# OpenRouter LLM Pricing, Token Limits & MCP Server Registry (`deepaksheoran172/openrouter-mcp-registry`) Actor
Live index of OpenRouter LLM token pricing, context windows, and Model Context Protocol (MCP) servers. Built for AI FinOps, model routing, and agentic tool discovery.
- **URL**: https://apify.com/deepaksheoran172/openrouter-mcp-registry.md
- **Developed by:** [Deepak Sheoran](https://apify.com/deepaksheoran172) (community)
- **Categories:** AI, Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet
## Pricing
from $10.00 / 1,000 openrouter & mcp registry queries
This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event
## What's an Apify Actor?
An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.
## How to integrate an Actor?
If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.
For examples already wired to this Actor's own input schema, see the [API](#api) section below.
Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).
# README
## 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).**
[](https://apify.com/deepaksheoran172/openrouter-mcp-registry)
[-green)](#cost-anchoring--pricing)
[](#fair-execution-guarantee)
[](https://mcp.apify.com/?actors=deepaksheoran172/openrouter-mcp-registry)
***
### ⚡ 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:
```json
{
"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:**
```json
{
"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.
[-blue?style=for-the-badge\&logo=apify)](https://apify.com/deepaksheoran172/openrouter-mcp-registry)
# Changelog
This Actor's version history is a separate document: https://apify.com/deepaksheoran172/openrouter-mcp-registry/changelog.md
# Actor input Schema
## `mode` (type: `string`):
Choose whether to index OpenRouter AI models catalog, MCP server tools registry, or both.
## `free_only` (type: `boolean`):
Filter models to only 100% free models ($0/1M prompt and completion). For MCP, filters to zero-auth servers.
## `multimodal_only` (type: `boolean`):
Filter models to only vision/multimodal capable models.
## `min_context` (type: `integer`):
Minimum token context window (e.g. 32000, 128000, 200000).
## Actor input object example
```json
{
"mode": "both",
"free_only": false,
"multimodal_only": false,
"min_context": 0
}
```
# Actor output Schema
## `results` (type: `string`):
No description
# API
You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.
## JavaScript example
```javascript
import { ApifyClient } from 'apify-client';
// Initialize the ApifyClient with your Apify API token
// Replace the '' with your token
const client = new ApifyClient({
token: '',
});
// Prepare Actor input
const input = {
"mode": "both",
"free_only": false,
"multimodal_only": false,
"min_context": 0
};
// Run the Actor and wait for it to finish
const run = await client.actor("deepaksheoran172/openrouter-mcp-registry").call(input);
// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
console.dir(item);
});
// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs
```
## Python example
```python
from apify_client import ApifyClient
# Initialize the ApifyClient with your Apify API token
# Replace '' with your token.
client = ApifyClient("")
# Prepare the Actor input
run_input = {
"mode": "both",
"free_only": False,
"multimodal_only": False,
"min_context": 0,
}
# Run the Actor and wait for it to finish
run = client.actor("deepaksheoran172/openrouter-mcp-registry").call(run_input=run_input)
# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
print(item)
# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start
```
## CLI example
```bash
echo '{
"mode": "both",
"free_only": false,
"multimodal_only": false,
"min_context": 0
}' |
apify call deepaksheoran172/openrouter-mcp-registry --silent --output-dataset
```
## MCP server setup
```json
{
"mcpServers": {
"apify": {
"type": "http",
"url": "https://mcp.apify.com/?tools=fetch-actor-details,deepaksheoran172/openrouter-mcp-registry"
}
}
}
```
The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).
## OpenAPI specification
Download the OpenAPI definition: https://api.apify.com/v2/actors/jwu7PurBv0MV2JU1s/builds/B6Xq7phJlkGWcVowl/openapi.json