decision-economic-optimizer

name	Decision Economic Optimizer
description	Deterministic decision-ranking API with HTTP 402 payments and outcome credits.
version	0.1.0
homepage	https://which-llm.com
credentials_required	true
primary_credential	WALLET_CREDENTIALS
sensitivity	high
always_on	false
disable_model_invocation	false
install_mechanism	instruction_only
writes_to_disk_on_install	false
downloads_code_on_install	false

Which‑LLM: Outcome‑Driven Decision Optimizer

Overview

Use this skill when you need a deterministic recommendation for which LLM to use under explicit constraints such as cost and quality.

This skill is for calling the Which‑LLM API. It does not run an LLM itself. For paid requests, the AI bot needs access to a crypto wallet.

When to use it

• Pick the cheapest model that still meets a quality target
• Choose a fallback model if the preferred one fails
• Keep model selection deterministic and auditable
• Report execution results and earn credits for later requests

Quick Reference

• API base URL: https://api.which-llm.com
• Primary paid endpoint: POST /decision/optimize
• Outcome endpoint: POST /decision/outcome
• Free discovery endpoints: GET /capabilities, GET /pricing, GET /status
• Payment asset: USDC
• Supported chains: Base, Ethereum, Arbitrum, Optimism, Avalanche

Registry Summary Expectations

• Primary credential: WALLET_CREDENTIALS
• Install mechanism: instruction-only
• Writes to disk on install: false
• Downloads code on install: false

Prerequisites

Before using this skill, have the following ready:

• Ability to make HTTPS requests to https://api.which-llm.com
• Ability to send and receive JSON
• AI bot access to a crypto wallet for paid requests

What this skill does

• Sends requests to the Which‑LLM API
• Uses POST /decision/optimize to get a recommended model and fallback plan
• Uses POST /decision/outcome to report real execution results
• Explains the request and response shapes for the public API
• Describes how to retry requests after payment has been satisfied externally

What this skill does not do

• It does not call an LLM directly
• It does not execute arbitrary code from your prompt