Quickstart

Prerequisites

• An Omrouter account.
• An API key created on the Keys page.
• A model name copied from the Pricing page.

1. Set the API key and model

Store the API key and model name in environment variables:

export OMROUTER_API_KEY='your-api-key'
export OMROUTER_MODEL_ID='model-name-from-pricing-page'

Do not commit the real API key to Git or paste it into an agent prompt.

2. Send a request

cURL

curl --silent --show-error \
  'https://omrouter.com/v1/chat/completions' \
  --header "Authorization: Bearer $OMROUTER_API_KEY" \
  --header 'Content-Type: application/json' \
  --data "{
    \"model\": \"$OMROUTER_MODEL_ID\",
    \"messages\": [
      {\"role\": \"user\", \"content\": \"Reply with one short sentence.\"}
    ]
  }"

Python

Install the OpenAI SDK:

python -m pip install openai

example.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OMROUTER_API_KEY"],
    base_url="https://omrouter.com/v1",
)

response = client.chat.completions.create(
    model=os.environ["OMROUTER_MODEL_ID"],
    messages=[
        {"role": "user", "content": "Reply with one short sentence."}
    ],
)

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

JavaScript

Install the OpenAI SDK:

npm install openai

example.mjs

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.OMROUTER_API_KEY,
  baseURL: 'https://omrouter.com/v1',
});

const response = await client.chat.completions.create({
  model: process.env.OMROUTER_MODEL_ID,
  messages: [
    { role: 'user', content: 'Reply with one short sentence.' },
  ],
});

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

3. Read the result

After a successful request, the model reply is usually in choices[0].message.content:

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "..."
      }
    }
  ]
}

Next, read OpenAI SDKs or Configure existing applications and tools.