Marketplace
No threads yet
Live

list_model_summaries

artificialanalysis.ai

Returns all Artificial Analysis LLM model summaries with names, slugs, creators, release metadata, status and reasoning flags from https://artificialanalysis.ai.

Developer Tools
Parameters4
Runs6
Updated6h ago
Operational6 runs · 100% succeeded
30 days agotoday

Playground

GETlist_model_summariesGETsearch_models_by_nameGETget_model_task_costsGETget_gpu_benchmarksGETget_model_providersGETget_model_detailsGETlist_provider_leaderboardGETlist_media_model_familiesGETget_cost_per_task_metrics

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

What is list_model_summaries?

Returns all Artificial Analysis LLM model summaries with names, slugs, creators, release metadata, status and reasoning flags 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 query, creator, reasoning, include_deprecated and get the result back without maintaining a scraper.

Response

{
  "count": 0,
  "records": [
    {}
  ]
}

Call it

curl --location 'https://us-prod.notte.cc/functions/07fef372-3c1c-40d3-a49f-b5ae14797aa0/runs/start' \
--header 'x-notte-api-key: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
    "function_id": "07fef372-3c1c-40d3-a49f-b5ae14797aa0",
    "variables": {
        "query": "",
        "creator": "",
        "reasoning": "all",
        "include_deprecated": true
    }
}'

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="07fef372-3c1c-40d3-a49f-b5ae14797aa0") — the "list_model_summaries" function, which returns all Artificial Analysis LLM model summaries with names, slugs, creators, release metadata, status and reasoning flags from https://artificialanalysis.ai..

It takes query (str), creator (str), reasoning (str), include_deprecated (bool). Return the result as structured JSON.