Generate Embeddings

Generate vector embeddings for input text(s).

POST /v1/embeddings

cURL

curl https://gateway.bud.studio/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Machine learning is transforming industries",
    "dimensions": 1536,
    "priority": "normal"
  }'

200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

cURL

curl https://gateway.bud.studio/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Machine learning is transforming industries",
    "dimensions": 1536,
    "priority": "normal"
  }'

200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Headers

Parameter	Type	Required	Description
Authorization	string	Yes	Bearer authentication header of the form Bearer <token> where <token> is your API key

Body

Parameter	Type	Required	Description
model	string	Yes	Embedding model identifier
input	string or array	Yes	Text(s) to embed. Can be a single string or array of strings
encoding_format	string	No	Format of the embedding. Options: float, base64. Default: float
dimensions	integer	No	Matryoshka dimensions for output embeddings. Default: model’s full dimensions
modality	string	No	Modality type: text, image, audio. Default: text
priority	string	No	Priority level: high, normal, low. Default: normal
include_input	boolean	No	Include original input text in response. Default: false
chunking	object	No	Chunking configuration for long texts (see Chunking Configuration below)

Chunking Configuration

The chunking parameter accepts an object with the following fields:

Parameter	Type	Description
enabled	boolean	Enable text chunking. Default: false
strategy	string	Chunking strategy: token, sentence, recursive, semantic, code, table. Default: token
chunk_size	integer	Max tokens per chunk (1-8192). Default: 512
chunk_overlap	integer	Token overlap between chunks. Default: 0
tokenizer	string	Tokenizer: cl100k_base, p50k_base, r50k_base, gpt2. Default: cl100k_base
min_sentences	integer	[sentence strategy] Minimum sentences per chunk. Default: 1

Supported Providers

OpenAI

text-embedding-3-small, text-embedding-3-large, ada-002

Azure OpenAI

Enterprise text embeddings with global availability

Cohere

embed-english-v3.0, embed-multilingual-v3.0

Voyage AI

voyage-2, voyage-code-2 specialized embeddings

Together AI

Nomic Embed and open-source embedding models

Google

text-embedding-004 and multimodal embeddings