Overview

Quickstart

Get started with Reroute

Reroute gives you access to every model in the catalog through a single API endpoint. It prices each request against the model's listed rate and routes it to a carrier that serves the model.

Approach	Best for
API	Full control, any language, no dependencies
OpenAI SDK	Drop-in for code that already uses OpenAI
Streaming	Chat UIs that render tokens as they arrive

Looking for models that work at a zero balance? Filter the model catalog by price, or see Limits & Credits.

Create an API key

Sign up, then open Settings → Keys and create a key. The full secret starts with sk-rr-v1- and is shown exactly once; we only store its hash. Export it as REROUTE_API_KEY.

Using the Reroute API

The examples below set the model to openai/gpt-oss-20b. Any model ID from the catalog works the same way. The two app headers are optional; setting them lists your app on the app rankings.

shell

curl https://reroute.wtf/api/v1/chat/completions \
  -H "Authorization: Bearer $REROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-20b",
    "messages": [
      { "role": "user", "content": "What is the meaning of life?" }
    ]
  }'

Using the OpenAI SDK

Change the base URL and the key. Nothing else in your code needs to change.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://reroute.wtf/api/v1",
    api_key="<REROUTE_API_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-oss-20b",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
    extra_headers={
        "HTTP-Referer": "https://your-app.com",  # optional, for app rankings
        "X-Title": "Your App",                   # optional, for app rankings
    },
)

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

typescript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://reroute.wtf/api/v1",
  apiKey: process.env.REROUTE_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-oss-20b",
  messages: [{ role: "user", content: "What is the meaning of life?" }],
});

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

Streaming

Set stream: true to receive server-sent events. Every chunk carries the same gen-… ID, which is also returned in the X-Generation-Id response header; the stream ends with data: [DONE].

typescript

const stream = await client.chat.completions.create({
  model: "openai/gpt-oss-20b",
  messages: [{ role: "user", content: "Write a haiku about freight trains." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Plain fetch

Non-streaming responses include usage.cost: the amount in USD deducted from your balance for this request.

typescript

const res = await fetch("https://reroute.wtf/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.REROUTE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "openai/gpt-oss-20b",
    messages: [{ role: "user", content: "What is the meaning of life?" }],
  }),
});

const data = await res.json();
console.log(data.choices[0].message.content, data.usage.cost);

NextAuthentication