Documentation

#Getting Started

#Quick Start

Integrate PromptUnit in two steps. No new SDKs, no refactoring — just change your base URL and add two headers.

from openai import OpenAI

client = OpenAI(
    api_key="your-openai-key",
    base_url="https://api.promptunit.ai/proxy/openai",
    default_headers={
        "x-promptunit-key": "pu_live_xxxxxxxxxxxx",
        "x-promptunit-feature": "customer-support",
    }
)

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

import OpenAI from "openai"

const openai = new OpenAI({
  apiKey: "your-openai-key",
  baseURL: "https://api.promptunit.ai/proxy/openai",
  defaultHeaders: {
    "x-promptunit-key": "pu_live_xxxxxxxxxxxx",
    "x-promptunit-feature": "customer-support",
  },
})

const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
})

#Authentication

Two headers authenticate your requests. The PromptUnit key identifies your account; the provider key is forwarded to the upstream model provider.

* Provider keys can be configured once in the PromptUnit dashboard instead of passing them per-request. Per-request keys always take precedence.

#Feature Tagging

The x-promptunit-feature header tags each request with the product feature that made the call. This powers per-feature cost breakdowns in your dashboard — the most valuable insight for understanding where your AI spend actually goes.

Pick descriptive, consistent kebab-case names:

You can pass any string up to 64 characters. Tags appear immediately in the dashboard after the first tagged request is received.

#OpenAI Integration

#Base URL

Replace the OpenAI base URL with the PromptUnit proxy endpoint. Every other part of your SDK usage stays identical.

#SDK Wrapper

The @promptunit/sdk package provides a typed wrapper that handles headers automatically. The API surface is identical to the official OpenAI SDK.

import { PromptUnitOpenAI } from "@promptunit/sdk"

const client = new PromptUnitOpenAI({
  promptUnitKey: "pu_live_xxxxxxxxxxxx",
  openAIKey: "sk-...",
  feature: "customer-support",
})

// Exactly like the OpenAI SDK — no other changes needed
const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
})

#Anthropic Integration

#Base URL

Point your Anthropic SDK at the PromptUnit proxy endpoint to get routing, compression, prompt caching optimization, and cost tracking.

#SDK Wrapper

PromptUnitAnthropic wraps the official Anthropic SDK. Prompt cache optimization (Layer 13) is applied automatically when your system prompt is eligible.

import { PromptUnitAnthropic } from "@promptunit/sdk"

const client = new PromptUnitAnthropic({
  promptUnitKey: "pu_live_xxxxxxxxxxxx",
  anthropicKey: "sk-ant-...",
  feature: "summarization",
})

const response = await client.messages.create({
  model: "claude-opus-4-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize this document." }],
})

#Response Headers

Every proxied response is augmented with x-promptunit-* headers that expose routing decisions, costs, quality scores, and optimization results. Your application can read these headers directly, or they are automatically ingested into your dashboard.

#Inferio™ Engine

Inferio™ is the inference optimization engine that processes every request before it reaches the upstream model provider. It operates as a transparent pipeline: your request goes in, an optimized request goes out to the best-fit model, and the original response format is returned to your application unchanged.

#How Routing Works

For each request, Inferio™ computes a score across 10 dimensions:

The score vector is matched against a continuously-updated capability matrix of available models. The cheapest model whose capability profile meets your configured quality threshold receives the request. If no cheaper model qualifies, the originally requested model is used as a passthrough.

#The 22 Layers

Inferio™ runs each request through up to 22 processing layers. Not all layers fire on every request — the pipeline is conditional based on request characteristics and your configuration.

Layer numbers reflect internal pipeline position. Non-sequential numbers indicate reserved slots for layers in private beta or upcoming release.

#Limits & Billing

PromptUnit charges only on verified savings — the measurable difference between what you would have paid and what you actually paid through optimized routing.