# AiGanak LLM Cost

> AiGanak LLM Cost is a free MCP server for ai models and llm tooling. LLM API prices, workload cost estimates and the extra tokens non-English text uses. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** CLI, API
- **Website:** https://aiganak.com/llm-api-pricing/
- **Repository:** https://github.com/aiganak/llm-prices/tree/HEAD/mcp
- **MCP Registry name:** io.github.AiGanak/llm-cost
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Most price lists stop at the per-million-token rate. This server also answers what a given workload will cost, with caching and batch discounts applied, and how much more the same text costs in another language. The README gives the example of asking which model is cheapest for a Tamil support bot, or what 50,000 requests of 6,000 input tokens (4,000 cached) and 500 output tokens cost on two models.

Seven tools cover model listings, single-model pricing (cache writes, long-context surcharges, announced changes and the source page), cost estimates, a cheapest-first comparison across models, a token_tax measure across 22 languages, text cost estimates with script detection and a dated log of price changes. Data comes from the open AiGanak llm-prices repository under CC BY 4.0; the server fetches the latest copy at start-up and falls back to a bundled one when offline. Prices are re-checked weekly against provider pages and token counts re-measured monthly.

No key or account is needed. It runs through npx and needs Node.js 18 or newer.

## Features

- **Workload costing:** Prices N requests with cached input and batch tiers.
- **Cheapest-first comparison:** Prices one workload on every tracked model.
- **Language token tax:** Shows how many more tokens a language uses than English, per model family.
- **Announced changes:** Includes dated future price changes in per-model details.
- **Offline fallback:** Uses a bundled data copy if the live fetch fails.
- **No key required:** Runs locally with no account.

## Good for

- Compare monthly cost of a chat workload across providers
- Check what a December price rise does to your bill
- Estimate cost of the same prompt in Hindi or Japanese
- Find the cheapest model for a long-context job

## Install

### Claude Code (Terminal)

```sh
claude mcp add llm-cost -- npx -y @aiganak/llm-cost-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "llm-cost": {
      "command": "npx",
      "args": [
        "-y",
        "@aiganak/llm-cost-mcp"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "llm-cost": {
      "command": "npx",
      "args": [
        "-y",
        "@aiganak/llm-cost-mcp"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "llm-cost": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@aiganak/llm-cost-mcp"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "llm-cost": {
      "command": "npx",
      "args": [
        "-y",
        "@aiganak/llm-cost-mcp"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "llm-cost": {
      "command": "npx",
      "args": [
        "-y",
        "@aiganak/llm-cost-mcp"
      ]
    }
  }
}
```

## Tools

- `list_models`: Lists current models with standard, cached-input and batch prices per million tokens.
- `get_model_price`: Returns full pricing for one model, including cache writes and announced changes.
- `estimate_cost`: Estimates the cost of N requests on one model.
- `compare_models`: Prices the same workload on every model, cheapest first.
- `token_tax`: Shows how many more tokens a language needs than English per model family.
- `estimate_text_cost`: Estimates tokens and cost for a text in any measured language.
- `price_changes`: Returns a dated log of LLM API price changes.

## FAQ

### Does it need an API key?

No. The README says no API key and no account.

### How current are the prices?

The data repo says prices are checked weekly against each provider's pricing page; the server pulls the latest at start-up.

### Which languages does token tax cover?

22 languages, measured monthly with each provider's official token counter.

### What licence is the data under?

CC BY 4.0, from the AiGanak llm-prices repository.

### Is AiGanak LLM Cost free?

Yes. AiGanak LLM Cost is free to use.

### How do I add AiGanak LLM Cost to Claude Code?

Run this command in your terminal: claude mcp add llm-cost -- npx -y @aiganak/llm-cost-mcp

### What are the best alternatives to AiGanak LLM Cost?

The closest alternatives to AiGanak LLM Cost are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/aiganak-llm-cost
