# OpenRouter Models Scraper — AI Pricing & Specs | from $1.50/1K (`bovi/openrouter-models-scraper`) Actor

Scrape OpenRouter's full AI model catalog: 300+ models with pricing (prompt/completion/image $/token), context length, modality, provider, per-endpoint breakdown, and supported parameters. Official public API, no access friction.

- **URL**: https://apify.com/bovi/openrouter-models-scraper.md
- **Developed by:** [Vitalii Bondarev](https://apify.com/bovi) (community)
- **Categories:** AI, Developer tools, Automation
- **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 Models Scraper — AI Pricing & Specs | from $1.50/1K

Scrape OpenRouter's full AI model catalog — 300+ models with pricing, context lengths, modalities, provider info, and optional per-endpoint breakdown.

### What you get

| Field | Example |
|-------|---------|
| `model_id` | `openai/gpt-4o` |
| `name` | `OpenAI: GPT-4o` |
| `provider` | `openai` |
| `context_length` | `128000` |
| `pricing_prompt_usd_per_token` | `0.0000025` |
| `pricing_completion_usd_per_token` | `0.00001` |
| `pricing_image_usd_per_token` | (when applicable) |
| `pricing_audio_usd_per_token` | (when applicable) |
| `pricing_web_search_usd` | (per search call) |
| `pricing_input_cache_read_usd_per_token` | (cache pricing) |
| `pricing_internal_reasoning_usd_per_token` | (reasoning models) |
| `modality` | `text+image->text` |
| `input_modalities` | `["text","image","file"]` |
| `tokenizer` | `GPT` |
| `is_free` | `false` |
| `pricing_tier` | `paid` / `free` / `variable` |
| `is_moderated` | `true` |
| `supported_parameters` | full list |
| `endpoints` | per-provider breakdown (optional) |
| `url` | browsable model page link |
| `created_at` | ISO datetime |
| + 16 more fields | see dataset schema |

**39 fields per model**, pay per result.

### Use cases

- **LLM cost comparison**: compare prompt/completion pricing across 57+ providers at once
- **Model discovery**: filter by modality, provider, context length, free vs. paid
- **Pricing monitoring**: track price changes over time (schedule the actor)
- **AI product research**: find which providers support which features (caching, reasoning, vision)
- **Competitive intelligence**: audit the LLM market automatically

### Input

| Parameter | Type | Description |
|-----------|------|-------------|
| `filterText` | string | Case-insensitive substring filter on model id/name/description |
| `includeEndpoints` | boolean | Fetch per-provider endpoint breakdown (one extra API call/model) |
| `maxItems` | integer | Max models to return; 0 = all (~300+) |
| `proxyConfiguration` | proxy | Optional Apify Residential proxy (not required for standard use) |

### Access method

Rung-1 (official public JSON API) — `GET https://openrouter.ai/api/v1/models`. No authentication, no access friction, no proxy required. Extremely reliable.

### Pricing

Pay-per-result (PPE). Charged per model record pushed to the dataset.

| Catalog size | Cost at $1.50/1K |
|---|---|
| Full catalog (~344 models) | ~$0.52 |
| Top 50 models | ~$0.08 |
| Single provider filter | pennies |

# Actor input Schema

## `filterText` (type: `string`):

Case-insensitive substring filter applied to model id, name, or description. Leave blank to return all models. Examples: 'gpt', 'claude', 'free', 'mistral'.

## `includeEndpoints` (type: `boolean`):

When enabled, fetches the /endpoints sub-resource for each model and includes a list of provider endpoints with their individual pricing, uptime, and latency. Adds one extra API call per model — expect slower runs on large catalogs.

## `maxItems` (type: `integer`):

Maximum number of model records to return. Set to 0 (default) for the full catalog (~300+ models). You are charged per model returned.

## `proxyConfiguration` (type: `object`):

Optional. OpenRouter's API is public and does not require a proxy for standard use. Enable Apify Residential proxy only if you encounter rate-limiting on very large runs.

## Actor input object example

```json
{
  "includeEndpoints": false,
  "maxItems": 0,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}
```

# Actor output Schema

## `results` (type: `string`):

Dataset containing Openrouter Models Scraper records (model\_id, name, provider, context\_length, pricing\_prompt\_usd\_per\_token, pricing\_completion\_usd\_per\_token, modality, is\_free, created\_at, scraped\_at, pricing\_image\_usd\_per\_token, pricing\_audio\_usd\_per\_token, pricing\_web\_search\_usd, pricing\_input\_cache\_read\_usd\_per\_token, pricing\_input\_cache\_write\_usd\_per\_token, pricing\_internal\_reasoning\_usd\_per\_token).

# 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 = {
    "maxItems": 0,
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": [
            "RESIDENTIAL"
        ]
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("bovi/openrouter-models-scraper").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 = {
    "maxItems": 0,
    "proxyConfiguration": {
        "useApifyProxy": True,
        "apifyProxyGroups": ["RESIDENTIAL"],
    },
}

# Run the Actor and wait for it to finish
run = client.actor("bovi/openrouter-models-scraper").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 '{
  "maxItems": 0,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}' |
apify call bovi/openrouter-models-scraper --silent --output-dataset

```

## MCP server setup

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

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/lvoICDiSBeKqcw9hr/builds/OqfEzD067y7UFOxAy/openapi.json