Documentation

API reference

The gateway speaks the OpenAI API format. If your code works with OpenAI, it works with Nordzhi AI after changing the base URL and API key.

Base URL & authentication

Base URL: https://nordzhi.com/v1

Headers:
  Authorization: Bearer YOUR_API_KEY
  Content-Type: application/json

Create API keys from the console. Keys are shown once at creation — store them securely. Requests are billed to the wallet of the key owner.

Chat completions

POST /v1/chat/completions — create a model response for a conversation.

curl https://nordzhi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-nordzhi-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum tunneling in one sentence."}
    ],
    "temperature": 0.7
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-nordzhi-xxxxxxxx",
    base_url="https://nordzhi.com/v1",
)

resp = client.chat.completions.create(
    model="claude-sonnet-4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-nordzhi-xxxxxxxx",
  baseURL: "https://nordzhi.com/v1",
});

const resp = await client.chat.completions.create({
  model: "gemini-2.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Request fields

Field	Type	Required	Notes
`model`	string	yes	Any model ID from the catalog.
`messages`	array	yes	Standard OpenAI message array.
`stream`	boolean	no	Enables SSE streaming (see below).
`temperature`, `max_tokens`, `top_p`, `tools`…	—	no	Forwarded to the upstream provider unchanged.

List models

GET /v1/models — returns the models currently enabled on the gateway.

curl https://nordzhi.com/v1/models \
  -H "Authorization: Bearer sk-nordzhi-xxxxxxxx"

Streaming

Set "stream": true to receive server-sent events. Chunks are proxied as they arrive from the upstream provider, so your existing OpenAI streaming code works unchanged.

curl https://nordzhi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-nordzhi-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role":"user","content":"Count to five."}],
    "stream": true
  }'

Errors

HTTP	type	Meaning
401	`authentication_error`	Missing or invalid API key.
402	`billing_error`	Insufficient wallet balance — please recharge.
400	`invalid_request_error`	Malformed request or unknown model.
503	`server_error`	No upstream channel is currently serving the requested model.

{
  "error": {
    "message": "Insufficient balance. Please recharge your wallet.",
    "type": "billing_error"
  }
}

Recharging your wallet

Open the wallet and submit a recharge request with the amount you plan to send.
Our support team emails you the bank account details at your registered address.
Complete the transfer, keep the receipt, and reply to the email.
Your balance is credited as soon as the transfer is confirmed — you can watch it land in your console.

Questions? Email [email protected] or use the contact form.