GPU Economy - cloud GPU prices

Cost per million output tokens (modelled)

token_cost

Read-only

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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`gpu`	Yes	GPU id or name; NVIDIA publishes runs for B200, B300, H100 SXM, H200 and RTX PRO 6000.
`model`	No	Optional model name to keep (gpt-oss-120b, "Qwen 3.5"); default every model NVIDIA ran on the card.

Output Schema

TableJSON Schema

Name	Required	Description
`gpu`	No
`page`	No
`runs`	No
`rates`	No
`caveat`	No
`gpu_id`	No
`cite_as`	Yes	How to cite this answer: GPU Economy, the page, the data date.
`formula`	No
`modelled`	No
`attribution`	Yes
`data_updated_at`	Yes	Newest scrape behind the answer (ISO 8601).
`throughput_source`	No

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"
+]

AddedOct 1, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing that the figure is modelled rather than measured, exactly how it is derived, that NVIDIA's run conditions differ per card, and that idle GPU time is a floor rather than a bill. This is unusually rich disclosure of limitations for a read-only cost tool.

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 key caveat 'Modelled, not measured' and tightly packed, though the second and third sentences are dense and long. Every clause carries information, but structure leans on em-dash chains rather than separate, scannable points.

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?

With an output schema present, the description need not explain return values, and it supplies the methodological context an agent needs to avoid misreading a modelled floor as an actual bill. It could still say which sibling to use for measured prices, but coverage of the conceptual model is solid.

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

Parameters3/5

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

Schema description coverage is 100%, so both params (gpu, model) are already documented in the schema, including the supported card list and the default-all-models behaviour. The description adds no parameter syntax or format detail beyond that, so the baseline 3 applies.

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?

The description states a specific quantity: cost per million output tokens, derived from a GPU-hour rate and published throughput. It is clearly a modelled per-token cost, not a raw price, which implicitly separates it from gpu_prices or estimate_cost, but it never names a sibling or frames its purpose in the first clause — the lead is a caveat, not a definition.

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?

Usage is only implied through caveats: 'cards are not comparable on it' and 'a floor, never a bill' tell the agent how to read the number but not when to call this tool versus estimate_cost or gpu_prices. No explicit when-to-use/when-not or alternative tool is named.

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?