Embeddings

POST/v1/embeddings

Generate vector embeddings for text, useful for semantic search, retrieval-augmented generation (RAG), clustering, classification, and reranking pipelines.

SandBase exposes an OpenAI-compatible embeddings endpoint. Use your SandBase API key with the OpenAI SDK by setting the base URL to https://api.sandbase.ai/v1.

Endpoint

POST https://api.sandbase.ai/v1/embeddings
Authorization: Bearer sk-sb-your-api-key
Content-Type: application/json

Request Body

Parameter	Type	Required	Default	Description
model	string	Yes	—	Embedding model ID, for example alibaba/text-embedding-v4
input	string or string[]	Yes	—	Text or list of texts to embed
dimensions	integer	No	Model default	Output vector dimension when supported
encoding_format	string	No	float	Embedding encoding format. float is supported

For alibaba/text-embedding-v4, supported dimensions values are 2048, 1536, 1024, 768, 512, 256, 128, and 64.

Examples

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-sb-YOUR_KEY",
    base_url="https://api.sandbase.ai/v1",
)

response = client.embeddings.create(
    model="alibaba/text-embedding-v4",
    input="SandBase provides a unified API for AI models, agents, and developer tools.",
    dimensions=1024,
    encoding_format="float",
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")

TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-sb-YOUR_KEY',
  baseURL: 'https://api.sandbase.ai/v1',
});

const response = await client.embeddings.create({
  model: 'alibaba/text-embedding-v4',
  input: 'SandBase provides a unified API for AI models, agents, and developer tools.',
  dimensions: 1024,
  encoding_format: 'float',
});

console.log(response.data[0].embedding.length);

cURL

curl https://api.sandbase.ai/v1/embeddings \
  -H "Authorization: Bearer sk-sb-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/text-embedding-v4",
    "input": "SandBase provides a unified API for AI models, agents, and developer tools.",
    "dimensions": 1024,
    "encoding_format": "float"
  }'

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0045, 0.0312]
    }
  ],
  "model": "alibaba/text-embedding-v4",
  "usage": {
    "prompt_tokens": 16,
    "total_tokens": 16
  }
}

Available Models

Model	Dimensions	Price (per 1M tokens)
alibaba/text-embedding-v4	64-2048	$0.10 input
openai/text-embedding-3-small	1536	$0.02
openai/text-embedding-3-large	3072	$0.13
voyage/voyage-3	1024	$0.06

→ Browse all embedding models