Cheap GPUs
v1.0.0Live GPU rental and LLM inference prices across dozens of providers, plus GPU price forecasts.
Endpoint health
online- Last checked
- 11/20/2026, 3:17:49 AM
- Latency
- 100 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.cheap-gpus%2Fcheap-gpus
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.cheap-gpus/cheap-gpus": {
"url": "https://cheap-gpus.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
7 shown · authentication unknown
Cheapest GPU rentals
cheapest_gpu
Cheapest current rental offers for one GPU family (e.g. "H100", "RTX 5090", "b200"), in USD per GPU-hour, cheapest first, one row per provider. pricing_type is "on_demand" (default; can't be interrupted) or "spot" (cheaper, the provider can reclaim the machine). limit: 1-10.
Schema valid · SHA-256 0a6863d8361b…
View input schema
{ "type": "object", "properties": { "gpu": { "description": "GPU family name, case-insensitive; aliases work (e.g. \"H100\", \"rtx 5090\", \"5090\", \"b200\"). Call list_gpu_families for the full list.", "examples": [ "H100", "RTX 5090" ], "title": "Gpu", "type": "string" }, "pricing_type": { "default": "on_demand", "description": "\"on_demand\" (fixed price, can't be interrupted) or \"spot\" (cheaper; the provider can reclaim the machine).", "enum": [ "on_demand", "spot" ], "title": "Pricing Type", "type": "string" }, "limit": { "default": 5, "description": "Maximum rows to return, 1-10; values outside the range are clamped.", "title": "Limit", "type": "integer" } }, "required": [ "gpu" ], "title": "cheapest_gpuArguments" }Cheapest LLM providers
cheapest_model_route
Cheapest inference providers for one LLM (e.g. "deepseek-v3", "gpt-oss-120b"; use find_model if unsure of the name). Prices are USD per 1M tokens; estimated_cost_usd is for the given input/output token counts. One row per provider, cheapest first. limit: 1-10.
Schema valid · SHA-256 b2e66fdc9eb0…
View input schema
Connections
streamable-http
https://cheap-gpus.com/mcp