbon readings are one or two days old (same hour of day), because the source publishes late.
carbon_lag_hsays how old each reading is. - Some readings are estimates. Where a grid operator reports part of its generation without a fuel type, the offer is marked
carbon_uncertain. - Carbon intensity counts what is generated in a grid zone, not imports. The CO₂-per-hour figure uses nameplate GPU power only; it is an estimate, not a measurement.
- Outside the US, Vast.ai gives only a host's country, so countries with several grid zones use one default zone.
grid_zoneshows which.
What is logged
To see whether the server works and what people look for, each request is logged with: the name and version your agent reports for itself, the country Cloudflare saw the request come from, the tool called, its arguments, and the outcome. No IP address, account, or anything else that identifies a person is stored.
Limits
60 requests a minute per client. Beyond that the server answers 429 with a Retry-After header. A normal agent session uses a handful.
Status
Early and free. The server may change; breaking changes will get a new path (/v2/mcp).
What comes next: GridHop
This index is the first public piece of GridHop, a broker for AI agents. Your agent hands over a GPU job with a budget and a deadline; GridHop picks the machine and the hour across marketplaces, runs it, and returns the results. One prepaid balance, spend caps enforced on our side, scheduling by price and by grid carbon.
It is not open yet. Join the waitlist to hear when it is, and to tell us what you would run.
Questions, wrong prices, a GPU class you could not find: write to [email protected] or open an issue.
Source: README.md at commit 0aad247
Tools
0Version history
5- v0.7.0LatestNov 16, 2026
- v0.6.1Nov 16, 2026
- v0.6.0Nov 15, 2026
- v0.4.0Nov 15, 2026
- v0.3.0Nov 15, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Price integrations
PriceWin
win.priceOfficial publisher
Remote MCP server for live hotel and flight price comparison across Booking.com, Agoda, Trip.com, Traveloka and others, plus direct hotel booking requests.

Canadian Retail Deals and Price Drops (Yugenox)
Published by GitHub account ArpitGandhi1934
Apify-hosted MCP server that lets an assistant pull Canadian retail price drops, flyer deals and per-store stock from public retailer pages.

DeFi Capital Flow-Price Gap
Published by GitHub account zsraduly77
Remote MCP server giving daily, Bitcoin-timestamped DeFi capital-flow versus token-price signals for 10 Ethereum tokens, with free and x402-paid tools.
Precio Real: is this used car's price fair? Spain
Published by GitHub account AlfaBlok
A remote MCP server that tells an assistant whether a used car's asking price in Spain is cheap, fair or dear compared with similar cars on sale.

LOUDTZU Canada Data & Price Tools
Published by GitHub account travisjmurphy
Nine Canada-focused tools for building permits, corporations, recalls, charities, funding programs and retail prices, run through your own Apify account.