Quickstart

This guide takes you from a fresh account to your first billed request.

1. Create an account and API key

Create an account at oxyrouter.in/register.
Open API keys in the dashboard and create a key.
Copy the secret immediately. It starts with oxy_sk_ and is shown only once.

The key inherits all three scopes by default: inference:read, inference:write, and usage:read. See Authentication for scope details and least-privilege guidance.

2. Set the key in your environment

export OXYROUTER_API_KEY="oxy_sk_..."

All inference requests use this header:

Authorization: Bearer oxy_sk_...

3. List available models

curl https://api.oxyrouter.in/v1/models \
  -H "Authorization: Bearer $OXYROUTER_API_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o-mini",
      "object": "model",
      "created": 1735689600,
      "owned_by": "oxyrouter"
    }
  ]
}

The model IDs returned here are the only IDs you should send. OxyRouter keeps upstream provider routing private and resolves it internally.

4. Send a chat completion

curl https://api.oxyrouter.in/v1/chat/completions \
  -H "Authorization: Bearer $OXYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Say hello in one short sentence."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OXYROUTER_API_KEY"],
    base_url="https://api.oxyrouter.in/v1",
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello in one short sentence."}],
)

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

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.OXYROUTER_API_KEY,
  baseURL: 'https://api.oxyrouter.in/v1',
})

const completion = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{ role: 'user', content: 'Say hello in one short sentence.' }],
})

console.log(completion.choices[0].message.content)

A successful response looks like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1735689600,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 8,
    "total_tokens": 22
  }
}

The model field always echoes the public OxyRouter model ID you requested.

5. Stream tokens

Set stream to true to receive server-sent events:

curl https://api.oxyrouter.in/v1/chat/completions \
  -H "Authorization: Bearer $OXYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Count to five."}],
    "stream": true
  }'

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"One"}}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":", two"}}]}

data: [DONE]

6. Check your spend

Every request is metered from provider-reported token usage and charged to your prepaid INR wallet. Open Usage and Billing & wallet in the dashboard to review spend, top up, and set daily or monthly caps.