Quickstart

This guide gets a first OpenAI-compatible NexoRouter request working in a few minutes.

Choose a path

NexoRouter does not publish a first-party SDK yet. “OpenAI-compatible” means you can reuse the documented Chat Completions shape; it does not automatically make every SDK method compatible.

Path

What you need

• A NexoRouter account.
• Prepaid balance in Billing.
• An active API key from Dashboard -> API Keys.
• A publicly available model ID from Models.

1. Create an API key

Open Dashboard -> API Keys and create a key.

Recommended settings for a first test:

Copy the full key when it is shown. Store it in an environment variable and do not paste it into Git, screenshots, tickets, or public chat.

export NEXOROUTER_API_KEY="your_nexorouter_key"

2. Set the base URL

Use the production base URL:

https://api.nexorouter.com/v1

Most SDKs and tools want the base URL only up to /v1. Do not add /chat/completions unless the tool explicitly asks for a full endpoint.

3. Choose a model

Open Models and copy the exact model ID. Model IDs are case-sensitive.

Good first choices:

4. Send a request

curl https://api.nexorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $NEXOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [
      { "role": "system", "content": "You are a concise assistant." },
      { "role": "user", "content": "Reply with one sentence: NexoRouter is connected." }
    ],
    "temperature": 0.7,
    "max_tokens": 128
  }'

A successful response contains the answer at choices[0].message.content.

5. Use an OpenAI SDK

Use the OpenAI SDK only with an explicit NexoRouter base URL. Keeping the official OpenAI default base URL while using a NexoRouter key will fail.

Install the matching package first:

python -m pip install --upgrade openai
# or
npm install openai

Python:

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[
        {"role": "user", "content": "Reply with one sentence: NexoRouter is connected."}
    ],
)

print(response.choices[0].message.content)

Node.js / TypeScript:

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "kimi-k2.6",
  messages: [
    { role: "user", content: "Reply with one sentence: NexoRouter is connected." },
  ],
});

console.log(response.choices[0].message.content);

Environment variable style:

export OPENAI_API_KEY="$NEXOROUTER_API_KEY"
export OPENAI_BASE_URL="https://api.nexorouter.com/v1"

Use this only for local tools or apps that already read OPENAI_API_KEY and OPENAI_BASE_URL. Do not overwrite real OpenAI credentials in a shared environment.

Confirm it in the Dashboard

After the request, open Usage Logs and check:

• API key name.
• Model ID.
• Prompt and completion tokens.
• Cost in USD and quota units.
• Latency.
• Request ID.
• Success or error status.

If the first request fails

Do not send your full API key to support. Send the key name, last four characters, request ID, model ID, and approximate time.

Success checklist

• The HTTP response is 200.
• choices[0].message.content contains text.
• Usage Logs shows the expected key and model ID.
• Tokens, cost, and latency are reasonable for the request.
• The key is not present in client code, Git, or logs.
• The model was copied from the current catalog, not an old guide.

Next

• Compatible client SDKs
• Agent integration
• Build a chat app
• OpenAI-compatible API
• API Reference
• Tool integrations