Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use LLM Token Counter with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Calculate exact and estimated token counts for GPT-4, GPT-4o, Claude, and Llama models.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 2 capabilities

The complete LLM Token Counter capability set.

These are the exact actions your AI can choose when you ask it to work with LLM Token Counter.

Capability set01 / 01

01-02

2 capabilities in this set.

Part of 2 available through LLM Token Counter.

  1. 01

    Token count

    Calculate character, word, and estimated token counts

  2. 02

    Analyze complexity

    Analyze text complexity and punctuation diversity

Observed, not estimated

687ms average. Fast in production.

LLM Token Counter is checked daily against the live service.

Daily averagePeak 934ms
Aug 20Today
Fastest day
507ms
Slowest day
934ms
14-day trend
Slowing+18%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 2 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of LLM Token Counter, so you can see the experience inside your AI.

It does not authenticate your account with LLM Token Counter. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

LLM Token Counter Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_zsoth4tZ4xpY6SYfMN3vLiFJZi46jUAy7QtwPENf/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — LLM Token Counter capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "llm-token-counter-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_zsoth4tZ4xpY6SYfMN3vLiFJZi46jUAy7QtwPENf/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions LLM Token Counter owners ask.

  • 01

    Which LLM tokenizers are supported?

    The server provides exact counts for cl100k_base (GPT-4) and o200k_base (GPT-4o), as well as approximations for Claude and SentencePiece-based models like Llama.

  • 02

    How does the capability handle chat message overhead?

    The calculate_chat_overhead logic accounts for the hidden structural tokens (like role indicators and delimiters) added by API templates to ensure your total token count is accurate.

  • 03

    Can I use this for text truncation?

    Yes, you can use the find_truncation_point capability to determine exactly where to trim your input text to stay within a specific token budget.

Explore

More in Developer Tools

Suggestions