MCP server

Tokenscost MCP Server

Free — no paid plan required. Every MCP tool works on the Free plan with no account and no API key.

Endpoint

https://jbfijhqnmextfsdtikox.supabase.co/functions/v1/mcp (streamable HTTP)

npx command

npx -y mcp-remote https://jbfijhqnmextfsdtikox.supabase.co/functions/v1/mcp

Claude Desktop

Add to claude_desktop_config.json

{
  "mcpServers": {
    "tokenscost": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://jbfijhqnmextfsdtikox.supabase.co/functions/v1/mcp"]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "tokenscost": {
      "url": "https://jbfijhqnmextfsdtikox.supabase.co/functions/v1/mcp"
    }
  }
}

Claude Code

claude mcp add --transport http tokenscost https://jbfijhqnmextfsdtikox.supabase.co/functions/v1/mcp

Tools exposed

  • search_models — Search priced models by name or ID, optionally filtered to one provider.
  • get_model_price — Input, output and cached-input prices (USD per 1M tokens), context window and last sync date for one model.
  • compare_models — Side-by-side prices for 2–10 models plus the cost of an optional input/output token workload.
  • list_providers — Every provider in the dataset with its priced and listed model counts.
  • cheapest_for — Rank the cheapest models for a given number of input and output tokens, with optional minimum context and provider filters.

API key

No API key or account is needed. Every tool is free and read-only.

MCP server limits: 60 requests per hour per IP address with no key, or 1,000 requests per hour with an optional free API key sent as Authorization: Bearer <key>. These are separate from REST API limits. Get a free key at https://tokenscost.com/signup.

Last updated: · Source: Pricing dataset · Methodology

Frequently asked questions

How are token costs calculated?

Multiply input tokens by the input rate and output tokens by the output rate, add the two amounts and divide by 1,000,000. A standard request example uses 1,000 input and 500 output tokens. Monthly budgets multiply the result by request volume; taxes, hidden reasoning tokens, tools and tier surcharges can add costs.

Which recorded model has the lowest request cost?

LFM 2.2 6b by Liquid AI costs $0.00002 for the standard request, with $0.01 input and $0.02 output per million tokens. This price ranking does not establish quality equivalence; verify task success and context requirements.

Can cached and batch discounts be combined?

Only recorded rates are used. Cached input can have cache-write or storage charges, while batch rates apply only to eligible asynchronous jobs. We do not automatically stack the discounts or treat an absent rate as zero. Check the linked provider source before budgeting.

How current is the public dataset?

The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. It contains 1,026 priced models across 124 providers, last updated 2026-10-31. Directory entries are counted separately. A synchronization date is not proof of independent verification.