MCP ServerSTDIOOfficialv1.1.0

AI-Cost-CLI MCP Server

Calculate and compare costs across 29 AI models for text, image, video, and audio APIs. Helps developers estimate spending and choose cost-effective models for their projects.

io.github.ufhouck/aicost-cli

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the AI-Cost-CLI MCP server does

How models use it and what it is built for.

Calculate and compare costs across 29 AI models for text, image, video, and audio APIs. Helps developers estimate spending and choose cost-effective models for their projects.

Connect to AI-Cost-CLI

Local install — runs as a subprocess.

uvx aicost-cli==1.1.0

Resources

Where to find authoritative docs and source for AI-Cost-CLI.

Example prompts for AI-Cost-CLI

Paste any of these into Agent Studio after connecting AI-Cost-CLI.

  • What's the cost difference between GPT-4 and Claude 3 for processing 10,000 tokens?
  • Compare pricing for image generation across DALL-E, Midjourney, and Stable Diffusion
  • Calculate total API costs for a project using video transcription and text generation
  • Which audio model offers the best price-to-performance ratio for speech-to-text?

AI-Cost-CLI MCP server — FAQ

Common questions about connecting and running AI-Cost-CLI.

  • What AI models does aicost-cli support?

    The server covers 29 models across text, image, video, and audio categories. It includes popular options like GPT-4, Claude, DALL-E, and others. Check the documentation for the complete current list.

  • How do I install and run aicost-cli?

    Install via `uvx aicost-cli@1.1.0`. The server runs over stdio transport, making it compatible with MCP clients. No additional configuration is required to get started.

  • Can aicost-cli help me choose between models?

    Yes, the server includes a recommender feature that compares costs and helps you select cost-effective models for your use case based on your requirements.

  • Does aicost-cli require API keys to calculate costs?

    Cost calculation uses publicly available pricing data, so you don't need API keys to estimate expenses. However, actual usage tracking may require integration with your API providers.

  • How often are the pricing rates updated?

    Refer to the project repository for information on pricing update frequency. AI model pricing changes regularly, so check the docs to understand how current the data is.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio

Related servers

More on MCP Playground