OpenRouter AI Model Pricing Scraper

OpenRouter AI Model Pricing Scraper

Scrape AI model pricing from OpenRouter, filter by provider, modality, context length, and price, up to a million models per run. Every model row includes prompt and completion cost per million tokens, context window, and supported modalities. Export to CSV, JSON, Excel, or XML.

OpenRouter lists hundreds of AI models from dozens of providers, but comparing them across the web interface is slow and manual. This Actor reads the full model catalog directly, lets you filter by provider, modality, minimum context length, and maximum price, and returns a clean dataset you can sort and analyze. No API key or OpenRouter account is required.

Who uses it	What they scrape OpenRouter for
AI engineers	Find the cheapest model that meets a minimum context-length requirement for a production pipeline.
Procurement teams	Audit per-token costs across providers before committing to an enterprise LLM budget.
Market analysts	Track how model pricing and context windows shift week over week across the AI industry.
Indie developers	Discover free or ultra-low-cost models to prototype without burning API credits.

What it does

This Actor collects AI model pricing and specs from the OpenRouter model catalog and returns each model as a flat row with prompt price, completion price, context length, and modality.

• 🔍 Provider filter: Narrow results to a single vendor such as OpenAI, Anthropic, Google, or Meta Llama.
• 🧠 Modality filter: Select only text-to-text, text+image-to-text, text-to-image, or text+audio-to-text models.
• 📏 Context-length floor: Exclude models with context windows below a threshold, e.g. 100,000 tokens.
• 💰 Price ceiling: Set a maximum prompt or completion price per million tokens and ignore everything above it.
• 🆓 Free-only toggle: Return only models where both prompt and completion prices are zero.
• 📊 Sort controls: Order results by newest first, cheapest prompt, cheapest completion, largest context, or name.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

What you can do with OpenRouter data

💰 Build a cost-optimized model shortlist.

An AI engineer sets a max prompt price of $0.50 and a min context of 128k tokens, then exports the ten cheapest models to a spreadsheet for a stakeholder review.

📈 Monitor pricing changes over time.

A market analyst schedules a daily run with no filters, diffs the CSV against the previous day, and flags any model whose prompt price dropped by more than 20 percent.

🆓 Find every free model available today.

An indie developer enables the free-only toggle, sorts by context length descending, and picks the largest free context window for a weekend side project.

🔍 Audit a single provider's entire catalog.

A procurement lead selects 'Anthropic' from the provider dropdown, sets maxItems to 1000, and receives every Anthropic model with its current per-token cost.

Why choose this scraper

	What you get
Prompt and completion price	Cost per million tokens for input and output, in USD.
Context length	Maximum token window the model supports.
Modality	Input and output types, e.g. text-to-text or text+image-to-text.
Provider	The vendor that hosts the model, normalized for grouping.

How it compares

This Actor scrapes the public model catalog for pricing data, while the two OpenRouter API Actors proxy LLM requests through OpenRouter's paid service.

Feature	ParseForge	OpenRouter	OpenRouter - Bring Your Own Key
Scrapes model pricing catalog	Yes	Not listed	Not listed
Filter by provider	Yes, 50+ providers	Not listed	Not listed
Filter by modality	Yes	Not listed	Not listed
Filter by max price per million tokens	Yes	Not listed	Not listed
Free models only toggle	Yes	Not listed	Not listed
No OpenRouter account required	Yes	Not listed	No, requires your own API key

Configure the run

Drive the Actor with an optional keyword search, a provider dropdown, a modality selector, and numeric price and context-length cutoffs. Filters run as each model is read so only matches reach your dataset. The Input tab lists every parameter.

A first run with the defaults:

{
  "maxItems": 10,
  "sortBy": "created"
}

A larger pull:

{
  "maxItems": 200,
  "sortBy": "created"
}

Pricing

Pay-per-result: $0.0438 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$4.38
1,000 results	$43.80
10,000 results	$438.00

New Apify accounts start with $5 in free credit.

Free users

Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect up to 1,000,000 results per run.

Run it

1. Create a free Apify account with $5 in credit.
2. Open the OpenRouter AI Model Pricing Scraper.
3. Set your inputs and any filters, then click Start.
4. Export the results as CSV, Excel, JSON, or XML from the Dataset tab.

Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.

Use with AI agents (MCP)

Give an AI agent live access to OpenRouter through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/openrouter-models-pricing-scraper"

Then prompt it in plain language to run the scraper and read back the results.

Troubleshooting

Why am I getting zero results?

Your filters may be too restrictive. Try removing the keyword query, clearing the price ceilings, or lowering the minimum context length. The free-only toggle also excludes any model that is not completely free.

The run finished but the dataset has fewer rows than my maxItems setting.

The Actor collected every model that matched your filters. If the total matching models is smaller than your maxItems value, you will see fewer rows. Broaden your filters to get more results.

Prices in the dataset look different from the OpenRouter website.

OpenRouter updates pricing frequently. Run the Actor again to fetch the latest data. If the discrepancy persists, check whether the website shows a promotional or discounted rate that the catalog page does not reflect.

I cannot find a specific model in the results.

Try searching by a keyword from the model name or description. Also check that your provider, modality, and price filters are not excluding it. Leaving all optional filters empty returns the full catalog.

FAQ

Question	Answer
Do I need an OpenRouter account or API key to run this?	No. This Actor reads the publicly available model catalog page. You do not need to sign up for OpenRouter or provide any credentials.
What pricing fields does each row include?	Every row returns the prompt price per million tokens and the completion price per million tokens, both in US dollars. Free models show zero for both fields.
Can I filter to only free models?	Yes. Enable the 'Free models only' checkbox in the input and the Actor will return only models where both prompt and completion prices are zero.
How do I find models with a large context window?	Set the 'Minimum context length' field to your desired token count, e.g. 100000, and the Actor will exclude any model with a smaller context window.
Can I search for a specific model by name?	Yes. Use the 'Model name or keyword' text field to search across model IDs, names, and descriptions. Leave it empty to return all models that match your other filters.
What providers are available in the dropdown?	The provider filter includes over 50 vendors: OpenAI, Anthropic, Google, Meta Llama, Mistral AI, DeepSeek, Cohere, x.AI (Grok), and many more.
How do I sort the results?	Use the 'Sort By' dropdown. You can order by newest first, cheapest prompt price, cheapest completion price, largest context length, or alphabetically by name.
What export formats are supported?	You can export your dataset to CSV, JSON, Excel, or XML from the Apify platform after the run completes.
How many models can I collect in one run?	Set the 'Maximum models' field to any number up to 1,000,000. The Actor will stop after collecting that many matching models.
Does this Actor use the OpenRouter API?	No. It scrapes the public model listing page, so there are no API rate limits or per-token charges from OpenRouter.

Related actors

Browse the full ParseForge collection for more scrapers.

🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by OpenRouter, Inc. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.