corpusAI Cloud Pricing

GPU rental quotes

gpu_quotes

Read-onlyIdempotent

Paid (0.01 USDC per call). Latest rental quotes for one GPU model across neo-clouds, marketplaces and other clouds. One row per quote in each provider's latest daily snapshot: provider, market (ondemand, spot = interruptible, bid = marketplace minimum bid, secure/community = RunPod tiers), GPUs in the quoted unit, USD per GPU-hour, quoted unit price, region where the provider exposes one, and provider-specific detail in extra (marketplace host reliability, VRAM, stock status). Sources are each provider's public price feed or page (Vast.ai: the cheapest 64 offers per model, on-demand and bid); /gpu/models lists who quotes each model. Snapshots are taken several times a day.

Input Schema

TableJSON Schema

Name	Required	Description
`gpu`	Yes	Normalized GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM
`market`	No	Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`, `network`, `lease`, `executed`).
`provider`	No	Restrict to one provider slug as listed by /gpu/models (for example `runpod`, `vast`, `lambda`).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`gpu`	No
`note`	No
`count`	No
`quotes`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "count": {
+      "type": "number"
+    },
+    "gpu": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "quotes": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "extra": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "description": "Provider-specific detail (offer id, host reliability, VRAM, stock).",
+                "properties": {},
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Provider-specific detail (offer id, host reliability, VRAM, stock)."
+          },
+          "gpus": {
+            "description": "GPUs in the quoted unit.",
+            "type": "number"
+          },
+          "market": {
+            "description": "ondemand; spot (interruptible); bid (marketplace minimum bid); secure/community (RunPod tiers); network (io.net network tier); executed (Nosana jobs that ran); lease (Akash active leases); rented (Vast offers inferred taken).",
+            "type": "string"
+          },
+          "observed": {
+            "type": "string"
+          },
+          "price_gpu_hr": {
+            "description": "USD per GPU-hour.",
+            "type": "number"
+          },
+          "price_unit_hr": {
+            "description": "USD per hour for the quoted unit.",
+            "type": "number"
+          },
+          "provider": {
+            "type": "string"
+          },
+          "region": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "sku": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "provider",
+          "market",
+          "gpus",
+          "price_gpu_hr"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed3 schema fields changedSep 27, 2026

changedInput schema / properties / gpu / description

Previous value: -"Normalised GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"New value: +"Normalized GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"

changedInput schema / properties / market / description

Previous value: -"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`)."New value: +"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`, `network`, `lease`, `executed`)."

changedInput schema / properties / provider / description

Previous value: -"Restrict to one provider (`runpod`, `vast`, `datacrunch`, `lambda`, `vultr`, `linode`, `oci`)."New value: +"Restrict to one provider slug as listed by /gpu/models (for example `runpod`, `vast`, `lambda`)."

Changed3 schema fields changedSep 26, 2026

changedInput schema / properties / gpu / description

Previous value: -"Normalized GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"New value: +"Normalised GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"

changedInput schema / properties / market / description

Previous value: -"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`, `network`, `lease`, `executed`)."New value: +"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`)."

changedInput schema / properties / provider / description

Previous value: -"Restrict to one provider slug as listed by /gpu/models (for example `runpod`, `vast`, `lambda`)."New value: +"Restrict to one provider (`runpod`, `vast`, `datacrunch`, `lambda`, `vultr`, `linode`, `oci`)."

Changed3 schema fields changedSep 26, 2026

changedInput schema / properties / gpu / description

Previous value: -"Normalised GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"New value: +"Normalized GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"

changedInput schema / properties / market / description

Previous value: -"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`)."New value: +"Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`, `network`, `lease`, `executed`)."

changedInput schema / properties / provider / description

Previous value: -"Restrict to one provider (`runpod`, `vast`, `datacrunch`, `lambda`, `vultr`, `linode`, `oci`)."New value: +"Restrict to one provider slug as listed by /gpu/models (for example `runpod`, `vast`, `lambda`)."

Changed1 schema field changedSep 26, 2026

changedInput schema / properties / gpu / description

Previous value: -"Normalised GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`."New value: +"Normalised GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`. Example: H100 SXM"

First observedSep 26, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description adds genuinely new behavior: it is paid (0.01 USDC per call), sources are public price feeds, snapshots are taken several times a day, and Vast.ai contributes only the cheapest 64 offers. Cost and data-freshness context go well beyond the annotations, though rate limits and failure behavior are absent.

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

Conciseness3/5

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

Front-loaded with the most decision-relevant facts (paid cost, what it returns). However, the long run-on middle enumerating each output column largely duplicates the existing output schema, which does not earn its place given a structured return definition is already provided.

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 values need not be re-explained, and the description still fills in cost, cadence, sources, and market semantics for a fairly complex tool. The main gap is the absence of comparative guidance against sibling quote/snapshot tools.

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 description coverage is 100%, so the baseline is 3, but the description adds real meaning the schema lacks by defining the market values (`spot` = interruptible, `bid` = marketplace minimum bid, `secure`/`community` = RunPod tiers). It confirms `gpu` must be a normalized model from /gpu/models, reinforcing rather than merely repeating the schema.

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 resource (latest rental quotes) and scope (one GPU model across neo-clouds, marketplaces and other clouds), so the agent knows exactly what it retrieves. However, it never distinguishes itself from close siblings like gpu_snapshot, ondemand, or spot_latest, leaving the agent to infer when this differs from those.

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 implied rather than stated: the reader can infer it's for the freshest cross-provider pricing for a single model, and '/gpu/models lists who quotes each model' gives some routing help. But there is no explicit when-to-use or when-not-to-use guidance versus the numerous snapshot and spot siblings.

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

All corpusAI Cloud Pricing 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.

GPU rental quotes

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources