Create Embedding

Request BodyCopy Anchor Link

This endpoint returns after the vectors are ready. For large batches, set your HTTP client timeout to at least 120s.

Choose a ModelCopy Anchor Link

Use GET /v1/models?recommended_for=embedding for current models and dimensions.

ResponseCopy Anchor Link

curl -X POST "https://api.tokenlab.sh/v1/embeddings" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0194, 0.0081]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  }
}

Batch EmbeddingsCopy Anchor Link

# Embed multiple texts at once
response = client.embeddings.create(
    model="text-embedding-3-small",
    input=[
        "First document text",
        "Second document text",
        "Third document text"
    ]
)

for i, data in enumerate(response.data):
    print(f"Document {i}: {len(data.embedding)} dimensions")

Related interfacesCopy Anchor Link

POST /v1/multimodal/embeddings

Read the selected model’s current model details before using another interface. Availability and request fields depend on the model.

Multimodal input uses one object or an array of objects with text, image_url, or image_base64 plus image_mime_type. Image input also requires enabled image support and explicit support in the model details. It is not available for every embedding model.