GPU and bare-metal price index, 36-month TCO scorecard, and blind counter-quotes.
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.
Hetzner (April 1 and June 15, 2026) and OVHcloud (July/August option and configuration changes, renewals from October 1, 2026) price changes by SKU, with renewal rules and when to stay versus switch. Use the returned SKU ids with calculate_36_month_tco.
Optional, e.g. advance-2, scale-a1, ax102
Hetzner (April 1 and June 15, 2026) and OVHcloud (July/August option and configuration changes, renewals from October 1, 2026) price changes by SKU, with renewal rules and when to stay versus switch. Use the returned SKU ids with calculate_36_month_tco.
| Argument | Type | Description |
|---|---|---|
| sku | string | Optional, e.g. advance-2, scale-a1, ax102 |
| provider | string |
{
"type": "object",
"properties": {
"sku": {
"type": "string",
"description": "Optional, e.g. advance-2, scale-a1, ax102"
},
"provider": {
"enum": [
"hetzner",
"ovhcloud"
],
"type": "string"
}
}
}Normalizes server costs over 36 months (or horizon_months): rent with announced price changes and an assumed yearly rise, setup fees, extra IPv4, egress overage, add-ons. Either pass incumbent_sku (an id from audit_2026_provider_repricing, e.g. ovh-advance-2-2026 or hetzner-ax102-1) with quantity, or pass scorecard: a full input with several quotes to compare (role incumbent|bid, units, pricing{base, unit month|gpu_hour, gpusPerUnit, promo}, setupFeePerUnit, extraIPv4, egress, sla, deliveryDays). Anything not stated is flagged and counted as $0.
| Argument | Type | Description |
|---|---|---|
| eur_usd | number | USD per EUR; defaults to the latest ECB reference rate |
| quantity | integer | |
| scorecard | object | Full ScorecardInput, as used by rentservers.com/tools/36-month-tco/ |
| extra_ipv4 | integer | |
| incumbent_sku | string | |
| horizon_months | integer | |
| overage_usd_per_tb | number | |
| egress_tb_per_month | number | |
| annual_escalation_pct | number | |
| ipv4_monthly_each_usd | number | |
| included_tb_per_server | number |
{
"type": "object",
"properties": {
"eur_usd": {
"type": "number",
"description": "USD per EUR; defaults to the latest ECB reference rate"
},
"quantity": {
"type": "integer",
"minimum": 1
},
"scorecard": {
"type": "object",
"description": "Full ScorecardInput, as used by rentservers.com/tools/36-month-tco/"
},
"extra_ipv4": {
"type": "integer",
"minimum": 0
},
"incumbent_sku": {
"type": "string"
},
"horizon_months": {
"type": "integer",
"maximum": 120,
"minimum": 1
},
"overage_usd_per_tb": {
"type": "number",
"minimum": 0
},
"egress_tb_per_month": {
"type": "number",
"minimum": 0
},
"annual_escalation_pct": {
"type": "number"
},
"ipv4_monthly_each_usd": {
"type": "number",
"minimum": 0
},
"included_tb_per_server": {
"type": "number",
"minimum": 0
}
}
}Prices Managed Inference on Google Cloud (Model A): GPU clusters and vLLM endpoints that run in the client's own GCP project. Google bills compute to the client at list price; Wells Software Consulting LLC bills a flat management retainer per node ($250 L4, $800 A100 80GB, $2,500 H100). For a model, peak requests per second, token split and commitment tier it returns every node shape with GCP compute, retainer and total per month, plus node counts with N+1 once throughput baselines are published (sizing_ready).
| Argument | Type | Description |
|---|---|---|
| tier | string | GCP pricing tier. cud_3y also notes DWS calendar block prices for H100. Default on_demand |
| model* | string | |
| peak_rps* | number | Peak requests per second |
| input_tokens | integer | Prompt tokens per request; default 512 |
| output_tokens | integer | Output tokens per request; default 256 |
{
"type": "object",
"required": [
"model",
"peak_rps"
],
"properties": {
"tier": {
"enum": [
"on_demand",
"cud_1y",
"cud_3y"
],
"type": "string",
"description": "GCP pricing tier. cud_3y also notes DWS calendar block prices for H100. Default on_demand"
},
"model": {
"enum": [
"llama-3.1-8b-fp8",
"mixtral-8x7b-awq",
"llama-3.1-70b-fp8"
],
"type": "string"
},
"peak_rps": {
"type": "number",
"maximum": 1000,
"minimum": 0.1,
"description": "Peak requests per second"
},
"input_tokens": {
"type": "integer",
"maximum": 32768,
"minimum": 16,
"description": "Prompt tokens per request; default 512"
},
"output_tokens": {
"type": "integer",
"maximum": 8192,
"minimum": 16,
"description": "Output tokens per request; default 256"
}
}
}Current, dated rental price benchmarks. GPUs: on-demand and 12-month reserved median USD per GPU-hour, lowest on-demand listing, reserved price by term, and RentServers.com's published quote medians. Dedicated: entry floors, reference tiers and Hetzner/OVHcloud SKU prices. VPS: cheapest and median by size.
| Argument | Type | Description |
|---|---|---|
| model | string | GPU (h100, h200, b200, gb200, a100, l40s) or server (ax102, ax42, advance-2, scale-a1, game-1). |
| region | string | Filters published quote medians. |
| category | string | Defaults to gpu, or dedicated when model is a server SKU. |
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "GPU (h100, h200, b200, gb200, a100, l40s) or server (ax102, ax42, advance-2, scale-a1, game-1)."
},
"region": {
"enum": [
"us",
"eu",
"apac"
],
"type": "string",
"description": "Filters published quote medians."
},
"category": {
"enum": [
"gpu",
"dedicated",
"vps"
],
"type": "string",
"description": "Defaults to gpu, or dedicated when model is a server SKU."
}
}
}Opens a counter-quote request with the RentServers.com desk: 3+ providers bid blind against the spec and the reply lays every quote out on one 36-month basis. Only call this when the user asks for quotes and provides their work email; they must click a confirmation link before any provider is contacted. Requests under $100/mo or for a single VPS get self-serve list prices instead of a ticket.
| Argument | Type | Description |
|---|---|---|
| name | string | |
| notes | string | |
| region* | string | |
| company | string | |
| category* | string | |
| quantity | integer | |
| gpu_count | integer | |
| gpu_model | string | |
| work_email* | string | |
| term_months | integer |
| renewal_date | string |
| spec_summary | string | e.g. 64 × H200 with InfiniBand, or 10 × 16-core/128 GB NVMe servers |
| incumbent_sku | string |
| incumbent_provider | string |
| monthly_budget_usd | number |
| incumbent_monthly_usd | number |
{
"type": "object",
"required": [
"work_email",
"category",
"region"
],
"properties": {
"name": {
"type": "string"
},
"notes": {
"type": "string",
"maxLength": 2000
},
"region": {
"enum": [
"US",
"Europe",
"Asia-Pacific",
"Any"
],
"type": "string"
},
"company": {
"type": "string"
},
"category": {
"enum": [
"gpu",
"dedicated",
"colo",
"vps"
],
"type": "string"
},
"quantity": {
"type": "integer",
"minimum": 1
},
"gpu_count": {
"type": "integer",
"minimum": 1
},
"gpu_model": {
"enum": [
"H100",
"H200",
"B200",
"GB200",
"A100",
"L40S"
],
"type": "string"
},
"work_email": {
"type": "string",
"format": "email"
},
"term_months": {
"type": "integer",
"maximum": 60,
"minimum": 0
},
"renewal_date": {
"type": "string",
"format": "date"
},
"spec_summary": {
"type": "string",
"maxLength": 300,
"description": "e.g. 64 × H200 with InfiniBand, or 10 × 16-core/128 GB NVMe servers"
},
"incumbent_sku": {
"type": "string"
},
"incumbent_provider": {
"type": "string"
},
"monthly_budget_usd": {
"type": "number",
"minimum": 0
},
"incumbent_monthly_usd": {
"type": "number",
"minimum": 0
}
}
}