OxyRouter API

OxyRouter exposes an OpenAI-compatible chat completions API. Point an existing OpenAI SDK at the OxyRouter base URL, use an oxy_sk_... API key, and keep the rest of your integration unchanged.

Base URL

https://api.oxyrouter.in/v1

QuickstartCreate a key and send your first chat completion.

Chat completionsNon-streaming and SSE responses, tools, and vision.

ModelsList the models your key can use.

Public catalogueBrowse models and retail pricing without signing in.

What this reference covers

• Inference API — chat completions and model discovery, authenticated with API keys.
• Public catalogue — enabled models and retail USD pricing, available without authentication.
• Account API — API keys, usage and spending limits, wallet deposits, BYOK provider credentials, and referrals. These endpoints are scoped to the signed-in user and use the dashboard session cookie.

Dashboard-only and administrative endpoints are intentionally not documented here.

At a glance

Item	Value
Base URL	https://api.oxyrouter.in/v1
API key format	oxy_sk_...
Inference auth	Authorization: Bearer oxy_sk_... or X-API-Key
Account auth	Dashboard session cookie (oxy_session)
Response format	OpenAI-compatible JSON and SSE
Billing	Prepaid INR wallet, charged from provider-reported token usage
Rate limits	Per key and per account; see Errors and limits
Interactive schema	api.oxyrouter.in/docs

OpenAI SDK compatibility

Any client that accepts a custom base URL works. Existing request and response shapes are preserved, including tool calling, vision message parts, and streaming chunks.

Python

from openai import OpenAI

client = OpenAI(
    api_key="oxy_sk_...",
    base_url="https://api.oxyrouter.in/v1",
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)

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

Node.js

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: 'Hello' }],
})

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