Embeddings

Generate vector embeddings for text input.

Endpoint: POST /api/v1/embeddings
Auth: Required

Request Body

Field	Type	Required	Default	Description
text	string or list	Yes	—	Text(s) to embed
model	string	No	Default embedding model	Model ID
provider	string	No	—	Provider name
additional_params	object	No	{}	Provider-specific parameters
byok_api_key	string	No	—	Your own provider API key

Supported Providers

Embeddings are supported by: openai, mistral, google, cohere.

Examples

PythonJavaScriptcURLOpenAI SDK

import requests

response = requests.post(
    "https://api.indoxhub.com/api/v1/embeddings",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/text-embedding-3-small",
        "text": "IndoxHub makes AI integration simple."
    }
)
result = response.json()
print(f"Dimensions: {result['dimensions']}")
print(f"Vector: {result['data'][0][:5]}...")

const response = await fetch("https://api.indoxhub.com/api/v1/embeddings", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "openai/text-embedding-3-small",
    text: "IndoxHub makes AI integration simple."
  })
});
const data = await response.json();
console.log(`Dimensions: ${data.dimensions}`);

curl https://api.indoxhub.com/api/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "text": "IndoxHub makes AI integration simple."
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.indoxhub.com/v1"
)
response = client.embeddings.create(
    model="openai/text-embedding-3-small",
    input="IndoxHub makes AI integration simple."
)
print(f"Dimensions: {len(response.data[0].embedding)}")

Batch Embeddings

Pass a list to embed multiple texts in one request:

response = requests.post(
    "https://api.indoxhub.com/api/v1/embeddings",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/text-embedding-3-small",
        "text": [
            "First document to embed",
            "Second document to embed",
            "Third document to embed"
        ]
    }
)
# response.json()["data"] is a list of embedding vectors

Response

{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "created_at": "2026-04-07T12:00:00Z",
  "duration_ms": 120.3,
  "provider": "openai",
  "model": "text-embedding-3-small",
  "success": true,
  "message": "",
  "data": [
    [0.0123, -0.0456, 0.0789, "...1536 dimensions"]
  ],
  "dimensions": 1536,
  "usage": {
    "tokens_prompt": 8,
    "tokens_completion": 0,
    "tokens_total": 8,
    "cost": 0.00001,
    "latency": 120.3
  }
}

Response Caching

Embedding responses are cached when ENABLE_RESPONSE_CACHE is enabled, reducing latency and cost for repeated inputs.