GPU Economy - cloud GPU prices

io.github.laserodds21Published by GitHub account laserodds21v1.5.1Updated Oct 27, 2026

Hourly cloud GPU prices from 80+ providers: find, compare, cost and track GPUs.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureFinanceData & Analytics

Overview

AI-generated overview

Remote MCP server for hourly cloud GPU rental prices from 60+ providers, letting an assistant find, compare, cost and track GPU rates.

What you can do
  • List tracked GPU models with VRAM, provider count and median on-demand rate, and find cards meeting memory and price limits
  • Look up live listed prices for one GPU or one provider, cheapest first, with read times and source pages
  • Compare two GPUs or two providers side by side, including price per GB of VRAM and signed differences
  • Estimate rental cost for N GPUs over a number of hours, and compare committed or spot rates against on-demand
  • Read price trends: the weekly price index, price history and recent price changes
  • Model cost per million output tokens, weigh buying a card against renting it, and search or fetch GPU Economy pages as text
When to use it
Useful when choosing a cloud GPU or provider, budgeting a training or inference workload, or tracking how rental rates move over time. It suits questions about current listed rates and relative cost rather than actual availability.
Requirements
A remote streamable HTTP endpoint at gpueconomy.com; no package, account, API key or environment variable is declared. Network access to the endpoint is needed.
Before you install
Prices are listed rates, not availability, and cost estimates cover rental fees only, excluding storage, egress, taxes and idle time. Token costs are modelled from published throughput, not measured. A commitment is paid whether or not the GPU runs. Data is published under CC BY 4.0 and answers ask to be cited to GPU Economy.

Installation

In SourceWeft

  1. Open GPU Economy - cloud GPU prices in the dashboard and add it to a workspace.
  2. 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.laserodds21%2Fgpu-prices/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.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "gpu-economy-cloud-gpu-prices": {
      "type": "http",
      "url": "https://gpueconomy.com/mcp"
    }
  }
}

Tools

16

list_gpus

List GPU models

Every GPU model tracked, with its id, VRAM, how many providers list it and the median on-demand rate card in USD per GPU-hour.

Takes no parameters.

gpu_prices

Current prices for one GPU

Current listed rental prices for one GPU model across providers, cheapest first, in USD per GPU-hour, each with the time it was read and the GPU Economy page that links its source. Live quotes only.

Parametersgpurequiredlimitmarketregion

provider_prices

Current prices at one provider

Every current listed rental price at one provider (runpod, lambda, aws, vast-ai, ...), in USD per GPU-hour, each with its read time and the GPU Economy page that links its source. Live quotes only.

Parametersproviderrequired

price_index

Cloud GPU Price Index (H100)

The Cloud GPU Price Index: median listed on-demand H100 SXM rate across providers, this week and the last eight weeks, with the base-100 index and the receipts; also the newest hourly point and the monthly averages over a fixed panel.

Parameterswindow

recent_price_changes

Recent price changes

Listed prices that changed in the last 30 days, one row per quote, newest change first: the figure before its first change in the window, the figure now, and how many times it changed. A quote back at its starting figure is left out, and so are marketplace floors unless asked for. Optionally for one GPU or one provider.

Parametersgpulimitproviderinclude_marketplaces

find_gpus

Find GPUs that meet a requirement

GPU models that meet a memory and price requirement, cheapest first: for each card its cheapest live on-demand rate card (provider, read time, page), its median rate card and panel size, VRAM and price per GB of VRAM. Community capacity and marketplace floors are out unless the market is set.

Parameterslimitmarketregionvendormin_vram_gbmax_usd_per_gpu_hour

compare_gpus

Compare two GPUs

Two GPU models side by side: VRAM, median rate card and panel size, cheapest on-demand rate, price per GB of VRAM, retail median where one exists, and every provider that lists both on-demand with the signed difference. Live quotes only.

Parametersarequiredbrequired

compare_providers

Compare two providers

Two providers on every GPU both list on-demand today: each side's cheapest on-demand rate card, the difference and which is lower, and the count. Community capacity and marketplace floors are left out of the comparison. Live quotes only.

Parametersarequiredbrequired

estimate_cost

Estimate what a workload costs

What N GPUs of one model cost for a number of hours at listed rates: at each of the cheapest rate cards and at the median rate card, with the arithmetic. Rental fee only - storage, network egress, taxes and idle time are not counted - and listed rates, not availability.

Parametersgpurequiredgpushourslimitmarketregion

price_history

Weekly price history of one GPU

Weekly median and cheapest listed on-demand rate for one GPU model, newest week first, from two sources kept apart: our own hourly reads, and a series reconstructed from a public price catalog (second-hand). Each week carries its panel size; read a median against it.

Parametersgpurequiredweeks

commitment_savings

What a 1- or 3-year commitment saves

Committed and spot rates for one GPU (or every GPU) set against the same provider's own on-demand rate for the same card, region and price scope - the pairs behind the site's typical discount - with the median per term across every card. A commitment is paid whether the GPU runs or not.

Parametersgputermlimit

provider_info

What a provider is and how it is read

One provider: its type (hyperscaler, specialist GPU cloud or marketplace), the regions or tiers it names, how GPU Economy reads its prices (pricing page, API or rendered page), how many GPU models and live quotes it has, a one-line note for a reader, its cheapest on-demand rate per card, and what it bills beyond the GPU-hour where read (what the rate includes, data out, storage, stopped instances, billing step). Links its GPU Economy page.

Parametersproviderrequired

token_cost

Cost per million output tokens (modelled)

Modelled, not measured: a listed GPU-hour rate divided by the output throughput NVIDIA published for that card and model, per million output tokens, at the cheapest live on-demand rate card and at the median, with NVIDIA's run (model, framework, precision, sequence, concurrency, date). Cards are not comparable on it - NVIDIA runs each card differently - and an idle GPU costs the same and produces nothing: a floor, never a bill.

Parametersgpurequiredmodel

buy_vs_rent

Buy or rent a GPU

A card's new retail price (median of 3+ sellers) against its live on-demand rental rates: months of rental, at the cheapest rate card and at the median, that equal the purchase price, at 100%, 70%, 50% and 25% of a 730-hour month. Rental fee only - power, hosting, the server around the card and resale are not counted. Without gpu, every card that has a retail median.

Parametersgpu

fetch

Read a GPU Economy page

The text of one GPU Economy page by an id from search (gpu:h100-sxm, provider:runpod, index:h100, reserved, buy-vs-rent): its live rates with read times, as plain text, with the page URL to cite.

Parametersidrequired

Version history

3
  1. v1.5.1LatestOct 26, 2026
  2. v1.4.0Oct 1, 2026
  3. v1.0.0Sep 29, 2026

Score

83% 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
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.