Live public cloud GPU rental prices (H100, A100, L40S and more) across 20+ providers.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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 public on-demand rental price for one GPU model (e.g. H100, A100, L40S, RTX 4090), with provider, source URL and comparison page.
GPU model, e.g. H100, H200, A100, L40S
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http gpu-cloud-prices https://hundredthrun-compute-desk.pages.dev/mcp
Cheapest public on-demand rental price for one GPU model (e.g. H100, A100, L40S, RTX 4090), with provider, source URL and comparison page.
| Argument | Type | Description |
|---|---|---|
| gpu* | string | GPU model, e.g. H100, H200, A100, L40S |
{
"type": "object",
"required": [
"gpu"
],
"properties": {
"gpu": {
"type": "string",
"description": "GPU model, e.g. H100, H200, A100, L40S"
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| gpu | string | Exact GPU model to match, case and punctuation insensitive, e.g. H100, H200, A100, L40S, B200, MI300X. Omit for all GPUs. |
| limit | integer | Maximum rows to return after sorting cheapest first (1 to 50, default 10). |
| provider | string | Provider name or part of it, case insensitive, e.g. "runpod", "lambda", "vast", "aws". Omit for all providers. |
| price_type | string | Pricing model to keep: on_demand (pay as you go), spot or preemptible (interruptible discount), reserved (committed term), serverless_per_second. Omit for all types. |
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"description": "Exact GPU model to match, case and punctuation insensitive, e.g. H100, H200, A100, L40S, B200, MI300X. Omit for all GPUs."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum rows to return after sorting cheapest first (1 to 50, default 10)."
},
"provider": {
"type": "string",
"description": "Provider name or part of it, case insensitive, e.g. \"runpod\", \"lambda\", \"vast\", \"aws\". Omit for all providers."
},
"price_type": {
"enum": [
"on_demand",
"spot",
"reserved",
"preemptible",
"serverless_per_second"
],
"type": "string",
"description": "Pricing model to keep: on_demand (pay as you go), spot or preemptible (interruptible discount), reserved (committed term), serverless_per_second. Omit for all types."
}
},
"additionalProperties": false
}List every tracked cloud GPU with on-demand price range (min, median, max USD per GPU-hour), provider count and the current cheapest offer.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 13, 2026.