AI Embeddings API docs
Generate vector embeddings for text using open-source models. Essential for semantic search, RAG pipelines, and recommendation systems.
Authentication
All AI Embeddings API requests authenticate via two headers. Get your API key from your RapidAPI dashboard after subscribing on the Basic (free) tier or higher.
X-RapidAPI-Key: YOUR_API_KEY X-RapidAPI-Host: ai-embeddings-by-helix-api.p.rapidapi.com
Base URL
https://ai-embeddings-by-helix-api.p.rapidapi.com
Endpoints
POST
/embedGenerate embeddings for text(s)
POST
/similarityCompute cosine similarity between texts
GET
/modelsList available models
Code Examples
Python
import requests
url = "https://ai-embeddings-by-helix-api.p.rapidapi.com/embed"
headers = {
"X-RapidAPI-Key": "YOUR_API_KEY",
"X-RapidAPI-Host": "ai-embeddings-by-helix-api.p.rapidapi.com",
}
response = requests.post(url, headers=headers)
print(response.json())JavaScript
const response = await fetch(
"https://ai-embeddings-by-helix-api.p.rapidapi.com/embed",
{
method: "POST",
headers: {
"X-RapidAPI-Key": "YOUR_API_KEY",
"X-RapidAPI-Host": "ai-embeddings-by-helix-api.p.rapidapi.com"
}
}
);
const data = await response.json();cURL
curl -X POST "https://ai-embeddings-by-helix-api.p.rapidapi.com/embed" \ -H "X-RapidAPI-Key: YOUR_API_KEY" \ -H "X-RapidAPI-Host: ai-embeddings-by-helix-api.p.rapidapi.com"
Response Format
All endpoints return JSON in this consistent envelope:
{
"status": "ok",
"data": { /* endpoint-specific payload */ },
"meta": {
"cached": false,
"latency_ms": 142,
"request_id": "req_abc123"
},
"timestamp": "2026-05-21T12:00:00Z"
}Error Codes
| HTTP | Code | Meaning |
|---|---|---|
| 400 | BAD_REQUEST | Missing or invalid parameter |
| 401 | UNAUTHORIZED | Invalid or missing API key |
| 403 | FORBIDDEN | Your plan doesn't include this endpoint |
| 429 | RATE_LIMIT_EXCEEDED | Too many requests — back off and retry |
| 500 | INTERNAL_ERROR | Something went wrong on our side |
| 503 | UPSTREAM_UNAVAILABLE | A third-party data source is down |
Common Use Cases
Semantic search
RAG pipelines
Recommendation engines
Duplicate detection
Content clustering
FAQ matching engine
Plagiarism detection
Resume-to-job matching
Document classification
Customer support ticket routing
Product similarity search
Legal case law matching
Knowledge graph construction
Email intent classification
Chatbot context retrieval
Academic citation matching
Code snippet search
News article deduplication
Feedback theme extraction
Anomaly detection in text logs