Build a Chat App | OpenDunes Docs

The OpenDunes API is OpenAI-compatible, so your existing OpenAI SDK work unchanged — just swap the base URL and key. Below is everything you need to go from zero to a working streaming chat in under five minutes.

What you'll build#

A small script that sends a user message to a model, streams the response token-by-token, and prints it to the terminal. You can extend this into a web app by piping the same SSE stream to a browser client.

Prerequisites#

An OpenDunes account at opendunes.com.
A positive DA balance (deposit via your dashboard).
An API key from your dashboard — stored as OPENDUNES_API_KEY in your environment.

Create a key#

If this is your first time, the default key is already waiting in Dashboard → Keys. Copy it and export it:

Shell

export OPENDUNES_API_KEY="sk-0a1b2c3d..."

Send your first message#

curl https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Marhba! Say hello in one line." }]
  }'

Add streaming#

Set stream: true and iterate over the delta chunks. Each chunk carries a partial content string; the stream ends with a [DONE] sentinel.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/api/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Write a one-paragraph story set in the Sahara."}],
    stream=True,
)

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

Build a multi-turn chat#

Pass the full conversation history in messages on each request. The model has no memory between calls — you own the history array.

JavaScript

import OpenAI from "openai";
import * as readline from "readline";

const client = new OpenAI({
  baseURL: "https://opendunes.com/api/v1",
  apiKey: process.env.OPENDUNES_API_KEY,
});

const history = [
  { role: "system", content: "You are a helpful assistant that answers in Algerian Darja when possible." },
];

const rl = readline.createInterface({ input: process.stdin, output: process.stdout });

function ask() {
  rl.question("You: ", async (input) => {
    if (!input.trim()) return ask();

    history.push({ role: "user", content: input });

    const stream = await client.chat.completions.create({
      model: "google/gemini-2.5-pro",
      messages: history,
      stream: true,
    });

    process.stdout.write("Assistant: ");
    let reply = "";
    for await (const chunk of stream) {
      const piece = chunk.choices[0]?.delta?.content ?? "";
      reply += piece;
      process.stdout.write(piece);
    }
    console.log();

    history.push({ role: "assistant", content: reply });
    ask();
  });
}

ask();

Check your balance#

After each request, the response header X-Balance-Available contains your remaining balance in micro-DA (1 DA = 1,000,000 micro-DA). You can also read your live balance from Dashboard → Billing.

Next steps#

Streaming in depth — SSE event format, error chunks, usage in the final chunk.
Models catalog — Browse all available models with DA pricing.
Migrate an existing OpenAI app — One-line switch from OpenAI to OpenDunes.

curl https://opendunes.com/api/v1/chat/completions \ -H "Authorization: Bearer $OPENDUNES_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "anthropic/claude-sonnet-5", "messages": [{ "role": "user", "content": "Marhba! Say hello in one line." }] }'

Add streaming#

Set stream: true and iterate over the delta chunks. Each chunk carries a partial content string; the stream ends with a [DONE] sentinel.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/api/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Write a one-paragraph story set in the Sahara."}],
    stream=True,
)

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

Build a multi-turn chat#

Pass the full conversation history in messages on each request. The model has no memory between calls — you own the history array.

JavaScript

import OpenAI from "openai";
import * as readline from "readline";

const client = new OpenAI({
  baseURL: "https://opendunes.com/api/v1",
  apiKey: process.env.OPENDUNES_API_KEY,
});

const history = [
  { role: "system", content: "You are a helpful assistant that answers in Algerian Darja when possible." },
];

const rl = readline.createInterface({ input: process.stdin, output: process.stdout });

function ask() {
  rl.question("You: ", async (input) => {
    if (!input.trim()) return ask();

    history.push({ role: "user", content: input });

    const stream = await client.chat.completions.create({
      model: "google/gemini-2.5-pro",
      messages: history,
      stream: true,
    });

    process.stdout.write("Assistant: ");
    let reply = "";
    for await (const chunk of stream) {
      const piece = chunk.choices[0]?.delta?.content ?? "";
      reply += piece;
      process.stdout.write(piece);
    }
    console.log();

    history.push({ role: "assistant", content: reply });
    ask();
  });
}

ask();