Hugging Face model

One model: everything in the search results plus all-time downloads, parameter count (total and per dtype), GGUF details, architectures and model type, card metadata (license, languages, base model, datasets, metrics), files, storage used, base-model relation, number of derived models (fine-tunes, adapters, quantizations, merges), Spaces using it, inference providers serving it, widget examples, model-index and evaluation results.

Every response includes credits_used: the credits this call cost.

Parameters

Every endpoint also takes fresh, raw, fields (see lean responses and caching).

Example

curl "https://api.api.sh/huggingface/v1/model?id=meta-llama%2FLlama-3.1-8B-Instruct" \
  -H "x-api-key: $APISH_KEY"

import os, requests

res = requests.get(
    "https://api.api.sh/huggingface/v1/model",
    params={"id": "meta-llama/Llama-3.1-8B-Instruct"},
    headers={"x-api-key": os.environ["APISH_KEY"]},
    timeout=120,
)
res.raise_for_status()
data = res.json()

const url = new URL("https://api.api.sh/huggingface/v1/model");
url.searchParams.set("id", "meta-llama/Llama-3.1-8B-Instruct");

const res = await fetch(url, { headers: { "x-api-key": process.env.APISH_KEY } });
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const data = await res.json();

Response

A JSON object with the fields described above, plus raw (the source's own data), cached, fetched_at and credits_used. Errors return {"success": false, "error": "…"} with the HTTP status (see errors). A lookup that ran but found nothing (404) costs the price above; refused calls and errors on our side are free (what's charged).