curl --request POST \
--url https://gateway.omnia-voice.com/v1/embeddings \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "Qwen/Qwen3-Embedding-8B",
"input": "<unknown>",
"encoding_format": "<string>",
"dimensions": 123,
"user": "<string>"
}
'import requests
url = "https://gateway.omnia-voice.com/v1/embeddings"
payload = {
"model": "Qwen/Qwen3-Embedding-8B",
"input": "<unknown>",
"encoding_format": "<string>",
"dimensions": 123,
"user": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'Qwen/Qwen3-Embedding-8B',
input: '<unknown>',
encoding_format: '<string>',
dimensions: 123,
user: '<string>'
})
};
fetch('https://gateway.omnia-voice.com/v1/embeddings', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://gateway.omnia-voice.com/v1/embeddings",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'Qwen/Qwen3-Embedding-8B',
'input' => '<unknown>',
'encoding_format' => '<string>',
'dimensions' => 123,
'user' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://gateway.omnia-voice.com/v1/embeddings"
payload := strings.NewReader("{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://gateway.omnia-voice.com/v1/embeddings")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.omnia-voice.com/v1/embeddings")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"object": "list",
"data": [
{
"object": "embedding",
"index": 123,
"embedding": [
123
]
}
],
"model": "<string>",
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance. Please top up your wallet.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "The model 'x' does not exist or is not available.",
"type": "invalid_request_error",
"code": "model_not_found"
}
}Create embeddings
Create embedding vectors for input text. Billed on input tokens only. When the workspace has response caching enabled, identical repeat requests are served from cache at a discount (see the X-Omnia-Cache response header).
curl --request POST \
--url https://gateway.omnia-voice.com/v1/embeddings \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "Qwen/Qwen3-Embedding-8B",
"input": "<unknown>",
"encoding_format": "<string>",
"dimensions": 123,
"user": "<string>"
}
'import requests
url = "https://gateway.omnia-voice.com/v1/embeddings"
payload = {
"model": "Qwen/Qwen3-Embedding-8B",
"input": "<unknown>",
"encoding_format": "<string>",
"dimensions": 123,
"user": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'Qwen/Qwen3-Embedding-8B',
input: '<unknown>',
encoding_format: '<string>',
dimensions: 123,
user: '<string>'
})
};
fetch('https://gateway.omnia-voice.com/v1/embeddings', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://gateway.omnia-voice.com/v1/embeddings",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'Qwen/Qwen3-Embedding-8B',
'input' => '<unknown>',
'encoding_format' => '<string>',
'dimensions' => 123,
'user' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://gateway.omnia-voice.com/v1/embeddings"
payload := strings.NewReader("{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://gateway.omnia-voice.com/v1/embeddings")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.omnia-voice.com/v1/embeddings")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"Qwen/Qwen3-Embedding-8B\",\n \"input\": \"<unknown>\",\n \"encoding_format\": \"<string>\",\n \"dimensions\": 123,\n \"user\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"object": "list",
"data": [
{
"object": "embedding",
"index": 123,
"embedding": [
123
]
}
],
"model": "<string>",
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance. Please top up your wallet.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "The model 'x' does not exist or is not available.",
"type": "invalid_request_error",
"code": "model_not_found"
}
}Authorizations
Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer .
Headers
Per-request cache control (only meaningful when the workspace has response caching enabled — it can reduce caching, never enable it). no-cache: skip the cache and force a fresh model run, refreshing the stored copy. no-store: fresh run AND keep this response out of cache storage entirely. Either way the response carries X-Omnia-Cache: bypass.
no-cache, no-store Body
"Qwen/Qwen3-Embedding-8B"
A string, or an array of strings to embed in one request.
The format of the returned embeddings (e.g. float).
The number of dimensions the output embeddings should have, if the model supports it.
A stable identifier for the end user.