Search Hugging Face models
hugging_face_models_searchSearch and filter Hugging Face models by task, library, language, licence, author, base model and more; use paginated results to find models that fit a project.
Instructions
Search and filter Hugging Face models by task, library, language, licence, base model and more. Optional inputs: query, author, pipelineTag, library, language and 12 more. Returns a list (use cursor when paginated).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "hugging_face_models_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Sort order: `downloads` (last 30 days), `likes`, `likes7d`, `likes30d`, `trending`, `created` or `updated`. Default: `trending`. | |
| tags | No | Comma-separated tags the repository must all have, e.g. `text-classification,pytorch` or `license:mit`. | |
| gated | No | `true` for gated models only, `false` to hide them. | |
| limit | No | Items per page, 1-1000. A page can hold fewer. Default: 50. | |
| order | No | `desc` (default) or `asc`. `asc` only works with `sort=created`. | |
| query | No | Search text. Matches repository ids, tags and card text. | |
| author | No | Only repositories owned by this user or organization. | |
| cursor | No | Pass `page.nextCursor` from the previous response to get the next page. Keep every other parameter the same. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| library | No | Library tag, e.g. `transformers`, `diffusers` or `gguf`. | |
| license | No | Licence id, e.g. `apache-2.0` or `mit`. | |
| language | No | Language code tag, e.g. `en` or `ja`. | |
| relation | No | How the models relate to `baseModel`: `finetune`, `adapter`, `merge` or `quantized`. | |
| baseModel | No | Only models built from this base model. Use with `relation`. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| pipelineTag | No | Task, e.g. `text-generation` or `text-to-image`. List them with the tags endpoint. | |
| maxParameters | No | Largest parameter count, e.g. `500M` or `7B`. | |
| minParameters | No | Smallest parameter count, e.g. `500M` or `7B`. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. | |
| inferenceProvider | No | Only models a hosted inference provider serves: a provider id, or `all` for any provider. |