Tokencost Mcp Server

Name: Tokencost Mcp Server
Author: ankit-aglawe

@ankit-aglawe

About Tokencost Mcp Server

An MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers.

#llm-pricing #token-cost #ai-models #cost-calculator #openai #anthropic #claude #gemini #gpt #model-comparison #token-counter #api-pricing #deepseek #llama #mistral

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

Get pricing for a specific model

Side-by-side pricing comparison

Calculate cost for given token counts

Find cheapest models with filters

List all available models

List all providers with pricing ranges

Overview

What is Tokencost Mcp Server?

Tokencost Mcp Server is an MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers. It allows AI assistants to query, compare, and estimate costs for models from OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek, and more.

How to use Tokencost Mcp Server?

Install by adding the server to your MCP config with npx -y tokencost-mcp-server as the command, or clone the repository and run from source. Use tools like tokencost_get_model_pricing, tokencost_compare_models, tokencost_estimate_cost, tokencost_find_cheapest, tokencost_list_models, and tokencost_list_providers.

Key features of Tokencost Mcp Server

Real-time pricing for 60+ models across 15 providers
Dedicated MCP tools for pricing queries and comparisons
Cost estimation for given input/output token counts
Filtered search for cheapest models by context length
Up-to-date pricing tracked by the TokenCost team
Free and open-source deployment via npx

Use cases of Tokencost Mcp Server

Query pricing for a specific LLM model by name
Compare side-by-side pricing of multiple models
Estimate processing cost for a known token count
Find the cheapest model meeting a minimum context window
List all available models or providers with price ranges

FAQ from Tokencost Mcp Server

What are the runtime requirements?

Node.js and npm are required; the server runs via npx or from a local clone.

How is pricing data kept current?

The TokenCost team monitors official provider announcements and updates pricing within days of changes.

Which providers are supported?

OpenAI, Anthropic, Google, xAI, Meta, Mistral, DeepSeek, Alibaba (Qwen), Amazon (Nova), NVIDIA, Cohere, Perplexity, Moonshot (Kimi), Zhipu (GLM), and MiniMax.