Cheap GPUs

Working Security A

com.cheap-gpus/cheap-gpusv1.0.0 Domain verified

Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts.

Cloud & DevOps

Watch Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://cheap-gpus.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

cheapest_gpu Read-only

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.

gpustring, required

limitinteger

pricing_typestring

Tools (7)

cheapest_gpu

read-only

Argument	Type	Description
gpu*	string
limit	integer
pricing_type	string

Input schema (JSON)

{
  "type": "object",
  "title": "cheapest_gpuArguments",
  "required": [
    "gpu"
  ],
  "properties": {
    "gpu": {
      "type": "string",
      "title": "Gpu"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 5
    },
    "pricing_type": {
      "type": "string",
      "title": "Pricing Type",
      "default": "on_demand"
    }
  }
}

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

read-only

Argument	Type	Description
limit	integer
model*	string
input_tokens	integer
output_tokens	integer

Input schema (JSON)

{
  "type": "object",
  "title": "cheapest_model_routeArguments",
  "required": [
    "model"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 5
    },
    "model": {
      "type": "string",
      "title": "Model"
    },
    "input_tokens": {
      "type": "integer",
      "title": "Input Tokens",
      "default": 1000000
    },
    "output_tokens": {
      "type": "integer",
      "title": "Output Tokens",
      "default": 1000000
    }
  }
}

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 widely offered first. limit: 1-10.

read-only

Argument	Type	Description
limit	integer
query*	string

Input schema (JSON)

{
  "type": "object",
  "title": "find_modelArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "query": {
      "type": "string",
      "title": "Query"
    }
  }
}

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

read-only

Argument	Type	Description
gpu*	string

Input schema (JSON)

{
  "type": "object",
  "title": "gpu_price_forecastArguments",
  "required": [
    "gpu"
  ],
  "properties": {
    "gpu": {
      "type": "string",
      "title": "Gpu"
    }
  }
}

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.

read-only

Argument	Type	Description
gpu*	string
days	integer
pricing_type	string

Input schema (JSON)

{
  "type": "object",
  "title": "gpu_price_historyArguments",
  "required": [
    "gpu"
  ],
  "properties": {
    "gpu": {
      "type": "string",
      "title": "Gpu"
    },
    "days": {
      "type": "integer",
      "title": "Days",
      "default": 30
    },
    "pricing_type": {
      "type": "string",
      "title": "Pricing Type",
      "default": "on_demand"
    }
  }
}

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, 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.

read-only

Argument	Type	Description
limit	integer
model*	string
quant	string

Input schema (JSON)

{
  "type": "object",
  "title": "gpus_needed_for_modelArguments",
  "required": [
    "model"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 5
    },
    "model": {
      "type": "string",
      "title": "Model"
    },
    "quant": {
      "type": "string",
      "title": "Quant",
      "default": "fp8"
    }
  }
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_gpu_familiesArguments",
  "properties": {}
}

Cheap GPUs

Try it

cheapest_gpu Read-only

Cheap GPUs

Try it

cheapest_gpu Read-only

Install

Tools (7)

Security checkA100/100