Search Hugging Face models

Search text. Matches repository ids, tags and card text.

min 1 chars · max 200 chars

Only repositories owned by this user or organization.

pattern: ^[A-Za-z0-9][A-Za-z0-9._-]{0,95}$

Task, e.g. `text-generation` or `text-to-image`. List them with the tags endpoint.

pattern: ^[a-z0-9-]{1,60}$

Library tag, e.g. `transformers`, `diffusers` or `gguf`.

pattern: ^[A-Za-z0-9_.-]{1,60}$

Language code tag, e.g. `en` or `ja`.

pattern: ^[A-Za-z0-9_-]{1,20}$

Licence id, e.g. `apache-2.0` or `mit`.

pattern: ^[A-Za-z0-9_.+-]{1,60}$

Comma-separated tags the repository must all have, e.g. `text-classification,pytorch` or `license:mit`.

min 1 chars · max 400 chars · pattern: ^[A-Za-z0-9_.:/+-]+(,[A-Za-z0-9_.:/+-]+)*$

Only models built from this base model. Use with `relation`.

pattern: ^[A-Za-z0-9][A-Za-z0-9._-]{0,95}\/[A-Za-z0-9][A-Za-z0-9._-]{0,95}$

How the models relate to `baseModel`: `finetune`, `adapter`, `merge` or `quantized`.

one of: finetune, adapter, merge, quantized

`true` for gated models only, `false` to hide them.

one of: true, false

Only models a hosted inference provider serves: a provider id, or `all` for any provider.

pattern: ^[a-z0-9-]{1,40}$

Smallest parameter count, e.g. `500M` or `7B`.

pattern: ^\d+(?:\.\d+)?[KMBTkmbt]?$

Largest parameter count, e.g. `500M` or `7B`.

pattern: ^\d+(?:\.\d+)?[KMBTkmbt]?$

Sort order: `downloads` (last 30 days), `likes`, `likes7d`, `likes30d`, `trending`, `created` or `updated`. Default: `trending`.

one of: downloads, likes, likes7d, likes30d, trending, created, updated

`desc` (default) or `asc`. `asc` only works with `sort=created`.

one of: asc, desc

Items per page, 1-1000. A page can hold fewer. Default: 50.

≥ 1 · ≤ 1000

Pass `page.nextCursor` from the previous response to get the next page. Keep every other parameter the same.

min 1 chars · max 1024 chars