ai-cost-calculator-api
Enables AI cost calculation, comparison, and optimization across major providers like Anthropic, OpenAI, Google, Meta, and Mistral. Supports cost estimation, budget-aware model finding, and token estimation through a simple API and MCP integration.
README
<p align="center"><img src="logo.png" width="120" alt="logo"></p>
AI Cost Calculator API
⭐ Building in public from $0 MRR. Star if you want to follow the journey — lazymac-mcp (42 tools, one MCP install) · lazymac-k-mcp (Korean wedge) · lazymac-sdk (TS client) · api.lazy-mac.com · Pro $29/mo.
🚀 Want all 42 lazymac tools through ONE MCP install?
npx -y @lazymac/mcp· Pro $29/mo for unlimited calls.
The world's first AI model cost estimation API.
Calculate, compare, and optimize your AI spending across every major provider -- Anthropic, OpenAI, Google, Meta, and Mistral -- with a single API call.
No other product does this. Every AI startup, developer, and enterprise building on LLMs needs to understand and control their costs. This API makes that trivial.
Why This Exists
- There is no unified API to calculate AI model costs across providers.
- Pricing pages are scattered, inconsistent, and change frequently.
- Developers waste hours building internal cost-tracking spreadsheets.
- Finance teams have no programmatic way to forecast AI budgets.
This API solves all of that.
Features
- Instant cost calculation for any model + token count
- Monthly cost estimation from daily usage patterns
- Cross-provider comparison sorted cheapest-first with savings analysis
- Budget-aware model finder -- find the best model under your cost ceiling
- Token estimation from raw text
- Batch vs standard pricing where providers offer discounts
- MCP server for integration with AI assistants (Claude, etc.)
- 15 models across 5 providers, updated regularly
Quick Start
npm install
npm start
# Server runs on http://localhost:5000
API Endpoints
Calculate Cost
curl -X POST http://localhost:5000/api/v1/calculate \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-4","input_tokens":1000,"output_tokens":500}'
Monthly Estimate
curl -X POST http://localhost:5000/api/v1/estimate \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4o","requests_per_day":1000,"avg_input_tokens":2000,"avg_output_tokens":500}'
Compare All Models
curl -X POST http://localhost:5000/api/v1/compare \
-H "Content-Type: application/json" \
-d '{"input_tokens":5000,"output_tokens":1000}'
Find Cheapest Model
curl "http://localhost:5000/api/v1/cheapest?input_tokens=1000&output_tokens=500&budget=0.01"
List All Models
curl http://localhost:5000/api/v1/models
List by Provider
curl http://localhost:5000/api/v1/models/anthropic
Estimate Tokens from Text
curl -X POST http://localhost:5000/api/v1/tokens \
-H "Content-Type: application/json" \
-d '{"text":"How much would it cost to process this sentence?"}'
MCP Server
Use with Claude Desktop or any MCP-compatible client:
{
"mcpServers": {
"ai-cost-calculator": {
"command": "node",
"args": ["src/mcp-server.js"]
}
}
}
Supported Models
| Provider | Model | Input $/MTok | Output $/MTok |
|---|---|---|---|
| Anthropic | Claude Opus 4 | $15.00 | $75.00 |
| Anthropic | Claude Sonnet 4 | $3.00 | $15.00 |
| Anthropic | Claude Haiku 3.5 | $0.80 | $4.00 |
| OpenAI | GPT-4o | $2.50 | $10.00 |
| OpenAI | GPT-4o Mini | $0.15 | $0.60 |
| OpenAI | GPT-4 Turbo | $10.00 | $30.00 |
| OpenAI | o1 | $15.00 | $60.00 |
| OpenAI | o3-mini | $1.10 | $4.40 |
| Gemini 2.0 Flash | $0.10 | $0.40 | |
| Gemini 1.5 Pro | $1.25 | $5.00 | |
| Meta | Llama 3.1 405B | $3.00 | $3.00 |
| Meta | Llama 3.1 70B | $0.70 | $0.80 |
| Mistral | Mistral Large | $2.00 | $6.00 |
| Mistral | Mistral Small | $0.20 | $0.60 |
Docker
docker build -t ai-cost-calculator-api .
docker run -p 5000:5000 ai-cost-calculator-api
License
MIT
Related projects
- 🧰 lazymac-mcp — Single MCP server exposing 15+ lazymac APIs as tools for Claude Code, Cursor, Windsurf
- ✅ lazymac-api-healthcheck-action — Free GitHub Action to ping any URL on a cron and fail on non-2xx
- 🌐 api.lazy-mac.com — 36+ developer APIs, REST + MCP, free tier
<sub>💡 Host your own stack? <a href="https://m.do.co/c/c8c07a9d3273">Get $200 DigitalOcean credit</a> via lazymac referral link.</sub>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.