Sync live LLM token rates and Model Context Protocol servers programmatically

OpenRouter Models & MCP Tool Registry Index — Real-Time AI Gateway Intelligence

Stop Paying $200–$500/Month for Static AI Model Observability SaaS. Query 450+ Live OpenRouter Models ($/1M Pricing, Free Tiers, Context Windows) & Curated MCP Servers for $0.01 Base Fee ($10 / 1,000 runs).

---

⚡ The Pain vs. Instant Relief

AI engineering agencies and autonomous agent developers waste engineering hours manually tracking model releases, price changes, and MCP compatibility:

• The Catastrophic Cost of Blind AI Routing: Hardcoding outdated LLM pricing tables leads to catastrophic budget overruns when running agentic loops. Furthermore, discovering production-ready Model Context Protocol (MCP) tools across fragmented GitHub repos is slow and insecure.
• The 1-Click Solution: Query live pricing, multimodal capabilities, context limits, and 100% free model tiers across 450+ OpenRouter endpoints, paired with a curated index of official Model Context Protocol (MCP) server tools.

---

💰 Cost Anchoring vs. Legacy SaaS

Solution	Cost	Setup Time	Coverage
Enterprise AI Gateway Dashboards	$200 – $500 / month	Days / Complex SDK Integration	Proprietary vendor lock-in
Manual Scraping & Maintenance	$50 / month dev hours	Continuous maintenance	Breaks on upstream JSON schema updates
OpenRouter & MCP Registry	$0.01 per run ($10 / 1,000 runs)	Instant (Zero Setup)	Live OpenRouter API + Vetted MCP Catalog

(Pay-Per-Event Primary Event registry-sync-query assessed at $0.01 upon run start. Secondary per-item event [$0.001/record] is uninvoked by code; entire 450+ model index and MCP registry snapshot delivers under the base fee. Standard platform compute credits apply; Free plan includes $5.00/month).

---

🛡️ Fair-Execution Guarantee

Upstream Fault Isolation Guarantee: If the upstream OpenRouter endpoint is unreachable or yields zero catalog models during execution, this Actor outputs diagnostic error records without silent aborts. You are never left without actionable execution telemetry.

---

🚀 Key Capabilities

• Real-Time Token Pricing: Automatically normalizes raw token fractions into unambiguous USD per 1 Million input and output tokens (pricing_prompt_1m, pricing_completion_1m).
• Free Tier Filtering: Instantly filters models to 100% free models ($0.00 / 1M prompt & completion) for cost-free agent development.
• Multimodal & Context Window Filtering: Filter specifically for vision-capable models with context windows of 32k, 128k, or 1M+ tokens.
• Curated MCP Tool Directory: Indexes official and vetted Model Context Protocol tools with transport modes (stdio, sse), tool counts, and auth requirements.

---

🔌 Plug-and-Play Integrations

1. Claude Desktop & Cursor IDE (MCP Server)

Add dynamic model pricing and MCP discovery directly into your AI coding assistant:

{
  "mcpServers": {
    "openrouter-mcp-registry": {
      "command": "npx",
      "args": ["-y", "@apify/mcp-server", "--actor", "deepaksheoran172/openrouter-mcp-registry"]
    }
  }
}

2. Clay.com HTTP Enrichment

Enrich your AI stack database or benchmark competitor model pricing inside Clay:

• Method: POST
• URL: https://api.apify.com/v2/acts/deepaksheoran172~openrouter-mcp-registry/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN
• Body:

  {
    "mode": "models",
    "free_only": true
  }
  

3. n8n & Make.com Automated Cron

Import our pre-built n8n template (tool4_openrouter_mcp_registry_n8n.json) to monitor model pricing shifts daily and push pricing drops or new LLM releases directly to your dev Discord or Slack channels.

---

📥 Input Parameters & 1-Click Prefill

Pre-filled with working defaults — click "Start" on Apify Store with zero typing:

Parameter	Type	Default	Description
mode	String	both	Fetch both (Models + MCP Tools), models only, or mcp only.
free_only	Boolean	false	When true, returns only 100% free models ($0/1M tokens) and zero-auth MCP tools.
multimodal_only	Boolean	false	When true, filters to only vision/multimodal capable models.
min_context	Integer	0	Minimum token context window (e.g. 32000, 128000).

---

📤 Output Artifacts

1. Dataset: Structured list of models and MCP servers with normalized pricing, capability flags, and source URLs.
2. Key-Value Store: Downloadable JSON and CSV indexes for static offline caching.

---

❓ High-Intent B2B FAQs

Q: Do I need an OpenRouter API key to run this Actor?

A: No. This Actor indexes public model metadata and pricing tables. Zero API keys or tokens are required to fetch the catalog.

Q: How often is the model catalog updated?

A: Live on every execution. When you run the Actor or trigger it via webhook, it makes a real-time call to OpenRouter's live API.

Q: What is an MCP Server?

A: Model Context Protocol (MCP) is an open standard developed by Anthropic allowing AI assistants like Claude and Cursor to safely access external tools, databases, and APIs.

---

🚀 Ready to Query Live AI Models & MCP Tools?

Discover 450+ models with live token pricing and curated MCP tools in seconds:

1. Click Try for free at the top right of this page.
2. Select your filtering mode (both, models, or mcp).
3. View real-time pricing per 1M tokens or export JSON for your autonomous agent pipeline.