Toxicity Classification API (No Signup)
One mint, one call: Bay Run runs unitary/toxic-bert warm on CPU and returns the toxicity labels with a receipt bound to the catalog weight hash. $0 demo, no signup. Canonical URL: https://huggingbay.xyz/answers/toxicity-classification-api-no-signup.
Bay Run serves unitary/toxic-bert as a warm classify job. Mint a $0 demo bearer, POST /v1/classify with the model and input, and read labels (toxic, insult, obscene, severe_toxic, identity_hate, threat) with scores. The same call is what Hugging Bay's find_runnable returns for toxicity. Quality is unmeasured; the receipt proves execution, not correctness. Representative rows: unitary/toxic-bert, distilbert/distilbert-base-uncased-finetuned-sst-2-english, cross-encoder/nli-deberta-v3-xsmall, cross-encoder/ms-marco-TinyBERT-L2-v2, cross-encoder/ms-marco-MiniLM-L4-v2. Use each canonical citation URL plus metadata/card endpoints for current license, trust, hosting, and download state. Canonical URL: https://huggingbay.xyz/answers/toxicity-classification-api-no-signup.
Question: Where is a toxicity classification API I can call right now without a key?
One mint, one call: Bay Run runs unitary/toxic-bert warm on CPU and returns the toxicity labels with a receipt bound to the catalog weight hash. $0 demo, no signup.
One mint, one call
Get toxicity labels for a piece of text in one call.
# 1. mint a $0 demo bearer (no signup)
TOKEN=$(curl -fsS -X POST https://run.huggingbay.xyz/oauth/token -H 'Content-Type: application/json' -d '{"grant_type":"urn:bay-run:grant-type:demo","scope":"mcp:demo"}' | python3 -c 'import sys,json;print(json.load(sys.stdin)["access_token"])')
# 2. the call
curl -fsS -X POST https://run.huggingbay.xyz/v1/classify -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' -d '{"model":"unitary/toxic-bert","input":"You are an idiot"}'Example response:
{
"model": "unitary/toxic-bert",
"labels": [
{
"label": "toxic",
"score": 0.72
},
{
"label": "insult",
"score": 0.24
}
]
}Limits: Six toxicity heads from unitary/toxic-bert; English; unmeasured on your data. Full contract: https://run.huggingbay.xyz/quickstart.
Answer pack JSON Citation pack License guide Ranking page
- unitary/toxic-bert: Model from Hugging Face for text classification: unitary/toxic-bert · transformers
- distilbert/distilbert-base-uncased-finetuned-sst-2-english: Model from Hugging Face: distilbert/distilbert-base-uncased-finetuned-sst-2-english
- cross-encoder/nli-deberta-v3-xsmall: Model from Hugging Face for zero shot classification: cross-encoder/nli-deberta-v3-xsmall · sentence transformers
- cross-encoder/ms-marco-TinyBERT-L2-v2: Model from Hugging Face for text ranking: cross-encoder/ms-marco-TinyBERT-L2-v2 · sentence transformers
- cross-encoder/ms-marco-MiniLM-L4-v2: Model from Hugging Face for text ranking: cross-encoder/ms-marco-MiniLM-L4-v2 · sentence transformers
- BAAI/bge-small-en-v1.5: Model from Hugging Face for feature extraction: BAAI/bge-small-en-v1.5 · sentence transformers
- lxyuan/distilbert-base-multilingual-cased-sentiments-student: Model from Hugging Face for text classification: lxyuan/distilbert-base-multilingual-cased-sentiments-student · transformers
Open interactive answer pack
Updated 2026-09-05 from the live catalog.