Great Work Labs
Models / Search and retrieval

Glyph

Emoji suggestions
glyph-1

The right emoji for a message, out of 1,800.

Price$0.01 per 1,000 texts
Speed (our servers)18 to 37 ms
Languages~100 languages
InputText, batches up to 64
Built onintfloat/multilingual-e5-small + Emojibase (MIT)

Glyph suggests emoji that match a message, a channel name or a reaction. It searches every standard emoji (smileys, people, animals, food, travel, objects, symbols) by meaning, not by keyword, so a message doesn't need to name the thing to find it.

Use it

curl https://labs.greatwork.company/v1/run \
  -H "Authorization: Bearer $GWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "glyph-1",
  "input": "we finally shipped the new release"
}'

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

Options

input: A short text (string or array of up to 64). The first 1,000 characters are read.

NameTypeDefaultWhat it does
top_kinteger5How many emoji to return.

Output

FieldTypeMeaning
emojisobject[]emoji, name, 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

Shipped

{
  "model": "glyph-1",
  "input": "we finally shipped the new release"
}
{
  "emojis": [
    {
      "emoji": "đŸ“Ļ",
      "name": "package",
      "score": 0.8204
    },
    {
      "emoji": "📒",
      "name": "ledger",
      "score": 0.8192
    },
    {
      "emoji": "🆕",
      "name": "NEW button",
      "score": 0.8156
    },
    {
      "emoji": "🚈",
      "name": "light rail",
      "score": 0.8137
    },
    {
      "emoji": "â„šī¸",
      "name": "information",
      "score": 0.8124
    }
  ]
}

Captured on our production servers: 22 ms, 1 text, $0.00001.

Coffee

{
  "model": "glyph-1",
  "input": "need coffee before this meeting",
  "top_k": 3
}
{
  "emojis": [
    {
      "emoji": "☕",
      "name": "hot beverage",
      "score": 0.834
    },
    {
      "emoji": "🤝",
      "name": "handshake",
      "score": 0.8268
    },
    {
      "emoji": "đŸĩ",
      "name": "teacup without handle",
      "score": 0.8253
    }
  ]
}

Captured on our production servers: 18 ms, 1 text, $0.00001.

Batch

{
  "model": "glyph-1",
  "input": [
    "happy birthday!",
    "the build is broken again",
    "pizza party friday"
  ],
  "top_k": 3
}
[
  {
    "emojis": [
      {
        "emoji": "🎈",
        "name": "balloon",
        "score": 0.8613
      },
      {
        "emoji": "🎀",
        "name": "ribbon",
        "score": 0.8529
      },
      {
        "emoji": "🎂",
        "name": "birthday cake",
        "score": 0.8457
      }
    ]
  },
  {
    "emojis": [
      {
        "emoji": "🚧",
        "name": "construction",
        "score": 0.8345
      },
      {
        "emoji": "🏭",
        "name": "factory",
        "score": 0.8267
      },
      {
        "emoji": "🔨",
        "name": "hammer",
        "score": 0.8255
      }
    ]
  },
  {
    "emojis": [
      {
        "emoji": "🍕",
        "name": "pizza",
        "score": 0.8396
      },
      {
        "emoji": "🍤",
        "name": "fried shrimp",
        "score": 0.812
      },
      {
        "emoji": "đŸĨ",
        "name": "fish cake with swirl",
        "score": 0.81
      }
    ]
  }
]

Captured on our production servers: 37 ms, 3 texts, $0.00003.

Good for

  • Suggest reactions in a chat app
  • Pick an icon for a new channel or project
  • Add emoji to notification titles
  • Decorate generated social posts

Limits and caveats

  • No flags or skin-tone variants; pick a skin tone in your UI.

Pricing

$0.01 per 1,000 texts. One unit per text. 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

intfloat/multilingual-e5-small + Emojibase, 118M parameters. License: MIT. We run it on our servers.