Live GPU rental prices on Vast.ai, RunPod, AWS and Google Cloud, price history and grid carbon.
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 GPU machines for rent right now across Vast.ai, RunPod, AWS spot and Google Cloud spot, ranked by price. Returns price per hour, provider, country, tier (datacenter or community host), reliability score, whether the price is interruptible (spot), and grid carbon intensity where an open data feed covers the host's grid (Europe and GB live; US by state or cloud region, a day old). Can filter and sort by carbon.Data is refreshed hourly; `observed_at` is the snapshot time. Read-only, free, no account.
GPU model, e.g. RTX4090, RTX5090, H100, H200, A100_80, A100_40, L40S, A6000, RTX3090, L4, T4. Loose forms like '4090' or 'RTX 4090' work.
datacenter keeps only hosts the provider lists as datacenters and drops community hosts (independent hosts on a marketplace)
GPUs on one machine
Maximum offers returned, in sort_by order. total_matching gives the full count.
price: cheapest first. carbon: lowest grid carbon intensity first, cheapest within the same grid; offers with no carbon value go last.
Minimum VRAM per GPU, GB
Only these providers. Default: all.
Upper bound on USD per hour for the whole machine
Only hosts in these ISO 3166-1 alpha-2 countries, e.g. ['US','DE']. Hosts with unknown country are excluded.
Drop hosts whose provider reliability score (0..1, Vast.ai only) is below this. Offers with no score are kept. 0 shows every host.
Only hosts on a grid at or below this carbon intensity, gCO2eq/kWh. Offers with no carbon value are dropped when this is set.
Omit (default) to get on-demand prices plus AWS and Google Cloud spot, which are real prices for a running machine. true also adds Vast.ai / RunPod minimum bids, which are a floor rather than the price of keeping the machine. false drops everything interruptible, cloud spot included (every AWS and Google Cloud offer here is spot).
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http gpu-price-index 'https://gridhop.dev/v1/mcp?src=mcp-registry'
Tool list last changed Nov 15, 2026.
Cheapest GPU machines for rent right now across Vast.ai, RunPod, AWS spot and Google Cloud spot, ranked by price. Returns price per hour, provider, country, tier (datacenter or community host), reliability score, whether the price is interruptible (spot), and grid carbon intensity where an open data feed covers the host's grid (Europe and GB live; US by state or cloud region, a day old). Can filter and sort by carbon.Data is refreshed hourly; `observed_at` is the snapshot time. Read-only, free, no account.
| Argument | Type | Description |
|---|---|---|
| tier | string | datacenter keeps only hosts the provider lists as datacenters and drops community hosts (independent hosts on a marketplace) |
| count | integer | GPUs on one machine |
| limit | integer | Maximum offers returned, in sort_by order. total_matching gives the full count. |
| sort_by | string | price: cheapest first. carbon: lowest grid carbon intensity first, cheapest within the same grid; offers with no carbon value go last. |
| vram_min | number | Minimum VRAM per GPU, GB |
| gpu_class* | string | GPU model, e.g. RTX4090, RTX5090, H100, H200, A100_80, A100_40, L40S, A6000, RTX3090, L4, T4. Loose forms like '4090' or 'RTX 4090' work. |
| providers | array | Only these providers. Default: all. |
| max_price_hr | number | Upper bound on USD per hour for the whole machine |
| region_filter | array | Only hosts in these ISO 3166-1 alpha-2 countries, e.g. ['US','DE']. Hosts with unknown country are excluded. |
| min_reliability | number | Drop hosts whose provider reliability score (0..1, Vast.ai only) is below this. Offers with no score are kept. 0 shows every host. |
| max_carbon_g_kwh | number | Only hosts on a grid at or below this carbon intensity, gCO2eq/kWh. Offers with no carbon value are dropped when this is set. |
| include_interruptible | boolean | Omit (default) to get on-demand prices plus AWS and Google Cloud spot, which are real prices for a running machine. true also adds Vast.ai / RunPod minimum bids, which are a floor rather than the price of keeping the machine. false drops everything interruptible, cloud spot included (every AWS and Google Cloud offer here is spot). |
{
"type": "object",
"required": [
"gpu_class"
],
"properties": {
"tier": {
"enum": [
"any",
"datacenter"
],
"type": "string",
"default": "any",
"description": "datacenter keeps only hosts the provider lists as datacenters and drops community hosts (independent hosts on a marketplace)"
},
"count": {
"type": "integer",
"default": 1,
"maximum": 16,
"minimum": 1,
"description": "GPUs on one machine"
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum offers returned, in sort_by order. total_matching gives the full count."
},
"sort_by": {
"enum": [
"price",
"carbon"
],
"type": "string",
"default": "price",
"description": "price: cheapest first. carbon: lowest grid carbon intensity first, cheapest within the same grid; offers with no carbon value go last."
},
"vram_min": {
"type": "number",
"maximum": 1024,
"minimum": 0,
"description": "Minimum VRAM per GPU, GB"
},
"gpu_class": {
"type": "string",
"description": "GPU model, e.g. RTX4090, RTX5090, H100, H200, A100_80, A100_40, L40S, A6000, RTX3090, L4, T4. Loose forms like '4090' or 'RTX 4090' work."
},
"providers": {
"type": "array",
"items": {
"enum": [
"vastai",
"runpod",
"aws_spot",
"gcp_spot"
],
"type": "string"
},
"description": "Only these providers. Default: all.",
"uniqueItems": true
},
"max_price_hr": {
"type": "number",
"minimum": 0,
"description": "Upper bound on USD per hour for the whole machine"
},
"region_filter": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z]{2}$"
},
"maxItems": 50,
"description": "Only hosts in these ISO 3166-1 alpha-2 countries, e.g. ['US','DE']. Hosts with unknown country are excluded."
},
"min_reliability": {
"type": "number",
"default": 0.9,
"maximum": 1,
"minimum": 0,
"description": "Drop hosts whose provider reliability score (0..1, Vast.ai only) is below this. Offers with no score are kept. 0 shows every host."
},
"max_carbon_g_kwh": {
"type": "number",
"minimum": 0,
"description": "Only hosts on a grid at or below this carbon intensity, gCO2eq/kWh. Offers with no carbon value are dropped when this is set."
},
"include_interruptible": {
"type": "boolean",
"description": "Omit (default) to get on-demand prices plus AWS and Google Cloud spot, which are real prices for a running machine. true also adds Vast.ai / RunPod minimum bids, which are a floor rather than the price of keeping the machine. false drops everything interruptible, cloud spot included (every AWS and Google Cloud offer here is spot)."
}
},
"additionalProperties": false
}How clean and how expensive the electricity is on the power grids GPU hosts sit on (Europe, Great Britain, the US): carbon intensity now, its low and high over the last 24 hours and when, the hour of day that is usually cleanest, the day-ahead wholesale power price now and the cheapest hour in the next 24. Use it to choose where or when to run a job that can wait. The grid_zone values match the grid_zone on find_offers results.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| sort_by | string | carbon: cleanest first. power_price: cheapest day-ahead price first. |
| grid_zone | string | One grid by id, e.g. SE-SE3, DE, US-TEX-ERCO |
| region_filter | array | Only grids in these ISO 3166-1 alpha-2 countries, e.g. ['SE','NO'] |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 60,
"minimum": 1
},
"sort_by": {
"enum": [
"carbon",
"power_price"
],
"type": "string",
"default": "carbon",
"description": "carbon: cleanest first. power_price: cheapest day-ahead price first."
},
"grid_zone": {
"type": "string",
"description": "One grid by id, e.g. SE-SE3, DE, US-TEX-ERCO"
},
"region_filter": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z]{2}$"
},
"maxItems": 50,
"description": "Only grids in these ISO 3166-1 alpha-2 countries, e.g. ['SE','NO']"
}
},
"additionalProperties": false
}Every GPU class in the current snapshot: VRAM, how many offers and which providers have it, the machine sizes (GPU counts) listed, and the cheapest on-demand and spot price per GPU. Use it to see what exists before calling find_offers, or to pick a class by VRAM and price.
| Argument | Type | Description |
|---|---|---|
| vram_min | number | Only classes with at least this much VRAM per GPU, GB |
{
"type": "object",
"properties": {
"vram_min": {
"type": "number",
"maximum": 1024,
"minimum": 0,
"description": "Only classes with at least this much VRAM per GPU, GB"
}
},
"additionalProperties": false
}How the cheapest rental price of one GPU class has moved: one point per day since 1 November 2026 (snapshots are hourly from 10 November; earlier days have only a few), or one per hour for the last three days. For each point: the cheapest on-demand price seen, the typical cheapest (median across the day's hourly snapshots) and the cheapest cloud spot price, per GPU. Use it to judge whether a price is unusually low or high before renting, or how much waiting could save.
| Argument | Type | Description |
|---|---|---|
| days | integer | How far back, in days (hourly: at most 3) |
| gpu_class* | string | GPU model, as for find_offers: RTX4090, H100, A100_80, L4 ... |
| granularity | string | hourly covers the last 72 hours |
{
"type": "object",
"required": [
"gpu_class"
],
"properties": {
"days": {
"type": "integer",
"default": 14,
"maximum": 90,
"minimum": 1,
"description": "How far back, in days (hourly: at most 3)"
},
"gpu_class": {
"type": "string",
"description": "GPU model, as for find_offers: RTX4090, H100, A100_80, L4 ..."
},
"granularity": {
"enum": [
"daily",
"hourly"
],
"type": "string",
"default": "daily",
"description": "hourly covers the last 72 hours"
}
},
"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 15, 2026.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
How clean and how expensive the electricity is on the power grids GPU hosts sit on (Europe, Great Britain, the US): carbon intensity now, its low and high over the last 24 hours and when, the hour of day that is usually cleanest, the day-ahead wholesale power price now and the cheapest hour in the next 24. Use it to choose where or when to run a job that can wait. The grid_zone values match the grid_zone on find_offers results.
How the cheapest rental price of one GPU class has moved: one point per day since 1 November 2026 (snapshots are hourly from 10 November; earlier days have only a few), or one per hour for the last three days. For each point: the cheapest on-demand price seen, the typical cheapest (median across the day's hourly snapshots) and the cheapest cloud spot price, per GPU. Use it to judge whether a price is unusually low or high before renting, or how much waiting could save.
Every GPU class in the current snapshot: VRAM, how many offers and which providers have it, the machine sizes (GPU counts) listed, and the cheapest on-demand and spot price per GPU. Use it to see what exists before calling find_offers, or to pick a class by VRAM and price.