Ai Token Counter

Last 30 days

Uptime

100%

Response time

89 ms typical, 89 ms slowest 5%

Last check

2 h ago

Next check

in 4 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "ai-token-counter": {
      "type": "http",
      "url": "https://api.lazy-mac.com/ai-token-counter/mcp"
    }
  }
}

4 tools

• count_tokens

  Count tokens for a text string or chat messages array for any supported AI model (GPT-4o, Claude, Gemini, Mistral, Llama).

• estimate_cost

  Estimate the cost of an AI API call given model and token counts or text. Returns input/output/total cost and optional monthly projection.

• get_model_pricing

  Get input/output pricing per 1M tokens for a specific AI model.

• list_models

  List all supported AI models with their pricing and context windows.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks