Skip to content

GPU Economy - cloud GPU prices

by laserodds21 · remote · no sign-in to list tools · v1.4.0 · published by GitHub user laserodds21

Hourly cloud GPU prices from 60+ providers: find, compare, cost and track GPUs.

Changes · 10
CompareRegistry entry

16 tools: 10 change things and 6 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http gpu-prices https://gpueconomy.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

16 tools

Changes things 10Claude Code: ask
  • buy_vs_rentA 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 pri…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • commitment_savingsCommitted 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 typic…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • estimate_costWhat 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • gpu_pricesCurrent 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • price_historyWeekly 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 p…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • price_indexThe 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 hou…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • provider_infoOne 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…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • provider_pricesEvery 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • recent_price_changesListed 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 chan…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • token_costModelled, 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 …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 6Claude Code: allow
  • compare_gpusTwo 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 bot…No findings

    Why it is in this group

    • The name "compare_gpus" says "compare": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • compare_providersTwo 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.No findings

    Why it is in this group

    • The name "compare_providers" says "compare": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • fetchThe 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 pa…No findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • find_gpusGPU 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…No findings

    Why it is in this group

    • The name "find_gpus" says "find": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_gpusEvery GPU model tracked, with its id, VRAM, how many providers list it and the median on-demand rate card in USD per GPU-hour.No findings

    Why it is in this group

    • The name "list_gpus" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http gpu-prices https://gpueconomy.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__gpu-prices__list_gpus",
      "mcp__gpu-prices__find_gpus",
      "mcp__gpu-prices__compare_gpus",
      "mcp__gpu-prices__compare_providers",
      "mcp__gpu-prices__search",
      "mcp__gpu-prices__fetch"
    ],
    "ask": [
      "mcp__gpu-prices__gpu_prices",
      "mcp__gpu-prices__provider_prices",
      "mcp__gpu-prices__price_index",
      "mcp__gpu-prices__recent_price_changes",
      "mcp__gpu-prices__estimate_cost",
      "mcp__gpu-prices__price_history",
      "mcp__gpu-prices__commitment_savings",
      "mcp__gpu-prices__provider_info",
      "mcp__gpu-prices__token_cost",
      "mcp__gpu-prices__buy_vs_rent"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as gpu-prices. Review it before you use it.