# OpenRouter LLM Intelligence & Model Pricing (`primesieve/openrouter-llm-intel`) Actor

Live intelligence on 440+ LLMs on OpenRouter. Normalized per-1M token pricing, context windows, free models, multi-modal specs, and market analysis.

- **URL**: https://apify.com/primesieve/openrouter-llm-intel.md
- **Developed by:** [Prime Sieve](https://apify.com/primesieve) (community)
- **Categories:** AI, Developer tools, Business
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## 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 LLM Intelligence, Pricing Matrix & Benchmark Analytics

**OpenRouter LLM Intelligence** is an enterprise-grade AI model pricing matrix, context leaderboard, and capability scraper designed by **Prime Sieve**.

It pulls live real-time intelligence on **440+ LLMs & Multi-modal models** hosted on OpenRouter — including DeepSeek, Anthropic Claude, OpenAI GPT-4.5/o3, Google Gemini 2.0/Flash, Meta Llama 3.3, Mistral, and open-source fine-tunes.

***

### ⚡ What Data You Get

For every single model, this Actor extracts and normalizes:

- **Identifier & Creator**: `anthropic/claude-3.7-sonnet`, `deepseek/deepseek-r1`, `openai/gpt-4.5-preview`, etc.
- **Normalized Pricing**: Exact USD cost per **1 Million Input Tokens** and **1 Million Output Tokens** (no scientific notation math required).
- **Context Window**: Total token capacity (from 8K up to 2M tokens).
- **Modalities**: `text->text`, `text+image->text`, audio, and embeddings.
- **Free Tier Detection**: Flags `:free` and $0/1M token models for cost-free development.
- **Market Intelligence Summary**: Automated breakdown of median token costs across the AI industry, top providers by model count, and top largest context window leaders.

***

### 💡 Use Cases

1. **AI Cost Optimization**: Continuously monitor price drops and token arbitrage across competitive providers.
2. **Dynamic LLM Routers**: Feed live price & context specs into custom agent routers and fallback systems.
3. **AI Industry Research**: Benchmark model pricing curves and track the rapid commoditization of frontier tokens.
4. **Developer Tooling**: Build auto-updating model pickers and cost estimation calculators for SaaS apps.

***

### ⚙️ Input Parameters

| Parameter | Type | Default | Description |
|---|---|---|---|
| `searchQuery` | String | `""` | Filter by keyword (e.g. `deepseek`, `claude`, `reasoning`, `vision`) |
| `providerFilter` | String | `"all"` | Filter by creator slug (e.g. `anthropic`, `openai`, `deepseek`, `meta-llama`) |
| `freeOnly` | Boolean | `false` | Only return $0 / free tier models |
| `filterModality` | String | `"all"` | Filter by modality (`text->text`, `text+image->text`) |
| `minContextLength` | Integer | `0` | Minimum token context window (e.g. `128000`) |
| `maxPromptPricePerMillion`| Number | `0` | Max input price ($ / 1M tokens) |
| `sortBy` | String | `"promptPriceAsc"` | Sort by price, context length, or name |
| `includeMarketSummary` | Boolean | `true` | Include an aggregate industry summary item |
| `maxResults` | Integer | `500` | Max records to output (0 for unlimited) |

***

### 📬 Stay Connected — Remote Signal Newsletter

Want to track autonomous agents, zero-infrastructure scrapers, and remote AI developer intelligence?

👉 **Subscribe to the Remote Signal Newsletter**: <https://remotesignal.substack.com>

*Weekly intelligence on building high-agency autonomous tools, AI engineering workflows, and remote tech signals. Powered by **Prime Sieve**.*

# Actor input Schema

## `filterModality` (type: `string`):

Filter models by input/output modality (e.g. text->text, text+image->text, all)

## `providerFilter` (type: `string`):

Filter models by creator/provider slug (e.g. anthropic, openai, meta-llama, google, mistralai, deepseek, or all)

## `freeOnly` (type: `boolean`):

Only return models with $0 cost or :free variant endpoints

## `searchQuery` (type: `string`):

Keyword search across model names, descriptions, and IDs (e.g. 'claude 3.7', 'deepseek r1', 'vision', 'reasoning')

## `minContextLength` (type: `integer`):

Filter out models with context windows smaller than this number (e.g. 32000, 128000, 1000000)

## `maxPromptPricePerMillion` (type: `number`):

Maximum allowed cost per 1M input tokens in USD (e.g. 5.0). Set to 0 or leave empty for no limit.

## `sortBy` (type: `string`):

Sort order of the parsed models

## `includeMarketSummary` (type: `boolean`):

Emits a summary record with median pricing, top providers, cheapest reasoning models, and largest context window leaders

## `maxResults` (type: `integer`):

Maximum number of model items to output (0 for all matching models)

## Actor input object example

```json
{
  "filterModality": "all",
  "providerFilter": "all",
  "freeOnly": false,
  "minContextLength": 0,
  "maxPromptPricePerMillion": 0,
  "sortBy": "promptPriceAsc",
  "includeMarketSummary": true,
  "maxResults": 500
}
```

# Actor output Schema

## `_type` (type: `string`):

Record type: 'model' or 'summary'

## `id` (type: `string`):

Unique OpenRouter model identifier (e.g. anthropic/claude-3.7-sonnet)

## `name` (type: `string`):

Human-readable model name

## `creator` (type: `string`):

Model creator / organization

## `contextLength` (type: `string`):

Maximum context length in tokens

## `promptPricePerMillion` (type: `string`):

Cost per 1 million input tokens

## `completionPricePerMillion` (type: `string`):

Cost per 1 million output tokens

## `isFree` (type: `string`):

True if model is free to run

## `modalities` (type: `string`):

Input and output modalities supported

## `openRouterUrl` (type: `string`):

Link to model page

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("primesieve/openrouter-llm-intel").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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("primesieve/openrouter-llm-intel").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 '{}' |
apify call primesieve/openrouter-llm-intel --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,primesieve/openrouter-llm-intel"
        }
    }
}
```

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 <APIFY_API_TOKEN>` 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/YcLY9cfcvQNt9bYMD/builds/clFQnauofIdh3lPwM/openapi.json