LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history
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 GPU rentals right now, optionally filtered by minimum VRAM (GB).
minimum VRAM in GB, e.g. 80
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Cheapest GPU rentals right now, optionally filtered by minimum VRAM (GB).
| Argument | Type | Description |
|---|---|---|
| min_vram_gb | number |
| minimum VRAM in GB, e.g. 80 |
{
"type": "object",
"properties": {
"min_vram_gb": {
"type": "number",
"description": "minimum VRAM in GB, e.g. 80"
}
}
}All provider prices for one LLM model: input/output/cache price per 1M tokens and context window per provider, cheapest first.
| Argument | Type | Description |
|---|---|---|
| model* | string | model slug or name, e.g. "deepseek-v4-flash" |
{
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "model slug or name, e.g. \"deepseek-v4-flash\""
}
}
}Daily minimum rental price history for a GPU (recorded daily since 2026-07-06).
| Argument | Type | Description |
|---|---|---|
| gpu* | string | GPU name, e.g. "H100 SXM" or "RTX 4090" |
| days | number | how many most-recent days to return (default 30) |
{
"type": "object",
"required": [
"gpu"
],
"properties": {
"gpu": {
"type": "string",
"description": "GPU name, e.g. \"H100 SXM\" or \"RTX 4090\""
},
"days": {
"type": "number",
"description": "how many most-recent days to return (default 30)"
}
}
}Every GPU with live rental pricing: cheapest $/hr, provider, tier, and VRAM.
No arguments.
{
"type": "object",
"properties": {}
}Search LLM models by name. Returns matching models with provider count and the cheapest input/output price per 1M tokens.
| Argument | Type | Description |
|---|---|---|
| query* | string | model name or fragment, e.g. "deepseek" or "llama 70b" |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "model name or fragment, e.g. \"deepseek\" or \"llama 70b\""
}
}
}