# which-llm

> which-llm — zapkid-which-llm. Use this tool when you need to make informed decisions based on ranked outcomes, and require a secure payment system with discounts for frequent usage. It solves problems related to decision-making under uncertainty, providing a reliable and cost-effective solution. The API accepts HTTP requests and returns ranked decisions, with payment processing via USDC and outcome credits for discounts.

Canonical page: https://skillsregistry.net/skills/zapkid-which-llm  
JSON: https://api.skillsregistry.net/v1/skills/zapkid-which-llm

## Description

Deterministic decision-ranking API with HTTP 402 USDC payments and outcome credits (discounts).

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-23

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** finance
- **Updated:** 2026-09-27

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/zapkid-which-llm)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zapkid-which-llm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zapkid-which-llm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zapkid-which-llm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt