Quickstart

Create a key and make your first OpenAI-compatible request in two minutes.

Owner

Product

Version

beta-2026.07

Verified

2026-07-13

Omnious is an OpenAI-compatible API for hundreds of models. Create one key, point your existing client at Omnious, and make your first request.

1. Create an API key

Open Integrations, choose Get API Key, set a spend limit and expiry, then copy the key. It is shown only once.

export OMNIOUS_CREDIT_KEY="your-key-here"

2. Send a request

Use model: "auto" to let Omnious choose, or use any exact model ID returned by GET /v1/models.

curl https://api.omnious.xyz/v1/chat/completions \
  -H "Authorization: Bearer $OMNIOUS_CREDIT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [
      { "role": "user", "content": "Explain second-price auctions in one sentence." }
    ],
    "stream": true
  }'

3. Or use the OpenAI SDK

Keep your existing OpenAI client and change only the base URL and key.

Python

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.omnious.xyz/v1",
    api_key=os.environ["OMNIOUS_CREDIT_KEY"],
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello from Omnious"}],
)

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

TypeScript

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.omnious.xyz/v1",
  apiKey: process.env.OMNIOUS_CREDIT_KEY,
});

const response = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Hello from Omnious" }],
});

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

Next steps

• Streaming, tools, images, and request fields
• Choose models and routing priorities
• Set limits and manage API keys
• Inspect usage and receipts