Compare GPU rental prices per hour on AWS, Azure, Google Cloud and Akash, by chip, with free GPUs.
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.
utilpeek: GPU prices: cheapest H100, A100, L4 per GPU-hour on AWS, Azure, Google Cloud, Akash. Returns cheapest GPU prices per GPU-hour on AWS, Azure and Google Cloud (list prices) and Akash (marketplace bids with GPUs free), by chip, memory, minimum GPUs per cloud machine, region and price ceiling; returns USD per machine-hour or null for unknown shape and an unknown-shape exclusion count; optionally rent-or-buy break-even. Input: all optional: `chip`, `min_gpu_mem_gb`, `min_gpus_per_machine`, `provider`, `regions`, `pricing`, `max_usd_per_gpu_hour`, `limit`, `rent_vs_buy`. List prices from a snapshot refreshed twice a day, excluding tax, egress and storage; spot changes often. A snapshot over 36 hours old is a 503 (not charged). Typically under 0.1 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. Docs: https://tanod.dev/learn/cloud-gpu-price-api.html
GPU chip, any case, e.g. H100 or A100 80GB.
Rows to return, 1-100.
Price to rank by; any is the lower of the two and also includes Akash marketplace rows (ranked by median bid); on_demand and spot are cloud list prices only.
Region names, e.g. us-east-1.
AWS, Azure, Google Cloud or Akash (marketplace bids, with GPUs free).
Rent-or-buy break-even against the cheapest matching row: monthly cloud cost, monthly ownership cost, break-even month and totals. When min_gpus_per_machine is set and rent_vs_buy.gpus is omitted, compares all GPUs of that machine; an explicit gpus overrides it. Same price.
Minimum GPU memory in GB.
Ceiling on the ranked price, USD.
Minimum GPUs in one cloud machine (1-16). Excludes rows without a known machine shape, including Akash marketplace inventory; count_excluded_unknown_machine_shape reports otherwise-matching rows excluded.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http gpu-prices https://tanod.dev/mcp/gpu-prices
utilpeek: GPU prices: cheapest H100, A100, L4 per GPU-hour on AWS, Azure, Google Cloud, Akash. Returns cheapest GPU prices per GPU-hour on AWS, Azure and Google Cloud (list prices) and Akash (marketplace bids with GPUs free), by chip, memory, minimum GPUs per cloud machine, region and price ceiling; returns USD per machine-hour or null for unknown shape and an unknown-shape exclusion count; optionally rent-or-buy break-even. Input: all optional: `chip`, `min_gpu_mem_gb`, `min_gpus_per_machine`, `provider`, `regions`, `pricing`, `max_usd_per_gpu_hour`, `limit`, `rent_vs_buy`. List prices from a snapshot refreshed twice a day, excluding tax, egress and storage; spot changes often. A snapshot over 36 hours old is a 503 (not charged). Typically under 0.1 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. Docs: https://tanod.dev/learn/cloud-gpu-price-api.html
| Argument | Type | Description |
|---|---|---|
| chip | any | GPU chip, any case, e.g. H100 or A100 80GB. |
| limit | integer | Rows to return, 1-100. |
| pricing | string | Price to rank by; any is the lower of the two and also includes Akash marketplace rows (ranked by median bid); on_demand and spot are cloud list prices only. |
| regions | any | Region names, e.g. us-east-1. |
| provider | any | AWS, Azure, Google Cloud or Akash (marketplace bids, with GPUs free). |
| rent_vs_buy | any | Rent-or-buy break-even against the cheapest matching row: monthly cloud cost, monthly ownership cost, break-even month and totals. When min_gpus_per_machine is set and rent_vs_buy.gpus is omitted, compares all GPUs of that machine; an explicit gpus overrides it. Same price. |
| min_gpu_mem_gb | any | Minimum GPU memory in GB. |
| max_usd_per_gpu_hour | any | Ceiling on the ranked price, USD. |
| min_gpus_per_machine | any | Minimum GPUs in one cloud machine (1-16). Excludes rows without a known machine shape, including Akash marketplace inventory; count_excluded_unknown_machine_shape reports otherwise-matching rows excluded. |
{
"type": "object",
"$defs": {
"RentVsBuy": {
"type": "object",
"title": "RentVsBuy",
"required": [
"purchase_usd"
],
"properties": {
"pue": {
"type": "number",
"title": "Pue",
"default": 1,
"maximum": 3,
"minimum": 1,
"description": "Power usage effectiveness multiplier for cooling and overhead."
},
"gpus": {
"type": "integer",
"title": "Gpus",
"default": 1,
"maximum": 1024,
"minimum": 1,
"description": "Number of GPUs bought and rented. Defaults to 1, or to the cheapest matching machine's GPU count when min_gpus_per_machine is set; an explicit value overrides that default."
},
"months": {
"type": "integer",
"title": "Months",
"default": 36,
"maximum": 120,
"minimum": 1,
"description": "Horizon in months."
},
"resale_pct": {
"type": "number",
"title": "Resale Pct",
"default": 0,
"maximum": 100,
"minimum": 0,
"description": "Resale value after the horizon, percent of the purchase price."
},
"usd_per_kwh": {
"type": "number",
"title": "Usd Per Kwh",
"default": 0.15,
"maximum": 5,
"description": "Electricity price in USD per kWh.",
"exclusiveMinimum": 0
},
"purchase_usd": {
"type": "number",
"title": "Purchase Usd",
"maximum": 10000000,
"description": "Purchase price of the GPUs in USD.",
"exclusiveMinimum": 0
},
"watts_per_gpu": {
"anyOf": [
{
"type": "number",
"maximum": 2000,
"exclusiveMinimum": 0
},
{
"type": "null"
}
],
"title": "Watts Per Gpu",
"default": null,
"description": "Power draw per GPU in watts under load; defaults by chip when the chip is a known one (H100 700, A100 400, L4 72), else required."
},
"hours_per_month": {
"type": "number",
"title": "Hours Per Month",
"default": 730,
"maximum": 744,
"minimum": 1,
"description": "Hours per month the GPUs run (utilisation)."
}
},
"additionalProperties": false
}
},
"title": "get_gpu_pricesArguments",
"properties": {
"chip": {
"anyOf": [
{
"type": "string",
"maxLength": 40,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Chip",
"default": null,
"description": "GPU chip, any case, e.g. H100 or A100 80GB."
},
"limit": {
"type": "integer",
"title": "Limit",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "Rows to return, 1-100."
},
"pricing": {
"enum": [
"on_demand",
"spot",
"any"
],
"type": "string",
"title": "Pricing",
"default": "any",
"description": "Price to rank by; any is the lower of the two and also includes Akash marketplace rows (ranked by median bid); on_demand and spot are cloud list prices only."
},
"regions": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string",
"maxLength": 40,
"minLength": 1
},
"maxItems": 20,
"minItems": 1
},
{
"type": "null"
}
],
"title": "Regions",
"default": null,
"description": "Region names, e.g. us-east-1."
},
"provider": {
"anyOf": [
{
"enum": [
"AWS",
"Azure",
"Google Cloud",
"Akash"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Provider",
"default": null,
"description": "AWS, Azure, Google Cloud or Akash (marketplace bids, with GPUs free)."
},
"rent_vs_buy": {
"anyOf": [
{
"$ref": "#/$defs/RentVsBuy"
},
{
"type": "null"
}
],
"default": null,
"description": "Rent-or-buy break-even against the cheapest matching row: monthly cloud cost, monthly ownership cost, break-even month and totals. When min_gpus_per_machine is set and rent_vs_buy.gpus is omitted, compares all GPUs of that machine; an explicit gpus overrides it. Same price."
},
"min_gpu_mem_gb": {
"anyOf": [
{
"type": "integer",
"maximum": 1000,
"minimum": 1
},
{
"type": "null"
}
],
"title": "Min Gpu Mem Gb",
"default": null,
"description": "Minimum GPU memory in GB."
},
"max_usd_per_gpu_hour": {
"anyOf": [
{
"type": "number",
"maximum": 1000000,
"exclusiveMinimum": 0
},
{
"type": "null"
}
],
"title": "Max Usd Per Gpu Hour",
"default": null,
"description": "Ceiling on the ranked price, USD."
},
"min_gpus_per_machine": {
"anyOf": [
{
"type": "integer",
"maximum": 16,
"minimum": 1
},
{
"type": "null"
}
],
"title": "Min Gpus Per Machine",
"default": null,
"description": "Minimum GPUs in one cloud machine (1-16). Excludes rows without a known machine shape, including Akash marketplace inventory; count_excluded_unknown_machine_shape reports otherwise-matching rows excluded."
}
}
}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 3, 2026.