Integrate RoutePlex in under 5 minutes — from zero to your first AI response.

1. Create an Account

2. Get Your API Key

After signing in, navigate to the API Keys page in your dashboard and create a new key. Keys start with rp_live_ and are shown only once — save it to a secrets manager immediately.

3. Install an SDK

bash

pip install routeplex          # Python 3.8+
npm install @routeplex/node    # Node 18+

4. Make Your First Request

Python

python

from routeplex import RoutePlex

client = RoutePlex(api_key="rp_live_YOUR_KEY")

# Auto-routing — RoutePlex analyzes your prompt and picks the best model
response = client.chat("Explain quantum computing")
print(response.output)
print(f"Model: {response.model_used}")
print(f"Cost: ${response.usage.cost_usd:.6f}")

Node.js

javascript

import { RoutePlex } from "@routeplex/node";

const client = new RoutePlex({ apiKey: "rp_live_YOUR_KEY" });

const response = await client.chat("Explain quantum computing");
console.log(response.output);
console.log(`Model: ${response.modelUsed}`);
console.log(`Cost: $${response.usage.costUsd.toFixed(6)}`);

curl

bash

curl -X POST https://api.routeplex.com/api/v1/chat \
  -H "Authorization: Bearer rp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [{"role": "user", "content": "Hello!"}],
    "mode": "routeplex-ai"
  }'

That's it. RoutePlex picked the best model for your prompt automatically.

5. Strategy Routing

Override auto-selection with a fixed priority when you know what you want:

python

response = client.chat("Write a haiku", strategy="speed")            # fastest model
response = client.chat("Review this code", strategy="quality")       # most capable
response = client.chat("Summarize this article", strategy="cost")    # cheapest

javascript

await client.chat("Write a haiku", { strategy: "speed" });

See Smart Routing for all strategies and when to use each.

6. Manual Mode

Pin a specific model when you need deterministic selection. If it's unavailable, RoutePlex automatically falls back:

python

response = client.chat("Hello!", model="gpt-4o")

javascript

await client.chat("Hello!", { model: "gpt-4o" });

7. Free Endpoints — no auth needed

python

# Estimate cost before running a request
estimate = client.estimate("Write a blog post about AI")
print(f"${estimate.estimated_cost_usd:.6f}")

# Enhance a weak prompt
result = client.enhance("tell me about kubernetes")
print(result.enhanced_prompt)

# List all available models
for m in client.list_models():
    print(f"{m.id} ({m.provider}) — {m.tier}")

OpenAI SDK Compatibility

Already using the OpenAI SDK? Just change the base_url:

python

from openai import OpenAI

client = OpenAI(
    api_key="rp_live_YOUR_KEY",
    base_url="https://api.routeplex.com/v1",
)

response = client.chat.completions.create(
    model="routeplex-ai",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Streaming, function calling, and all standard parameters work unchanged.

Next Steps

Python & Node.js SDKs — Full SDK reference
Smart Routing — How auto-selection picks models
Routing Modes — Auto vs manual mode
Cost Control — Caps, alerts, and budget guards
Examples — Real-world code patterns
API Reference — Full endpoint documentation
Playground — Try models interactively