Marketplace
No threads yet
Live

get_gpu_benchmarks

artificialanalysis.ai

Returns GPU system benchmarks, throughput, output speed, latency measurements, pricing and chip specifications from https://artificialanalysis.ai.

Parameters2
Runs5
Updated6h ago
Operational5 runs · 100% succeeded
30 days agotoday

Playground

Runs on Notte and spends your workspace credits — what comes back is the live response, not a sample.

What is get_gpu_benchmarks?

Returns GPU system benchmarks, throughput, output speed, latency measurements, pricing and chip specifications from https://artificialanalysis.ai. It runs on Notte's browser infrastructure and returns structured JSON, so you can call it like any other API — pass gpu, model and get the result back without maintaining a scraper.

Response

{
  "gpus": [
    {}
  ],
  "gpu_count": 0,
  "rental_prices": [
    {}
  ],
  "system_benchmarks": [
    {}
  ],
  "rental_price_count": 0,
  "system_benchmark_count": 0
}

Call it

curl --location 'https://us-prod.notte.cc/functions/17f9896b-105d-48e7-b850-bec7feda8d8b/runs/start' \
--header 'x-notte-api-key: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
    "function_id": "17f9896b-105d-48e7-b850-bec7feda8d8b",
    "variables": {
        "gpu": "",
        "model": ""
    }
}'

Ask an agent

Paste this into Claude Code, Cursor or any MCP client to have an agent call this function for you.

prompt
Use the Anything API MCP server (https://anything.notte.cc/mcp).

Call run(function_id="17f9896b-105d-48e7-b850-bec7feda8d8b") — the "get_gpu_benchmarks" function, which returns GPU system benchmarks, throughput, output speed, latency measurements, pricing and chip specifications from https://artificialanalysis.ai..

It takes gpu (str), model (str). Return the result as structured JSON.