Sieve scores a comment, chat message or review for toxicity, severe toxicity, insults, threats, obscenity, identity attacks and sexually explicit language. flagged is true when any of them crosses your threshold.
It also answers OpenAI-style requests at /v1/moderations, so moderation code you already have can point here.
Use it
curl https://labs.greatwork.company/v1/run \
-H "Authorization: Bearer $GWL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sieve-1",
"input": "You'\''re a complete idiot and everyone here knows it."
}'const res = await fetch("https://labs.greatwork.company/v1/run", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.GWL_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "sieve-1",
"input": "You're a complete idiot and everyone here knows it."
}),
});
const { output, usage } = await res.json();import os, requests
res = requests.post(
"https://labs.greatwork.company/v1/run",
headers={"Authorization": f"Bearer {os.environ['GWL_API_KEY']}"},
json={
"model": "sieve-1",
"input": "You're a complete idiot and everyone here knows it."
},
)
output = res.json()["output"]Set GWL_API_KEY to a key from your dashboard. The bare name sieve works too and follows new versions. Also answers POST /v1/moderations (OpenAI): see compatible endpoints.
Options
input: A string, or an array of up to 64 strings to run as a batch.
| Name | Type | Default | What it does |
|---|---|---|---|
threshold | number | 0.5 | Score at or above which a label counts as flagged (non-English text scores lower; try 0.35 for multilingual communities). |
Output
| Field | Type | Meaning |
|---|---|---|
flagged | boolean | True when any label is at or above threshold. |
labels | string[] | Labels at or above threshold. |
scores | object | toxicity, severe_toxicity, obscene, threat, insult, identity_attack, sexual_explicit, each 0 to 1. |
Every response wraps this in {"id", "model", "output", "usage": {"units", "unit", "cost_usd"}, "latency_ms"}. Send an array as input and output is an array in the same order.
Examples
Insult
{
"model": "sieve-1",
"input": "You're a complete idiot and everyone here knows it."
}{
"flagged": true,
"labels": [
"toxicity",
"insult"
],
"scores": {
"toxicity": 0.9095,
"severe_toxicity": 0.0412,
"obscene": 0.1594,
"threat": 0.0045,
"insult": 0.9069,
"identity_attack": 0.0133,
"sexual_explicit": 0.0032
}
}Captured on our production servers: 38 ms, 1 text, $0.00002.
Heated but fine
{
"model": "sieve-1",
"input": "This patch notes update is a disaster, who signed off on removing the old map?"
}{
"flagged": false,
"labels": [],
"scores": {
"toxicity": 0.0548,
"severe_toxicity": 0.0019,
"obscene": 0.0043,
"threat": 0.0037,
"insult": 0.0403,
"identity_attack": 0.002,
"sexual_explicit": 0.0009
}
}Captured on our production servers: 37 ms, 1 text, $0.00002.
Batch
{
"model": "sieve-1",
"input": [
"Great stream tonight!",
"nobody wants you here, just leave",
"the ref was blind today lol"
]
}[
{
"flagged": false,
"labels": [],
"scores": {
"toxicity": 0.0098,
"severe_toxicity": 0.001,
"obscene": 0.0014,
"threat": 0.003,
"insult": 0.0042,
"identity_attack": 0.0008,
"sexual_explicit": 0.0037
}
},
{
"flagged": false,
"labels": [],
"scores": {
"toxicity": 0.0867,
"severe_toxicity": 0.0024,
"obscene": 0.0027,
"threat": 0.0068,
"insult": 0.0562,
"identity_attack": 0.0072,
"sexual_explicit": 0.0013
}
},
{
"flagged": false,
"labels": [],
"scores": {
"toxicity": 0.0558,
"severe_toxicity": 0.0028,
"obscene": 0.0036,
"threat": 0.003,
"insult": 0.0374,
"identity_attack": 0.0027,
"sexual_explicit": 0.0031
}
}
]Captured on our production servers: 71 ms, 3 texts, $0.00006.
Good for
- Hold toxic comments for review
- Score chat in a game or community
- Clean a dataset before training
- Warn users before they post
Limits and caveats
- Can over-flag texts that mention identity groups without attacking them.
- Weaker on low-resource languages (Amharic, Arabic).
- For policy categories like self-harm, weapons or fraud, use Warden.
Pricing
$0.02 per 1,000 texts. One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. Failed calls aren't charged, and a call never costs more than its estimate (POST /v1/estimate tells you before you run it).
Built on
Horizon-Labs/multilingual-toxicity-small, 141M (mmBERT-small encoder) parameters. License: Apache-2.0. We run it on our servers with our own long-text chunking and score aggregation.