Civitai Models Scraper

Civitai Models Scraper

Scrape Civitai AI models by search term, type, or base model, up to a million per run. Every model comes with its creator, stats, version details, trigger words, and download URLs. No API key required. Export to CSV, JSON, Excel, or XML.

Finding the right AI art model on Civitai means scrolling through endless checkpoints, LoRAs, and embeddings. This Actor searches the public Civitai API directly, filters by model type, base model, and NSFW status, and returns a clean dataset you can sort and compare offline. No browser, no login, no rate-limit headaches.

Who uses it	What they scrape Civitai for
AI artists and prompt engineers	Build a personal catalog of LoRAs and checkpoints for a specific style or character.
Model trainers and creators	Monitor download trends and ratings for competing models in their niche.
Content curators and directory builders	Populate a searchable database of Civitai models with trigger words and example images.
Market researchers	Track which base models and model types are gaining traction week over week.

What it does

This Actor collects Civitai AI models matching your search query and filters, and returns each one as a flat row with its metadata, stats, and version links.

• 🔍 Free-text search: Find models by name, creator, or any keyword the Civitai API accepts.
• 📊 Sort order control: Pull the highest rated, most downloaded, or newest models first.
• 🏷️ Model type filter: Narrow results to Checkpoint, LoRA, ControlNet, VAE, Textual Inversion, and more.
• 🧱 Base model filter: Limit results to a specific architecture like SD 1.5, SDXL 1.0, Pony, or Flux.1 D.
• 🔞 NSFW toggle: Include or exclude adult content with a single checkbox.

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

What you can do with Civitai data

🎨 Build a style-specific model library.

An AI artist searches for 'watercolor' LoRAs, filters by SDXL 1.0, and exports the top 200 rated models with their trigger words to test in ComfyUI.

📈 Track model popularity over time.

A market researcher runs the Actor weekly with the 'Most Downloaded' sort, collecting stats on checkpoints to spot rising trends before they peak.

🗂️ Populate a community model directory.

A curator scrapes all Textual Inversions and Hypernetworks, filters out NSFW content, and builds a searchable gallery with download links and example images.

⚙️ Audit models for a specific base architecture.

A trainer filters by 'Pony' base model and 'Checkpoint' type to compile a list of all Pony-based merges and their download counts.

Why choose this scraper

	What you get
No API key	Reads the public Civitai API endpoint with no registration or token.
Fixed flat schema	Every model returns the same fields so your dataset is ready for analysis.
High throughput	Collect up to 1,000,000 models in a single run.
Version details	Each row includes the latest version's download URL, trigger words, and base model.

How it compares

Three other Civitai scrapers exist on Apify. This Actor focuses on fast, high-volume model search with a simple flat schema, while others add creator profiles, images, or video model support.

Feature	ParseForge	Civitai Models & Creators Scraper	Civitai Model Scraper - AI Image Model Intelligence	Civitai Scraper - AI Model Catalog, LORAs, Checkpoints & Stats
Free-text search query	Yes	Yes	Yes	Yes
Model type filter (14 types)	Yes	Not listed	Not listed	Yes
Base model filter	Yes	Not listed	Yes	Yes
NSFW toggle	Yes	Not listed	Not listed	Yes
Sort by rating, downloads, or newest	Yes	Not listed	Not listed	Not listed
Up to 1,000,000 models per run	Yes	Not listed	Not listed	Not listed
No API key required	Yes	Not listed	Yes	Not listed

Configure the run

Drive the Actor with a free-text search query, then narrow results by model type, base model, and NSFW status. Filters are sent to the Civitai API so only matching models count toward your maxItems limit. The Input tab lists every parameter.

A first run with the defaults:

{
 "maxItems": 10
}

A larger pull:

{
 "maxItems": 200
}

Pricing

Pay-per-result: $0.0085 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$0.85
1,000 results	$8.50
10,000 results	$85.00

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 Civitai Models 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 Civitai 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/civitai-models-scraper"

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

Troubleshooting

Why am I getting no results?

Check that your search query is not too restrictive. Try broadening the term, removing the base model filter, or toggling the NSFW setting. Also confirm the model type you selected exists on Civitai.

The Actor returns fewer models than my maxItems setting.

The Civitai API only returns models that match your filters. If the total matches are fewer than maxItems, the Actor will return everything it found. Try removing filters to widen the pool.

My base model filter is not working as expected.

The base model field is free-text and passed directly to the API. Make sure your spelling matches Civitai's convention exactly, for example 'SDXL 1.0' rather than 'SDXL'.

I am getting NSFW models even though I left the checkbox unchecked.

The default setting excludes NSFW content. If you still see adult models, the Civitai API may classify them differently. Try adding a negative keyword to your search query or report the model on Civitai.

The download URL is not working.

Civitai download URLs can expire or require a referrer. The Actor returns the URL provided by the API at the time of the run. Try re-running the Actor to get a fresh URL.

FAQ

Question	Answer
Do I need a Civitai API key to use this Actor?	No. This Actor reads the public, unauthenticated Civitai API endpoint. You do not need to register an application or provide a token.
What model types can I filter by?	You can filter by Checkpoint, Textual Inversion, Hypernetwork, Aesthetic Gradient, LoRA, LoCon, ControlNet, Upscaler, Motion Module, VAE, Poses, Wildcards, Workflows, and Other.
How do I search for a specific model name?	Enter your search term in the 'Search term for models' field. The Actor sends it as a free-text query to the Civitai API, which matches against model names.
Does this Actor download the model files?	No. It returns the download URL for the latest version of each model. You can use that URL in a separate download step or Actor.
Can I scrape all models on Civitai?	You can collect up to 1,000,000 models per run. Use a broad search or leave the query empty, set a high maxItems, and choose your sort order to pull a large slice of the catalog.
How do I exclude NSFW models?	Leave the 'Allow NSFW' checkbox unchecked. This is the default setting and tells the API to return only safe-for-work models.
What base models can I filter by?	Enter any base model string the Civitai API recognizes, such as 'SD 1.5', 'SDXL 1.0', 'Pony', or 'Flux.1 D'. The field is free-text so you can try newer architectures as they appear.
Does the Actor return trigger words?	Yes. The dataset includes trained trigger words from the latest model version, which you can copy directly into your prompts.
Can I sort results by newest first?	Yes. Set the 'Sort by' dropdown to 'Newest' and the Actor will return the most recently published models matching your filters.
What export formats are supported?	You can export your dataset to CSV, JSON, Excel, or XML from the Apify platform after the run completes.

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 Civitai, 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.