GPU Economy - cloud GPU prices

Find GPUs that meet a requirement

find_gpus

Read-only

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.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Cards to return; default 10.
`market`	No	Market of the cheapest rate; default on_demand.
`region`	No	Rates listed in US or EU regions, plus rates that name no region (a provider's rate everywhere); default any.
`vendor`	No	Default any.
`min_vram_gb`	No	Least memory per GPU, in GB (24, 48, 80, 141...). Default 0.
`max_usd_per_gpu_hour`	No	Highest acceptable rate per GPU-hour, compared with each card's cheapest rate. Optional.

Output Schema

TableJSON Schema

Name	Required	Description
`gpus`	No
`note`	No
`cite_as`	Yes	How to cite this answer: GPU Economy, the page, the data date.
`attribution`	Yes
`requirement`	No
`cards_matching`	No
`data_updated_at`	Yes	Newest scrape behind the answer (ISO 8601).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 1, 2026

addedOutput schema / properties / cite_as

Added value: +{
+  "description": "How to cite this answer: GPU Economy, the page, the data date.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "data_updated_at",
-  "attribution"
-]New value: +[
+  "data_updated_at",
+  "attribution",
+  "cite_as"
+]

Changed2 schema fields changedOct 1, 2026

addedInput schema / properties / region

Added value: +{
+  "description": "Rates listed in US or EU regions, plus rates that name no region (a provider's rate everywhere); default any.",
+  "enum": [
+    "any",
+    "US",
+    "EU"
+  ],
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "type": "string"
+    },
+    "cards_matching": {},
+    "data_updated_at": {
+      "description": "Newest scrape behind the answer (ISO 8601).",
+      "type": "string"
+    },
+    "gpus": {},
+    "note": {},
+    "requirement": {}
+  },
+  "required": [
+    "data_updated_at",
+    "attribution"
+  ],
+  "type": "object"
+}

AddedOct 1, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover readOnlyHint and openWorldHint, so the description carries the behavioral load and does disclose the sort order (cheapest first), the per-card payload (cheapest live on-demand rate card with provider/read time/page, median rate card and panel size, VRAM, price per GB), and the market-exclusion rule. It stops short of noting caching staleness or pagination limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the qualifying criteria and sort order before the field enumeration, and every clause maps to real output content. It is dense and reads as one long sentence, but there is little outright waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be restated, and the description still sketches the key return fields. For a zero-required-parameter filtered query tool this is close to complete, with only sibling routing left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning beyond it: it clarifies which market defines the 'cheapest' rate (live on-demand) and that community/marketplace floors stay out unless the market parameter overrides the default. That directly explains the effect of the market parameter on results.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (find) and resource (GPU models) qualified by criteria (memory and price requirement) and sort order (cheapest first). The 'meet a requirement' framing distinguishes it from a plain list_gpus, but it never names a sibling to sharpen that contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives one conditional rule — community capacity and marketplace floors are excluded unless the market is set — which implicitly tells the agent when the default result set is narrowed. However, it offers no guidance on when to use this versus list_gpus, compare_gpus, or gpu_prices.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All GPU Economy - cloud GPU prices tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?