Setup & Configuration

Account Creation

Getting started with Plexor Labs? Labs takes just a few minutes. During the research phase, all features are completely free with no credit card required.

API Key Generation

API keys authenticate your requests to Plexor Labs' gateway. You can create multiple keys for different environments (development, staging, production) or applications.

Creating Your First API Key

Using Your API Key

Include your API key in the Authorization header of every request:

Authorization: Bearer plx_your_api_key_here

curl -X POST https://api.plexor.dev/gateway/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer plx_your_api_key_here" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Routing Modes

Plexor Labs' intelligent routing system analyzes your requests and routes them to the optimal LLM provider based on your selected mode. Each mode offers a different balance between cost savings and response quality.

Setting Your Routing Mode

You can set the routing mode in three ways:

1. Per-Request Header

X-Plexor-Mode: eco

2. Account Default (Dashboard)

Set your default routing mode in the dashboard settings. This applies to all requests that don't specify a mode header.

3. Environment Variable (Claude Code)

export PLEXOR_MODE=balanced

Provider Preferences

Beyond routing modes, you can configure provider preferences to control which LLM providers Plexor Labs uses for your requests.

Available Providers

Forcing a Specific Provider

Use the X-Plexor-Provider header to route requests to a specific provider:

curl -X POST https://api.plexor.dev/gateway/anthropic/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Plexor-Provider: deepseek" \
  -d '{"model": "claude-sonnet-4-20250514", "max_tokens": 1024, "messages": [...]}'

Provider Exclusions

You can exclude specific providers from routing decisions using the dashboard settings or the X-Plexor-Exclude-Providers header:

X-Plexor-Exclude-Providers: openai,gemini

Usage Tracking & Billing

Plexor Labs provides detailed usage tracking and transparent billing. During the research phase, all usage is free, but tracking is still available to help you understand your consumption patterns.

Usage Metrics

Plexor Labs tracks the following metrics for each request:

• Input Tokens: Number of tokens in your prompt
• Output Tokens: Number of tokens in the response
• Cost (USD): Actual cost charged to you
• Savings (USD): Amount saved compared to direct API pricing
• Latency (ms): Response time from request to completion
• Provider Used: Which LLM provider handled the request
• Model Used: Specific model that generated the response

Viewing Usage Statistics

Access your usage statistics through the Dashboard or via the API:

curl https://api.plexor.dev/api/users/me/usage \
  -H "Authorization: Bearer YOUR_API_KEY"

Billing Tiers

Security Best Practices

Protecting your API keys and data is critical. Follow these best practices to secure your Plexor Labs integration.

Revoking Compromised Keys

If you believe an API key has been compromised:

1. Navigate to API Keys in your dashboard
2. Find the compromised key and click "Revoke"
3. Create a new API key immediately
4. Update your applications with the new key
5. Review recent usage for any unauthorized activity

Rate Limits & Quotas

Plexor Labs implements rate limits to ensure fair usage and system stability. Rate limits apply per API key.

Rate Limit Headers

Plexor Labs returns rate limit information in response headers:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1704067200

Handling Rate Limits

When you exceed rate limits, Plexor Labs returns a 429 Too Many Requests response. Implement exponential backoff in your application:

import time
import random

def make_request_with_retry(request_fn, max_retries=5):
    for attempt in range(max_retries):
        response = request_fn()
        if response.status_code != 429:
            return response

        # Exponential backoff with jitter
        wait_time = (2 ** attempt) + random.uniform(0, 1)
        time.sleep(wait_time)

    raise Exception("Max retries exceeded")

Dashboard Features

The Plexor Labs dashboard provides comprehensive visibility into your API usage, costs, and savings.

Accessing the Dashboard

Visit /dashboard after logging in to access all dashboard features. The dashboard is accessible from any device with a modern web browser.

Frequently Asked Questions

Next Steps

Now that you've set up your Plexor Labs account, explore these resources to get the most out of intelligent LLM routing:

• HTTP API Reference - Complete API documentation with all endpoints and parameters
• Claude Code Integration - Use Plexor Labs with Claude Code CLI for development
• MCP Server Setup - Connect via Model Context Protocol
• Dashboard - Monitor your usage and track savings in real-time