Live
get_model_details
artificialanalysis.aiReturns detailed model specifications, benchmark evaluations, intelligence, context window and provider pricing from https://artificialanalysis.ai.
Parameters1
Runs5
Updated6h ago
Operational5 runs · 100% succeeded
30 days ago90 days agoranfailednot checkedtoday
Playground
Runs on Notte and spends your workspace credits — what comes back is the live response, not a sample.
What is get_model_details?
Returns detailed model specifications, benchmark evaluations, intelligence, context window and provider pricing 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 model_slug and get the result back without maintaining a scraper.
Response
{
"model": {},
"pricing": [
{}
],
"evaluations": {},
"provider_count": 0
}Call it
curl --location 'https://us-prod.notte.cc/functions/ae95ec2f-e6c7-4a90-8bf2-8c46dc177850/runs/start' \
--header 'x-notte-api-key: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
"function_id": "ae95ec2f-e6c7-4a90-8bf2-8c46dc177850",
"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="ae95ec2f-e6c7-4a90-8bf2-8c46dc177850") — the "get_model_details" function, which returns detailed model specifications, benchmark evaluations, intelligence, context window and provider pricing from https://artificialanalysis.ai.. It takes model_slug (str). Return the result as structured JSON.