OpenAI Compatibility

curl --request POST \
  --url https://api.example.com/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

POST

chat

completions

OpenAI Compatibility

curl --request POST \
  --url https://api.example.com/v1/chat/completions

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/v1/chat/completions"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

Elumenta provides OpenAI-compatible endpoints for text chat:

POST /v1/chat/completions — create a response, including streaming responses;
GET /v1/models — list available text models in OpenAI format.

The exact base URL is https://elumenta.ru/v1. Do not append /api or /chat/completions: the OpenAI SDK appends the endpoint path itself.

Access

Use the same nb_... API key that you use with /api/v2; you do not need a separate key. API access requires the Advanced plan or higher (t2_advanced or vip, level 3). Lower plans receive a 403 response explaining the required plan.

Complete Python example

Install the official SDK:

pip install openai

Copy the entire example and replace only the API key:

from openai import OpenAI

client = OpenAI(api_key="nb_...", base_url="https://elumenta.ru/v1")

response = client.chat.completions.create(
    model="gpt-5-nano",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain recursion in one sentence."},
    ],
)

print(response.choices[0].message.content)
billing = getattr(response, "elumenta", {}) or {}
print(f"Charged: {billing.get('tokens_spent', 'unknown')} tkn")
print(f"Balance: {billing.get('balance', 'unknown')} tkn")

The system, user, and assistant roles are supported, as are temperature and max_tokens. The final message must use the user role.

Streaming

Pass stream=True to consume response chunks as they arrive:

stream = client.chat.completions.create(
    model="gpt-5-nano",
    messages=[{"role": "user", "content": "Name three planets."}],
    stream=True,
)

for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

    billing = getattr(chunk, "elumenta", {}) or {}
    if billing:
        print(f"\nCharged: {billing.get('tokens_spent', 'unknown')} tkn")
        print(f"Balance: {billing.get('balance', 'unknown')} tkn")

The elumenta object arrives in the final stream chunk. Its tokens_spent and balance fields are included only when their values are known, so read them with .get() as shown above. The object can be empty, for example when streaming reconciliation does not run for a web session.

Call cost

Each synchronous response contains two adjacent objects:

usage — exactly the three standard OpenAI fields: prompt_tokens, completion_tokens, and total_tokens;
elumenta.tokens_spent — the tkn actually charged for this call after reconciliation with the provider’s real usage, when known;
elumenta.balance — the balance remaining after the charge, when known.

Either cost field may be absent, and elumenta may be an empty object when neither value is known. In streaming mode Elumenta cannot completely populate usage, because the completion event does not contain the input and output token counts. To keep the response shape consistent in both modes, cost fields are placed alongside usage in elumenta, rather than inside usage. For synchronous HTTP responses, X-RateLimit-Limit contains the request limit and X-Token-Balance contains the token balance. Streaming responses do not include X-Token-Balance: headers are sent before the stream finishes, while the final charge is not yet known. Read the current balance from elumenta.balance in the final chunk instead.

List models

models = client.models.list()
for model in models.data:
    print(model.id)

GET /v1/models follows the OpenAI format and therefore does not include pricing; this is how the OpenAI specification is structured. Elumenta prices are available from GET /api/v2/models. For images, video, audio, and other capabilities, use the unified Elumenta API.

Getting Started

Concepts

Guides

Generate

Generations (results)