Live

get_cost_per_task_metrics

artificialanalysis.ai

Returns Intelligence Index cost-per-task metrics for one model from https://artificialanalysis.ai, including cost, token counts, timing, and Coding or Agentic Index.

Developer Tools Crypto & Web3

Parameters1

Runs3

Updated5h ago

Operational3 runs · 100% succeeded

30 days ago90 days agoranfailednot checkedtoday

Playground

GETget_cost_per_task_metrics GETsearch_models_by_name GETget_model_task_costs GETlist_model_summaries GETget_gpu_benchmarks GETget_model_providers GETget_model_details GETlist_provider_leaderboard GETlist_media_model_families

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

Parameters

model_slugstr= DEFAULT_MODEL_SLUG

Need another parameter? Ask the agent →

Waiting on your first callSet the parameters on the left and test it — the real response shows up right here.

What is get_cost_per_task_metrics?

Returns Intelligence Index cost-per-task metrics for one model from https://artificialanalysis.ai, including cost, token counts, timing, and Coding or Agentic Index. It runs on Notte's browser infrastructure and returns structured JSON, so you can call it like any other API — pass model_slug and get the result back without maintaining a scraper.

Response

{
  "record": {},
  "model_slug": "<string>",
  "source_url": "<string>"
}

Call it

curl --location 'https://us-prod.notte.cc/functions/d99ca856-4545-4189-8b29-58a990f92f0b/runs/start' \
--header 'x-notte-api-key: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
    "function_id": "d99ca856-4545-4189-8b29-58a990f92f0b",
    "variables": {
        "model_slug": "DEFAULT_MODEL_SLUG"
    }
}'

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="d99ca856-4545-4189-8b29-58a990f92f0b") — the "get_cost_per_task_metrics" function, which returns Intelligence Index cost-per-task metrics for one model from https://artificialanalysis.ai, including cost, token counts, timing, and Coding or Agentic Index..

It takes model_slug (str). Return the result as structured JSON.