Prompt Enhancement rewrites your prompt before it reaches the AI model. It detects what kind of question you are asking, strips ambiguity, and adds structure — all in milliseconds, with no extra API call and no stored data.

How It Works

When you enable enhancement, RoutePlex detects the intent behind your prompt and rewrites it with targeted improvements — adding structure, specificity, and context that lead to better model responses.

For example:

A vague coding question gets language context, edge-case hints, and output format guidance
A debugging prompt gets error framing and reproduction steps
An analysis request gets structured criteria and comparison framework
A writing prompt gets tone, audience, and length guidance

Enhancement is skipped automatically if your prompt is already detailed enough.

Using with SDKs

Python SDK

python

from routeplex import RoutePlex

client = RoutePlex(api_key="YOUR_API_KEY")

# Enable per request
response = client.chat("fix my code", enhance_prompt=True)
print(response.output)

Node.js SDK

javascript

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

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

const response = await client.chat("fix my code", { enhancePrompt: true });
console.log(response.output);

Using with curl

bash

curl -X POST https://api.routeplex.com/api/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [{"role": "user", "content": "fix my code"}],
    "mode": "routeplex-ai",
    "enhance_prompt": true
  }'

Using with OpenAI SDK

python

from openai import OpenAI

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

response = client.chat.completions.create(
    model="routeplex-ai",
    messages=[{"role": "user", "content": "fix my code"}],
    extra_headers={"X-RoutePlex-Enhance": "true"}
)

Enhancement Response

When enhancement is applied, the response includes metadata:

json

{
  "data": {
    "output": "...",
    "enhancement": {
      "applied": true,
      "original_prompt": "fix my code"
    }
  }
}

When applied is false, the original prompt was already detailed enough and was sent unchanged.

Standalone Enhance Endpoint

Preview the enhanced prompt without making a full chat request. No API key required, completely free:

Python SDK

python

result = client.enhance("tell me about kubernetes")
if result.changed:
    print(f"Enhanced: {result.enhanced_prompt}")

Node.js SDK

javascript

const result = await client.enhance("tell me about kubernetes");
if (result.changed) {
  console.log(`Enhanced: ${result.enhancedPrompt}`);
}

curl

bash

curl -X POST https://api.routeplex.com/api/v1/chat/enhance \
  -H "Content-Type: application/json" \
  -d '{"prompt": "sort a list in python"}'

Body field: prompt (not message). Max 8000 characters.

Privacy

Enhancement is stateless — your prompt is processed in memory and immediately discarded. Nothing is stored. The standalone /enhance endpoint requires no authentication.

Try It

The Playground has an enhancement toggle that lets you see the before/after in real time.