MCP App Store
by KeenEthics
Cheap GPUS icon

Cheap GPUS MCP Server for Claude

By janus.ai

Overview

Compare live GPU rental and LLM inference prices from inside Claude. Cheap GPUs (cheap-gpus.com) tracks on-demand and spot rental rates from 30+ GPU cloud providers, including vast.ai, RunPod, Lambda, CoreWeave, AWS, Azure and Google Cloud, and per-token prices from 24 LLM inference providers. Prices refresh every few hours. What you can ask: - Cheapest GPU rentals: the lowest current price per GPU-hour for any of 24 GPU families (H100, H200, B200, B300, A100, RTX 5090, L40S and more), on-demand or spot, one row per provider. - GPU price history: daily median prices for a GPU family over the last 90 days. - GPU price forecasts: where prediction markets (Kalshi, Polymarket) and ICE futures expect H100, H200, B200, A100 and RTX 5090 rental prices to go, alongside today's compute-index benchmarks. - Cheapest LLM providers: the lowest-cost providers for a model, with an estimated cost for your input and output token counts. - GPUs needed to host a model: how many of each GPU an open-weight model needs at a given quantization (FP16 to 1-bit), and the cheapest way to rent that setup right now. Example prompts: "What's the cheapest H100 right now?", "How much would 10M input tokens of DeepSeek V3 cost across providers?", "What GPUs do I need to run gpt-oss-120b at 4-bit, and what does it cost per hour?" Read-only public data, no account or sign-in needed. Each result shows when it was last updated, flags stale prices, and links to the matching page on cheap-gpus.com.

How to connect

  1. Claude: Open the Cheap GPUS listing in the Claude connectors directory and choose Connect. Claude listing Cheap GPUS exposes 7 tools here.

Tools

cheapest_gpu

Claude
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 "on_demand" (default; can't be interrupted) or "spot" (cheaper, the provider can reclaim the machine). limit: 1-10.

cheapest_model_route

Claude
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_cost_usd is for the given input/output token counts. One row per provider, cheapest first. limit: 1-10.

find_model

Claude
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 widely offered first. limit: 1-10.

gpu_price_forecast

Claude
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-index benchmarks and cheap-gpus.com's own current median price. Covers H100, H200, B200, A100 and RTX 5090.

gpu_price_history

Claude
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

Claude
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, fp8, mxfp8, int8, q6, fp6, q5, q4km, nvfp4, awq, mxfp4, gptq, int4, q3, q2, iq2, iq1. Estimates memory only (weights + 20% runtime overhead), not throughput. limit: 1-10.

list_gpu_families

Claude
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.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/cheap-gpus-mcp"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/cheap-gpus-mcp)