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)

{
  "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)

{
  "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 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
• daily-llm-price-change-alerts
• 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.