Embeddings

Embeddings

Creates an embedding vector representing the input text.

Endpoint

POST /v1/embeddings

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model ID
input	string/array	Yes	Text to embed (string or array of strings)
encoding_format	string	No	float (default) or base64

Example

curl -X POST https://cryptgpt.co/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    }
  ],
  "model": "gemma-4-26b",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Multiple Inputs

curl -X POST https://cryptgpt.co/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b",
    "input": ["Hello world", "Goodbye world"]
  }'

Use Cases

• Semantic search: Compare embedding similarity for document retrieval
• Clustering: Group similar texts together
• Classification: Use embeddings as features for ML models
• Recommendation: Find similar items based on text descriptions