Skip to content
MCP server

Open Weights Index

Daily LLM price ladder and release timeline for AI models, served over MCP

Install
Platforms
API
Runs
Remotely
Version
1.0.0
Listing updated
today

About Open Weights Index

Open Weights Index is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

The index tracks what a million tokens costs across more than 400 models drawn from the OpenRouter catalogue, refreshed daily. Alongside the price ladder it keeps a timeline of 57 model releases going back to ChatGPT, so you can see when particular models arrived and how the field has moved.

It also reports market share across three kinds of model use: routed traffic, enterprise adoption and open-model use. Comparisons are drawn between China and the US and Canada, and between open-weight and closed models. The MCP registry entry describes monthly cost estimates per workload, which turns raw token prices into a rough spend figure for a given job.

The server is aimed at developers and analysts who want current model pricing or market context inside an AI client rather than scraping a web page. The website and registry entry do not list the individual tools the server exposes or any licence terms.

Install

Run in a terminal

claude mcp add --transport http open-weights https://open-weights.forj.workers.dev/mcp

Add to Settings → Connectors → Add custom connector

https://open-weights.forj.workers.dev/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "open-weights": {
      "url": "https://open-weights.forj.workers.dev/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "open-weights": {
      "type": "http",
      "url": "https://open-weights.forj.workers.dev/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "open-weights": {
      "serverUrl": "https://open-weights.forj.workers.dev/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "open-weights": {
      "type": "http",
      "url": "https://open-weights.forj.workers.dev/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Daily token price ladder
Lists per-million-token prices for over 400 models from the OpenRouter catalogue, updated each day.
Model release timeline
Tracks 57 model releases since ChatGPT launched, showing when each one came out.
Monthly workload cost estimates
Estimates monthly spend for a given workload, according to the MCP registry entry.
Market share breakdown
Shows share across routed, enterprise and open model use.
Regional and open-closed comparisons
Compares models from China with those from the US and Canada, and open against closed models.
Remote MCP endpoint
Available over streamable HTTP at a hosted MCP URL, with no local package to install.

Good for

  • Comparing per-token prices of candidate models before choosing one for an application
  • Estimating the monthly cost of a workload across different models
  • Tracking when new models were released and how the market has shifted
  • Giving an AI assistant live access to current LLM pricing data

Open Weights Index FAQ

How often is the price data updated?

The website describes a daily price ladder drawn from the OpenRouter catalogue.

Which transport does the MCP server use?

The registry entry lists a remote streamable-http endpoint and no local packages.

Where does the pricing data come from?

The price ladder is built from the OpenRouter catalogue.

How do I add Open Weights Index to Claude Code?

Run this command in your terminal: claude mcp add --transport http open-weights https://open-weights.forj.workers.dev/mcp

What are the best alternatives to Open Weights Index?

The closest alternatives to Open Weights Index are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers

Alternatives to Open Weights Index

  1. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  2. signafAIde

    MCP server

    Local MCP server to set up, verify and check coverage of signed agent action records

    Runs locally
    • 5 tools
    • Freemium
    • Security
  3. Toolkien

    MCP server

    One MCP gateway for all your MCP servers, with code mode, permissions and audit

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • AI models and LLM tooling
  4. Lugh

    MCP server

    Write, check and dry-run Lugh agent programs with policy, budgets and approvals

    Runs locally
    • 5 tools
    • Open source
    • AI models and LLM tooling
  5. HypePaper

    MCP server

    Research papers, benchmarks, citations and topic experts for AI assistants

    • 58 tools
    • Remote
    • Freemium
    • AI models and LLM tooling