Two settings.
40-70% lower
AI bill.
Our estimate for apps with many simple requests, not a guarantee.
Change the API address and the key. PromptUnit routes each call to the cheapest model that handles it. Full cost visibility from day one. No other code changes.
Try live demoNo setup · 30 seconds · No API key needed
Works with
What is this?
The Inferio engine sits between your app and your AI provider and sends each request to the cheapest model that will answer it just as well.
See it in action
Before you connect anything.
Run a real prompt.
Watch how we choose the model.
See your cost drop instantly.
Try the demoThe problem
You're overpaying for AI.
And it doesn't show up anywhere obvious.
40–70%
of AI spend could be saved (our estimate)
Your app sends every call to GPT-4o. Sentiment checks, summaries, simple Q&A: a $0.30/M model handles those just as well. The difference goes straight to OpenAI.
$0
cost visibility by feature
OpenAI sends you one number. No breakdown by endpoint, feature, or call type. You can't cut what you can't see.
2 settings
to fix all of it
Not a rewrite. Not a new SDK. Change base_url and the key, and you get full visibility, automatic routing, and real savings from the first call.
See every request and what it saved.
Connect in minutes. Savings start with your first request, and you watch it happen: the model you asked for, the model that answered, and what you saved. Turn routing off anytime.
Real-time cost breakdown
Every API call logged by model, feature, and cost, the moment it happens.
Only switches when it's safe
A request moves to a cheaper model only when that model is just as good for it. Everything else stays on the model you chose.
Routing decisions explained
Know why each request was routed where, not just that it was.
This month's AI spend
$273
down 43% vs $480/mo baseline
Saved this month
$207
43% of your bill
Total API calls
48,200
this month
What-if Analysis
What each quality setting saves you.
Current monthly cost
$480
without optimization
With PromptUnit
$273
balanced routing mode
You save
$207/mo
43% of your bill
Recent Routing Decisions
Why each request was sent to the model it was.
Seconds after you connect
Your first request went through PromptUnit
You saved 94%
Example: a support ticket classified into a category. A request only moves to a cheaper model when that model is just as good for it.
How it works
Up and running in minutes
Connect
Add your provider API keys and swap your base URL. No SDK changes, no refactoring.
Takes ~5 minutesSee your first request
Send one request and watch it arrive: the model you asked for, the model that answered, and what you saved.
Within secondsSave
Every request is checked. When a cheaper model is just as good for it, we use it. Everything else stays on the model you chose.
Savings from the first requestBuilt for production
Routing is the start.
This is what comes after.
Most proxies tell you which model ran. PromptUnit tells you which feature is overpaying, warns you when quality drops, and stops runaway spend before it reaches your provider.
Feature Attribution
Tag API calls with x-promptunit-feature and see exactly what each part of your product costs: calls, spend, savings, and save rate per feature. No other proxy gives you this breakdown.
Quality Regression Alerts
PromptUnit scores every response and monitors per-task quality in real time. When a model starts degrading on your specific traffic, you get an email before your users notice. No other proxy does this automatically.
classification dropped to 58% avg quality
38 calls in the last 4 hours
Alerts fire at most once per 12 hours per task type. Rate-limited, not noisy.
Circuit Breaker Controls
Set hourly and daily spend limits. Define a spike threshold. Choose to auto-downgrade or block on anomaly. Configured in your dashboard, enforced at the proxy layer before any cost hits your provider.
All three included. No add-ons, no enterprise gate.
Pricing
We only make money when you save.
No subscription. No flat fee. We take 20% of what we save you. Nothing else.
That's it. No subscription, no flat fee. We earn only when you save.
No savings. No charge. Ever.
- Unlimited API calls proxied
- OpenAI, Anthropic, Google, Groq, DeepSeek and OpenRouter, plus Mistral, Together, Perplexity, xAI and Cohere as extra options
- Real-time cost analytics dashboard
- Smart model routing with quality guardrails
- Email spend alerts
No savings
No charge
Cancel anytime
No contracts
Free to start
No card needed
Fails safe
Retries your model
Your numbers
How much are you leaving on the table?
Drag the slider. See your estimate in seconds.
ROI Calculator
Estimate your savings
Estimates based on observed routing patterns. Actual savings depend on your traffic mix and quality threshold. Your dashboard shows the real saving on every request, and nothing is charged before we've saved you money.
Savings from your first request. No charge until we've saved you money.
Security & Privacy
Your data stays yours. Always.
We never read, store, or retain your prompt content. We do not train on your data. Ever.
Zero prompt storage
Your prompt content is never written to disk. Not to our database, not to logs. The request passes through. The content does not.
Encrypted in transit
All traffic between your app, PromptUnit, and AI providers travels over TLS 1.3. Your keys and requests are encrypted at every hop.
Keys encrypted at rest
Your provider API keys are encrypted with AES-256-GCM before being stored. Each key gets a unique random IV. Even with database access, the keys are unreadable.
No training on your data
We never use your traffic to train models or share prompt signals across customers. Quality fingerprinting is statistical, never content-based.
Two settings. Full savings.
Point your base_url at PromptUnit and use your PromptUnit key as the key. Keep every other line of code exactly as it is. PromptUnit routes calls between models automatically. Your SDK, error handling, and response parsing are untouched.
- Same OpenAI SDK, no new imports or dependencies
- If a cheaper model ever fails, we retry on the model you asked for
- Works with Python, Node.js, Go, Ruby, any HTTP client
- Remove us any time by switching the address and key back
- Privacy mode: only models, tokens, cost and timing are kept
- Only switches when a cheaper model is just as good for the request
Works with any OpenAI-compatible SDK: Python, Node, Go, Ruby
Works with any OpenAI-compatible SDK: Python, Node, Go, Ruby
Stop guessing your AI costs.
See exactly where you're wasting.
Connect in minutes. Savings start with your first request, and your dashboard shows each request and what it saved. Turn routing off anytime.
Savings from the first request · 5-minute setup · Cancel anytime
Why PromptUnit
Built different from every proxy you've tried
Other tools route requests. PromptUnit optimizes them. Before, during, and after.
| Capability | PromptUnit | LiteLLM | Cloudflare | Helicone |
|---|---|---|---|---|
| Smart routing | ✅ | Partial | ❌ | ❌ |
| Format conversion across providers | ✅ | ✅ | Partial | ❌ |
| Prompt efficiency scoringunique | ✅ | ❌ | ❌ | ❌ |
| Circuit breaker | ✅ | Partial | ❌ | Partial |
| Aligned pricing model | ✅ | ❌ | ❌ | ❌ |
Based on publicly available documentation as of April 2026. Features reflect default capabilities without custom implementation.
Pay Only From Savings
Free until PromptUnit has saved you money, then 20% of what it saves. If it saves nothing, you pay nothing, so the bill can never be larger than the savings.
You Stay in Control
Send the header x-promptunit-routing: off to keep one request on its model, or turn routing off for your whole account on your dashboard. A request kept on its model goes out with your prompts exactly as your app wrote them.
Prompt Efficiency Advisor
Scores every prompt 0–100. Tells you not just what you spent, but why you overspent and which features to fix. This turns your dashboard into an action plan.
Advanced Intelligence
Algorithms that get smarter
with every request
Five compounding intelligence layers that run on top of routing. They improve automatically as traffic grows. A new entrant starts at zero. You don't.
Prompt Complexity Classifier
Scores every prompt across 8 axes before a single token is sent. Detects reasoning depth, constraint density, and code indicators. Routes simple requests to cheap models without burning tokens on the routing decision itself.
Semantic Request Cache
Fingerprints incoming requests using normalized content hashing. Returns a cached response when an equivalent request was seen recently. Zero API cost. Hit rate compounds with volume.
High-Stakes Flag
Flags requests about medical, legal, financial, security or irreversible infrastructure topics, so your app can add its own review. Routing keeps your model for emergencies and holds medical, legal and financial requests to a stricter quality bar.
Cross-Customer Quality Oracle
Aggregates anonymized quality signals across all platform traffic to build a real-world per-model, per-task performance index. Every request across all customers trains it. No single customer can build this.
Adaptive Threshold Learning
Every night, adjusts the quality bar for each kind of request from your own results: up when answers score poorly or get repeated, down a little when they hold up. Each model's scores are corrected by how it did on your traffic.
The data flywheel
Every routing decision, quality signal, and cache hit feeds back into the system. Your routing gets more accurate the more you use it. OpenAI can't build this. Open-source proxies won't.
Features
Everything your AI stack needs
Routing, observability and cost optimization. Everything any AI-powered app needs, without building it yourself.
Smart Routing
10-dimension task classification routes every call to the cheapest model that clears your quality bar. No more paying GPT-4 prices for GPT-4o-mini tasks.
Spend Caps
Hourly and daily spending limits, $100 and $500 by default, and you can change them. When one is reached, requests stop until the window resets, so a runaway loop can't keep spending.
Every Request Itemized
The dashboard shows every request: the model asked for, the model that answered, what it cost and what it saved, grouped into the steps of your app.
Prompt Efficiency Scoring
Scores every prompt 0–100 for efficiency. Tells you not just what you spent, but why you overspent and which features to fix first.
Multi-Provider
Send requests through OpenAI, Anthropic, Google, Groq, DeepSeek or your OpenRouter key. Add Mistral, Together, Perplexity, xAI or Cohere keys and PromptUnit can switch requests to their models too.
Zero Code Change
Swap your baseURL to www.promptunit.ai. Your existing OpenAI SDK, response parsing, and error handling all continue to work exactly as before.
FAQ