Text Embedding 004

Developer documentation

Text Embedding 004

Text Embedding 004 for semantic search, retrieval, ranking, and vector analytics.

Model Reference

Embedding models

Vector generation for semantic search, RAG, retrieval, clustering, ranking, and analytics. Endpoint: http://omixa.cloud/api/v1/embeddings

Text Embedding 004

text-embedding-004

Text Embedding 004 for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 2,048 tokens
input per 1m tokens $0.150000
minimum hold $0.010000
Integration reference

Connect Text Embedding 004

Use Omixa's unified endpoint and your workspace API key. Provider routing, billing, failover, and usage records are handled by Omixa.

POST http://omixa.cloud/api/v1/embeddings
  • Provider: google
  • Endpoint type: google_gemini_embeddings
  • Context window: 2,048 tokens
Request schema

Request fields

Only send options supported by this model. Required fields and accepted values are listed below.

Field Type Required Accepted values Description
model string Yes text-embedding-004 Use `text-embedding-004`. Omixa resolves the active provider route and failover key automatically.
input string|array Yes Any valid value Text or array of texts to embed.
dimensions integer No Any valid value Output vector dimensions for models that support truncation.
encoding_format string No float, base64 OpenAI-compatible embedding encoding.
user string No Any valid value Optional end-user identifier for audit or provider policy forwarding.
Ready to send

Payload and response

Start with this model-safe payload and expect the normalized Omixa response shape shown beside it.

Example JSON payload
{
    "model": "text-embedding-004",
    "input": "Customer support knowledge base paragraph.",
    "dimensions": 1024
}
Response shape
{
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "embedding": [
                0.0123,
                -0.0456
            ],
            "index": 0
        }
    ],
    "usage": {
        "prompt_tokens": 12,
        "total_tokens": 12
    }
}
Language examples

Copy-ready integration code

Replace the example API key with a workspace key and keep model-specific fields unchanged unless the table above marks them optional.

cURL
curl -X POST http://omixa.cloud/api/v1/embeddings \
  -H "Authorization: Bearer omx_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-004",
    "input": "Customer support knowledge base paragraph.",
    "dimensions": 1024
}'
JavaScript fetch
const response = await fetch('http://omixa.cloud/api/v1/embeddings', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer omx_live_xxx',
    'Content-Type': 'application/json'
  },
  body: "{\n    \"model\": \"text-embedding-004\",\n    \"input\": \"Customer support knowledge base paragraph.\",\n    \"dimensions\": 1024\n}"
});
const data = await response.json();
Python requests
import requests

response = requests.post(
    'http://omixa.cloud/api/v1/embeddings',
    headers={'Authorization': 'Bearer omx_live_xxx', 'Content-Type': 'application/json'},
    json={
    "model": "text-embedding-004",
    "input": "Customer support knowledge base paragraph.",
    "dimensions": 1024
}
)
print(response.json())
PHP cURL
$ch = curl_init('http://omixa.cloud/api/v1/embeddings');
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => ['Authorization: Bearer omx_live_xxx', 'Content-Type: application/json'],
    CURLOPT_POSTFIELDS => '{
    "model": "text-embedding-004",
    "input": "Customer support knowledge base paragraph.",
    "dimensions": 1024
}',
    CURLOPT_RETURNTRANSFER => true,
]);
$response = curl_exec($ch);
C# HttpClient
using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new System.Net.Http.Headers.AuthenticationHeaderValue("Bearer", "omx_live_xxx");
var json = @"{
    ""model"": ""text-embedding-004"",
    ""input"": ""Customer support knowledge base paragraph."",
    ""dimensions"": 1024
}";
var response = await client.PostAsync("http://omixa.cloud/api/v1/embeddings", new StringContent(json, System.Text.Encoding.UTF8, "application/json"));
var body = await response.Content.ReadAsStringAsync();
Go net/http
payload := []byte(`{
    "model": "text-embedding-004",
    "input": "Customer support knowledge base paragraph.",
    "dimensions": 1024
}`)
req, _ := http.NewRequest("POST", "http://omixa.cloud/api/v1/embeddings", bytes.NewReader(payload))
req.Header.Set("Authorization", "Bearer omx_live_xxx")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
Production checklist

Operational notes

  • Authenticate with `Authorization: Bearer omx_live_xxx`.
  • Omixa handles provider keys, routing, billing, failover, and usage recording behind this endpoint.
  • Google Vertex requests use active Vertex accounts configured by the admin; Omixa retries the next healthy account when a route fails before output starts.
Copied Markdown