Great Work Labs
Models / Understand text

Tone

Sentiment analysis
tone-1

Positive, neutral or negative, in 30+ languages.

Price$0.02 per 1,000 texts
Speed (our servers)38 to 60 ms
Languages30+ languages, strongest in English, Spanish, French, German, Portuguese, Italian, Arabic, Hindi
InputText, batches up to 64
Built onHorizon-Labs/multilingual-sentiment-small (Apache-2.0)

Tone reads a review, message or post and says whether it's positive, neutral or negative, with a polarity score from -1 to 1 you can sort and average.

Mixed opinions, plain facts and questions come back neutral, so a ticket that only asks for an invoice doesn't drag your average down.

Use it

curl https://labs.greatwork.company/v1/run \
  -H "Authorization: Bearer $GWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tone-1",
  "input": "Arrived two days early and the fit is perfect. Ordering a second one in green."
}'

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

Options

input: A string, or an array of up to 64 strings to run as a batch.

No options: send input and that's it.

Output

FieldTypeMeaning
labelstringpositive, neutral or negative.
scorenumberConfidence in label, 0 to 1.
polaritynumberP(positive) minus P(negative), from -1 to 1.
labelsobject[]All three labels with scores.

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

Happy review

{
  "model": "tone-1",
  "input": "Arrived two days early and the fit is perfect. Ordering a second one in green."
}
{
  "label": "positive",
  "score": 0.9942,
  "polarity": 0.9917,
  "labels": [
    {
      "label": "positive",
      "score": 0.9942
    },
    {
      "label": "neutral",
      "score": 0.0034
    },
    {
      "label": "negative",
      "score": 0.0025
    }
  ]
}

Captured on our production servers: 60 ms, 1 text, $0.00002.

Unhappy ticket

{
  "model": "tone-1",
  "input": "Third time this month the export has failed and nobody has replied to my emails."
}
{
  "label": "negative",
  "score": 0.9985,
  "polarity": -0.9985,
  "labels": [
    {
      "label": "negative",
      "score": 0.9985
    },
    {
      "label": "neutral",
      "score": 0.0015
    },
    {
      "label": "positive",
      "score": 0
    }
  ]
}

Captured on our production servers: 39 ms, 1 text, $0.00002.

Neutral question

{
  "model": "tone-1",
  "input": "Can you send me last month's invoice as a PDF?"
}
{
  "label": "neutral",
  "score": 0.9991,
  "polarity": 0.0002,
  "labels": [
    {
      "label": "neutral",
      "score": 0.9991
    },
    {
      "label": "positive",
      "score": 0.0005
    },
    {
      "label": "negative",
      "score": 0.0004
    }
  ]
}

Captured on our production servers: 38 ms, 1 text, $0.00002.

Good for

  • Score reviews and NPS comments
  • Flag angry support tickets for a fast reply
  • Track brand mentions over time
  • Sort feedback before you read it

Limits and caveats

  • Sarcasm is hard: "great, it broke again" can come back positive.
  • Not for decisions about individual people.

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-sentiment-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.