LLM API Pricing Scraper — OpenRouter Prices & Changes
Pricing
Pay per event
LLM API Pricing Scraper — OpenRouter Prices & Changes
LLM API prices for 450+ models (OpenAI, Anthropic, Google, DeepSeek, Mistral, Qwen) from OpenRouter: input/output $ per 1M tokens, cache price, context length. Flags new models and price changes since your last run. $1 per 1,000 models.
Pricing
Pay per event
Rating
0.0
(0)
Developer
Agent Data Co
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
16 days ago
Last modified
Categories
Features
Share
LLM API Pricing Scraper — OpenRouter Model Prices & Price Changes
Get LLM API pricing for 450+ models listed on OpenRouter (OpenAI, Anthropic, Google, DeepSeek, Meta, Mistral, xAI, Qwen, Moonshot and more): input and output price per 1M tokens, cached-input price, context length, max output tokens, modalities and tool support. Every run is compared with your previous run, so the Actor also tells you which models are new, which had a price change (with the old price) and which were removed.
Price: $1.00 per 1,000 models + $0.001 per run. A full catalogue of every model costs about $0.45; a daily "what changed" run usually costs a few cents.
Use cases
- Price-change alerts: schedule a daily run with
onlyChanged: trueand get a Slack, email or webhook message whenever a provider cuts or raises a price. - AI cost dashboards and model routers: keep your internal price table in sync with the market instead of hand-editing it.
- Comparison sites and directories: refresh LLM price pages, calculators and "cheapest model" lists every day.
- Analysts and investors: build a price history per model and track how fast token prices fall.
- AI agents: call it from the Apify MCP server so your agent can answer "which model is cheapest for this job?" with today's prices.
What does it do?
It reads OpenRouter's public models API, normalises all prices to USD per 1M tokens, and compares the result with the snapshot saved by your last run (kept in a named key-value store). Each row gets a change label: first_snapshot, new_model, price_changed, context_changed or unchanged. Price changes include a previous object with the old input and output prices. Models that disappeared are listed in the REMOVED_MODELS record. No API key, login or proxy is needed. Prices are OpenRouter's listed prices and can differ from prices charged directly by each provider.
Input
| Field | What it does |
|---|---|
providers | Only these providers, e.g. openai, anthropic, google, deepseek |
search | Only models whose ID or name contains this text, e.g. claude |
freeOnly | Only free models |
onlyChanged | Only models that are new or changed since your last run |
stateStoreName | Named key-value store that keeps the snapshot (use a different name per schedule) |
maxItems | Maximum number of models to return (default 1,000) |
Example input (the run the output below comes from):
{"providers": ["deepseek", "openai", "anthropic", "google", "mistralai", "moonshotai", "z-ai", "qwen"],"onlyChanged": true}
Example output
Real items from a run on 2 November 2026, compared with a snapshot from 20 October. That run returned 32 models: 27 price changes and 5 new models.
[{"id": "mistralai/mistral-large-4-0","name": "Mistral: Mistral Large 4","provider": "mistralai","created": "2026-10-06T13:42:02.000Z","contextLength": 1048576,"maxCompletionTokens": 262144,"inputModalities": ["text","image"],"outputModalities": ["text"],"promptUsdPer1M": 0.7,"completionUsdPer1M": 2.1,"cacheReadUsdPer1M": 0.07,"requestUsd": null,"imageUsd": null,"isFree": false,"supportsTools": true,"huggingFaceId": "mistralai/Mistral-Large-4-1T-A52B","description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","change": "price_changed","previous": {"promptUsdPer1M": 0.68,"completionUsdPer1M": 2.09},"_meta": {"actor": "llm-model-pricing-feed","schemaVersion": "1.0","scrapedAt": "2026-11-02T09:44:16.756Z"}},{"id": "openai/gpt-6.1-terra","name": "OpenAI: GPT-6.1 Terra","provider": "openai","created": "2026-10-26T18:13:29.000Z","contextLength": 1050000,"maxCompletionTokens": 128000,"inputModalities": ["file","image","text"],"outputModalities": ["text"],"promptUsdPer1M": 1,"completionUsdPer1M": 5,"cacheReadUsdPer1M": 0.05,"requestUsd": null,"imageUsd": null,"isFree": false,"supportsTools": true,"huggingFaceId": null,"description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","change": "new_model","_meta": {"actor": "llm-model-pricing-feed","schemaVersion": "1.0","scrapedAt": "2026-11-02T09:44:16.536Z"}}]
Export as JSON, CSV, Excel or HTML, or pull the data through the Apify API, webhooks, Make, Zapier, n8n or the Apify MCP server.
How much does it cost?
Pay per event, no subscription:
- $0.001 per run (actor start)
- $0.001 per model returned ($1.00 per 1,000)
Examples: the full catalogue (about 450 models) costs about $0.45. A daily onlyChanged run that finds 10 changes costs $0.011, which is about $0.33 a month. You pay nothing for results on a failed run: if no data is found, the run fails with a clear message instead of returning an empty "success".
Prefer a ready-made table?
Agent Data Co publishes the same data as free, daily-updated LLM API pricing pages by provider and model, with price history and side-by-side comparisons. Use this Actor when you need the raw data in your own tools.
FAQ
Where does the data come from? OpenRouter's public models API (GET https://openrouter.ai/api/v1/models). No authentication and no personal data.
How do I get only changes? Set onlyChanged: true. The first run saves a snapshot and returns everything; later runs return only new and changed models.
Something broke? Open an issue on the Issues tab. The Actor is tested every day.
More AI-ecosystem Actors from Agent Data Co
Built and maintained by Agent Data Co. Our Actors collect public AI-ecosystem data and work well together on a daily schedule:
- GitHub Trending AI Repos Scraper: AI agent, MCP and LLM repos with stars and topics
- Show HN Scraper (Hacker News AI launches): new AI launches on Hacker News with points and comments
- MCP Servers Scraper (official MCP registry): every server in the official MCP registry
- Hugging Face Scraper: trending models, datasets and Spaces
- SaaS Pricing Page Monitor: plan and price changes on any pricing page
- App Store Reviews Scraper: iOS reviews for any app, by country