# whichmodel-mcp

> Use this tool when you need to optimize large language model (LLM) selection for cost and performance, as it provides real-time pricing and benchmarks across 300+ models to inform routing recommendations. It solves the problem of inefficient model selection by offering data-driven guidance for AI agents. Input your specific requirements and receive output recommendations for the most cost-effective LLM models.

Canonical page: https://skillsregistry.net/skills/simon-foad-whichmodel-mcp  
JSON: https://api.skillsregistry.net/v1/skills/simon-foad-whichmodel-mcp

## Description

Cost-optimized LLM model routing recommendations for AI agents — real-time pricing and benchmarks across 300+ models.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/simon-foad/whichmodel-mcp)

## 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": "simon-foad-whichmodel-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/simon-foad-whichmodel-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/simon-foad-whichmodel-mcp/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