# Cheap Gpus MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.cheap-gpus%2Fcheap-gpus
Registry id: `mcp-registry/com.cheap-gpus/cheap-gpus`
Status: live (checked 2026-11-22T15:49:34.477Z)

## Verdict

Cheap Gpus MCP server answered 100% of Glimind's liveness checks over 30 days, better than 43% of MCP servers, with 282 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (99/100) across 7 tools, costing an agent about 1,629 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 43% of MCP servers |
| Median handshake latency | 282 ms | 43% of MCP servers |
| p95 handshake latency | 456 ms | — |
| Checks in 30 days | 4,045 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 99/100 (A) | 90% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~1,629 tokens | 51% of MCP servers |
| Days observed | 18 | — |

## Install

```json
{
  "mcpServers": {
    "cheap-gpus-mcp-server": {
      "type": "http",
      "url": "https://cheap-gpus.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http cheap-gpus-mcp-server https://cheap-gpus.com/mcp
```

## Tools (7)

- `cheapest_gpu`: Cheapest current rental offers for one GPU family (e.g. "H100", "RTX 5090", "b200"), in USD per GPU-hour, cheapest first, one row per provider. pricing_type is 
- `cheapest_model_route`: Cheapest inference providers for one LLM (e.g. "deepseek-v3", "gpt-oss-120b"; use find_model if unsure of the name). Prices are USD per 1M tokens; estimated_cos
- `find_model`: Search the LLM catalog by name (e.g. "deepseek v3", "gpt-oss", "llama 70b"). Returns model slugs to pass to cheapest_model_route / gpus_needed_for_model, most w
- `gpu_price_forecast`: Market-implied future rental price for one GPU family (USD per GPU-hour), from prediction markets (Kalshi, Polymarket) and ICE futures, plus today's compute-ind
- `gpu_price_history`: Daily price history for one GPU family: each day's median across providers of each provider's cheapest offer (USD per GPU-hour). days: 1-90.
- `gpus_needed_for_model`: How many GPUs it takes to self-host an open-weight LLM at a given quantization, and the cheapest rental setups for it right now. quant is one of: fp16, bf16, fp
- `list_gpu_families`: List every GPU family tracked on cheap-gpus.com, with VRAM, live cheapest on-demand price (USD per GPU-hour), and how many providers currently offer it.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
