# LLM Price & Model Change Alerts (Schedule Daily) (`m8forever/ai-model-pricing-tracker`) Actor

Schedule daily LLM price/model change alerts from OpenRouter + LiteLLM. Emits price_up/down, new_model, removed_model, context_change. First run baselines free; later runs bill per change (~$0.005). Optional full catalog query (~$0.10).

- **URL**: https://apify.com/m8forever/ai-model-pricing-tracker.md
- **Developed by:** [Hanxiao Yang](https://apify.com/m8forever) (community)
- **Categories:** AI, Developer tools, Other
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.10 / catalog query

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

## LLM Price & Model Change Alerts (Schedule Daily)

**Keywords:** LLM price change alert, OpenRouter model monitor, LiteLLM price map, GPT Claude Gemini DeepSeek price drop, new model alert, schedule daily AI pricing, token cost per 1M, AI agent tool.

**Schedule this Actor daily** to get a recurring feed of LLM **price moves, new models, removals, and context-length changes**. Built for AI agents, cost dashboards, and procurement that need *alerts*, not a one-shot table.

Sources: **OpenRouter** public models API + open **LiteLLM** price map (provider sites are **not** scraped).

### Recommended: daily monitor (~pennies when quiet)

```json
{
  "mode": "monitor",
  "providers": ["openai", "anthropic", "google", "deepseek"],
  "stateStoreName": "ai-model-pricing-state"
}
```

1. **First scheduled run** writes a baseline to `stateStoreName` and emits one `type=baseline` row (no `change-event` charges).
2. **Later runs** emit only diffs: `price_up`, `price_down`, `new_model`, `removed_model`, `context_change` (~$0.005 each).
3. Keep `stateStoreName` **stable** across the schedule so baselines persist.

Quiet days with no catalog churn ≈ actor-start only (~$0.00005). That is the subscription feel.

### One-shot catalog (~$0.10)

```json
{
  "mode": "catalog",
  "sources": ["openrouter", "litellm"]
}
```

### Input

| Field | Meaning |
|---|---|
| `mode` | `monitor` (schedule), `catalog` (one-shot), `both`. Overrides toggles when set. |
| `sources` | `openrouter`, `litellm` (default both) |
| `providers` / `search` / `modality` / `maxInputPricePer1M` | filters (also scope change detection) |
| `emitCatalog` / `detectChanges` | used only when `mode` is empty |
| `stateStoreName` | KV baseline name — **keep stable on schedules** |
| `includeArxiv` / `includeHfTrending` / `maxItems` | free add-ons |

### Output rows

- `type=baseline` — first monitor run (key count, filters)
- `type=change` — `event` in `price_up|price_down|new_model|removed_model|context_change`
- `type=model` — catalog row (when catalog/both)
- `type=arxiv_paper` / `type=hf_trending_model` — optional

### Pricing (pay per event)

- **Catalog query** — $0.10 per run that returns catalog rows (primary; whole catalog, not per-model)
- **Change event** — $0.005 per change row
- Actor start ~$0.00005; add-on / baseline rows free

Typical daily OpenAI+Anthropic watch: ~$0.00–$0.05/day when the catalog is stable; spikes only when models actually change.

### Sources & compliance

OpenRouter public models API; LiteLLM price map (MIT); arXiv metadata (CC0 attribution); Hugging Face Hub public API. Prices may differ from provider list prices — verify before buying. Not affiliated with any provider.

### Use cases & scheduling

- **Daily LLM price change alerts** — `mode: monitor` on a daily schedule; quiet days cost almost nothing, changes arrive as rows you can webhook to Slack/email.
- **New model alerts** — get `new_model` / `removed_model` events for OpenAI, Anthropic, Google, DeepSeek and others listed on OpenRouter.
- **Find the cheapest model** — `mode: catalog` with `maxInputPricePer1M` to list models under a price cap.
- **Cost dashboards & procurement** — normalized price per 1M input/output tokens and context length.
- **AI agent tool** — give an agent a fresh price table instead of stale training data.

Tip: create an [Apify Schedule](https://docs.apify.com/platform/schedules) for the Actor or one of the tasks below to turn it into a recurring monitor, and add a webhook/integration to get results in Slack, email or Google Sheets.

### Ready-made example tasks

One-click, pre-filled inputs you can run or copy:

- [openai-anthropic-price-monitor](https://apify.com/m8forever/ai-model-pricing-tracker/tasks/openai-anthropic-price-monitor)
- [daily-llm-price-change-alerts](https://apify.com/m8forever/ai-model-pricing-tracker/tasks/daily-llm-price-change-alerts)
- [cheap-llm-under-1-dollar-per-million](https://apify.com/m8forever/ai-model-pricing-tracker/tasks/cheap-llm-under-1-dollar-per-million)

### FAQ

**Do you scrape provider websites?**\
No. Sources are the OpenRouter public models API and the open-source LiteLLM price map.

**Why didn't my first monitor run return changes?**\
The first run stores a baseline (`type=baseline`). Changes appear from the second scheduled run on — keep `stateStoreName` stable.

**Are prices exactly the provider's list price?**\
Usually close, but OpenRouter/LiteLLM may differ. Verify before buying.

**How often should I schedule it?**\
Daily is enough for most teams; hourly is possible if you need faster alerts.

# Actor input Schema

## `mode` (type: `string`):

monitor = change alerts only (schedule this daily; first run baselines, no change charges). catalog = full price table (~$0.10). both = catalog + changes. Leave empty to use emitCatalog/detectChanges toggles.

## `sources` (type: `array`):

Data sources: openrouter, litellm

## `providers` (type: `array`):

Limit catalog and change detection to these providers, e.g. openai, anthropic, google, deepseek

## `search` (type: `string`):

Substring filter on model id / display name

## `modality` (type: `string`):

Require this input modality: text, image, audio, video, or file

## `maxInputPricePer1M` (type: `integer`):

Keep models whose input price is at most this USD per 1M tokens

## `emitCatalog` (type: `boolean`):

Used when mode is empty. true charges catalog-query (~$0.10). Prefer mode=monitor for schedules.

## `detectChanges` (type: `boolean`):

Used when mode is empty. Compares to stateStoreName snapshot.

## `stateStoreName` (type: `string`):

Named KV store for baseline. Keep the SAME name across scheduled runs.

## `includeArxiv` (type: `boolean`):

Optional add-on: push recent arXiv AI papers (free)

## `arxivCategories` (type: `array`):

arXiv category codes when includeArxiv is true

## `includeHfTrending` (type: `boolean`):

Optional add-on: push HF trending models (free)

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

Max arXiv / HF add-on rows

## Actor input object example

```json
{
  "sources": [
    "openrouter",
    "litellm"
  ],
  "emitCatalog": true,
  "detectChanges": true,
  "stateStoreName": "ai-model-pricing-state",
  "includeArxiv": false,
  "arxivCategories": [
    "cs.CL",
    "cs.LG",
    "cs.AI"
  ],
  "includeHfTrending": false,
  "maxItems": 25
}
```

# 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 '<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("m8forever/ai-model-pricing-tracker").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("m8forever/ai-model-pricing-tracker").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 m8forever/ai-model-pricing-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,m8forever/ai-model-pricing-tracker"
        }
    }
}
```

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/QLztqdFLZpXySRf53/builds/sulHsQ790UAgvt2r8/openapi.json