Great Work Labs
Models / Understand text

Sort

Zero-shot classification
sort-1

Classify text into your own labels. No training.

Price$0.01 per 1,000 label checks
Speed (our servers)98 to 216 ms
Languages100+ languages for the text; labels work best in English
InputText, batches up to 32
Built onHorizon-Labs/multilingual-zeroshot-small (Apache-2.0)

Sort puts text into categories you name in the request: ["billing", "bug report", "feature request"] works on the first call, no examples or training needed.

Set multi_label: true when a text can belong to several labels at once (a ticket that's both a bug and a billing problem). Descriptive labels beat terse ones: "asks for a refund" scores better than "refund".

Use it

curl https://labs.greatwork.company/v1/run \
  -H "Authorization: Bearer $GWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "sort-1",
  "input": "I was charged twice for my subscription this month, please fix it.",
  "labels": [
    "billing",
    "bug report",
    "feature request",
    "account access"
  ]
}'

Set GWL_API_KEY to a key from your dashboard. The bare name sort works too and follows new versions.

Options

input: A string, or an array of up to 32 strings. Only the first 2,000 characters are read.

NameTypeDefaultWhat it does
labels requiredstring[]2 to 20 candidate labels, in plain words.
multi_labelbooleanfalseScore each label on its own (several can be true) instead of picking one.
templatestring"This example is {label}."Sentence the model checks for each label. {label} is replaced. Try "The user wants to {label}." for intents.

Output

FieldTypeMeaning
labelstringBest label.
scorenumberIts score, 0 to 1.
labelsobject[]Every label with its score, best first.

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

Support ticket

{
  "model": "sort-1",
  "input": "I was charged twice for my subscription this month, please fix it.",
  "labels": [
    "billing",
    "bug report",
    "feature request",
    "account access"
  ]
}
{
  "label": "billing",
  "score": 0.9881,
  "labels": [
    {
      "label": "billing",
      "score": 0.9881
    },
    {
      "label": "bug report",
      "score": 0.0071
    },
    {
      "label": "feature request",
      "score": 0.0028
    },
    {
      "label": "account access",
      "score": 0.0019
    }
  ]
}

Captured on our production servers: 216 ms, 4 labels, $0.00004.

Intent

{
  "model": "sort-1",
  "input": "can you move my 3pm with Dana to tomorrow morning",
  "labels": [
    "schedule a meeting",
    "reschedule a meeting",
    "cancel a meeting",
    "ask a question"
  ],
  "template": "The user wants to {label}."
}
{
  "label": "reschedule a meeting",
  "score": 0.5831,
  "labels": [
    {
      "label": "reschedule a meeting",
      "score": 0.5831
    },
    {
      "label": "schedule a meeting",
      "score": 0.2028
    },
    {
      "label": "cancel a meeting",
      "score": 0.1224
    },
    {
      "label": "ask a question",
      "score": 0.0917
    }
  ]
}

Captured on our production servers: 123 ms, 4 labels, $0.00004.

Multi-label

{
  "model": "sort-1",
  "input": "The app crashes every time I try to update my credit card.",
  "labels": [
    "billing",
    "bug report",
    "mobile app"
  ],
  "multi_label": true
}
{
  "label": "mobile app",
  "score": 0.9947,
  "labels": [
    {
      "label": "mobile app",
      "score": 0.9947
    },
    {
      "label": "bug report",
      "score": 0.9869
    },
    {
      "label": "billing",
      "score": 0.0733
    }
  ],
  "multi_label": true
}

Captured on our production servers: 98 ms, 3 labels, $0.00003.

Good for

  • Route tickets without training a classifier
  • Tag articles with your own taxonomy
  • Detect intents in chat messages
  • Prototype a classifier before you have data

Limits and caveats

  • Results depend on label wording: try a few phrasings.
  • With many similar labels (40+ intents) accuracy drops; split them into groups.
  • Swahili is weak.

Pricing

$0.01 per 1,000 label checks. One unit per label per text: classifying one text into 5 labels is 5 units ($0.00005). 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-zeroshot-small, 141M (mmBERT-small encoder) parameters. License: Apache-2.0. We run it on our servers.