whichmodel-mcp

A model routing advisor for autonomous agents — get cost-optimised LLM recommendations via MCP.

whichmodel.dev tracks pricing and capabilities across 100+ LLM models, updated every 4 hours. This MCP server exposes that data so AI agents can pick the right model at the best price for every task.

MCP Endpoint

https://whichmodel.dev/mcp

Transport: Streamable HTTP (MCP spec 2025-03-26)

Related MCP server: ToolRoute

Quick Start

Add to your MCP client config:

{
  "mcpServers": {
    "whichmodel": {
      "url": "https://whichmodel.dev/mcp"
    }
  }
}

No API key required. No installation needed.

Stdio (local clients)

For MCP clients that use stdio transport (Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "whichmodel": {
      "command": "npx",
      "args": ["-y", "whichmodel-mcp"]
    }
  }
}

This runs a thin local proxy that forwards requests to the remote server.

Tools

recommend_model

Get a cost-optimised model recommendation for a specific task type, complexity, and budget.

Returns: recommended model, alternative, budget option, cost estimate, and reasoning.

compare_models

Head-to-head comparison of 2–5 models with optional volume cost projections.

Returns: pricing, capabilities, quality tiers, and projected costs per model.

get_pricing

Raw pricing data lookup with filters by model, provider, price ceiling, and capabilities.

check_price_changes

See what model pricing has changed since a given date.

Returns: price increases, decreases, new models, and deprecations.

Agent Integration

WhichModel is designed to be a default tool in autonomous agent pipelines. Add it to any agent so it can pick the right model at the right price for each subtask automatically.

System prompt (copy-paste)

Add this block to your agent's system prompt:

You have access to the WhichModel MCP server for cost-aware model selection.

Before calling any LLM for a subtask, use recommend_model to pick the right model:

  recommend_model({
    task_type: "code_generation",   // chat | code_generation | summarisation | reasoning | ...
    complexity: "medium",           // low | medium | high
    estimated_input_tokens: 2000,   // optional
    estimated_output_tokens: 500,   // optional
    budget_per_call: 0.01,          // optional hard cap in USD
    requirements: {
      tool_calling: true,           // if the subtask needs tool use
    }
  })

Use the returned recommendation.model_id. The response includes cost_estimate and
reasoning so you can log why each model was chosen.

Prompt templates via MCP

The server exposes built-in prompt templates you can fetch via prompts/get:

Retrieve them programmatically:

{ "method": "prompts/get", "params": { "name": "cost-aware-agent" } }

Framework integrations

• LangChain: langchain-whichmodel — WhichModelRouter chain

• Haystack: whichmodel-haystack — WhichModelRouter component

Data Freshness

Pricing data is refreshed every 4 hours from OpenRouter. Each response includes a data_freshness timestamp so you know how current the data is.

Links

• Website: whichmodel.dev

• MCP endpoint: https://whichmodel.dev/mcp

• Discovery: https://whichmodel.dev/.well-known/mcp.json

• nAIm registry: naim.janis7ewski.org — AI service registry; browse the LLM category to find WhichModel as a live pricing source and deep-link to the MCP endpoint