> **For coding agents and LLMs:** This is one Social Fetch marketing page (markdown export). For API orientation start with [`/llms.txt`](https://www.socialfetch.dev/llms.txt); for auth and crawl rules use [`/agents.txt`](https://www.socialfetch.dev/agents.txt); for every operation use [`/llms-endpoints.txt`](https://www.socialfetch.dev/llms-endpoints.txt).

## This page

- **On-site (HTML):** <https://www.socialfetch.dev/platforms/hugging-face/models>
- **Markdown (.mdx) URL:** <https://www.socialfetch.dev/platforms/hugging-face/models.mdx>

---

# Hugging Face Models API

Search the model catalogue by task, library, size, licence and base model, with likes, downloads and tags on every row.

`GET /v1/hugging-face/models` returns a page of repositories in `results`. Use `query`, `author`, `pipelineTag`, `library`, `language`, `license` and `tags` to narrow the list, `baseModel` with `relation` to find finetunes, adapters, merges or quantized builds, and `gated` or `inferenceProvider` to filter by access or hosted availability. `minParameters` and `maxParameters` take values such as `500M` or `7B`.

Each row carries `id`, `url`, `author`, `likes`, `downloads`, `downloadsAllTime`, `trendingScore`, `pipelineTag`, `library`, `license`, `gated`, `parameters` and the full `tags` list. Sort with `sort` and `order`, choose `limit` up to 1000, and pass `page.nextCursor` as `cursor` while `page.hasMore` is true.

## Request

- **Endpoint:** `GET /v1/hugging-face/models`
- **Credits:** 1 credit
Failed requests are free
- **Input:** by keyword and filters
- **Full reference:** [docs](https://www.socialfetch.dev/docs/api/v1/hugging-face/models/get)
- **Platform page:** [/platforms/hugging-face](https://www.socialfetch.dev/platforms/hugging-face)

## FAQ

### How do I find models for a task such as text generation?

Set pipelineTag=text-generation. The list of task ids is available from GET /v1/hugging-face/tags with group=pipeline_tag.

### Can I search by parameter count?

Yes. minParameters and maxParameters accept values like 500M or 7B, and a minimum above the maximum is refused with a 400 before any lookup.

### How do I find finetunes of one model?

Set baseModel to a model id such as openai-community/gpt2 and relation to finetune, adapter, merge or quantized. relation without baseModel is refused.

### How does paging work?

Results carry page.hasMore and page.nextCursor. Send page.nextCursor back as cursor with the same filters to get the next page.

### How much does a search cost?

Pricing is documented on the operation in the API registry (shown on this page). Confirm on every response with meta.creditsCharged: that field is the billing source of truth. Each paginated page is a separate billed request.