# Hundredth Run GPU Cloud Prices

> Live public cloud GPU rental prices (H100, A100, L40S and more) across 20+ providers.

- name: io.github.hundredthrun/gpu-cloud-prices
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 89/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.hundredthrun%2Fgpu-cloud-prices
- tools: https://api.protogrid.dev/v1/servers/io.github.hundredthrun%2Fgpu-cloud-prices/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "gpu-cloud-prices": {
      "type": "http",
      "url": "https://hundredthrun-compute-desk.pages.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-0d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 550 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`, `stability.new_links`: tool history recorded for 0 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 550 tokens to load them all
- tool set hash: 7eb4046dbf6777263e1ecba73058d0d8
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.hundredthrun/gpu-cloud-prices.svg)](https://protogrid.dev/servers/io.github.hundredthrun/gpu-cloud-prices)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://hundredthrun-compute-desk.pages.dev/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `cheapest_gpu`: Cheapest public on-demand rental price for one GPU model (e.g. H100, A100, L40S, RTX 4090), with provider, source URL and comparison page.
- `get_prices`: Search the raw per-provider GPU rental price table (USD per GPU-hour), sorted cheapest first. Use this when you need more than the single cheapest offer: comparing providers for one GPU, finding spot, preemptible or reserved rates, or checking one provider's prices. For just the lowest on-demand price of one GPU, call cheapest_gpu; for an overview of all GPUs, call list_gpus. Returns up to `limit` rows, each with provider, gpu, variant, price, price_type, term, region, source_url and date_checked. Rows without a public numeric price (contact sales) are excluded.
- `list_gpus`: List every tracked cloud GPU with on-demand price range (min, median, max USD per GPU-hour), provider count and the current cheapest offer.