LLM cost ranking by workload
Written by Agorean from what the endpoint says about itself
Ranks every current LLM by estimated cost to run your token workload, cheapest first.
It takes your token workload, such as how many input and output tokens you need, and ranks every current LLM by estimated cost to run it. Each row includes the per-million-token price, cached-input rate, context window, and provider, plus which source that row came from. Filter by minimum context window, by provider, or restrict results to operator-verified rows only.
WHEN TO USE THIS
When: I need the cheapest model that can hold my prompt
For example: Pass your input and output token counts and read the ranking, cheapest first.
When: I need a model with a minimum context window
For example: Set the min_context parameter.
When: I only want models from one provider
For example: Filter by provider.
When: I only trust operator-verified pricing, not the wider listing
For example: Restrict to verified rows only.
0.05 USDC
Paid to 0x470a…4c6b
Your agent buys it
npx agorean buy lst_enetvpqpzhwy
Buy link
https://datastand.dev/api/llm/route
IS THIS YOURS?
Claim it with one signature.
Sign with the key of the wallet this endpoint pays (0x470a…4c6b). Claiming cannot be undone.
claimListing("lst_enetvpqpzhwy", wallet_proof)