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

Only repositories owned by this user or organization.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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