The world of AI is an explosion of power, but accessing it is a maze of keys, models, and APIs. We believe getting to the magic shouldn't be part of the puzzle.
Zaguán is your single, elegant passage to the entire universe of AI. One unified API to connect you to every model you need, so you can stop juggling and start building.
Zaguán isn't just another API proxy. It's an architectural gateway that transforms complexity into elegance, connecting you to the entire AI universe through a single, unified passage.
Just as a zaguán connects street to courtyard, Zaguán connects your application to the entire universe of AI models. One beautiful entrance, infinite possibilities.
Virtual Models automatically route across multiple providers. Circuit breakers detect failures and switch providers in real-time. Built for the long architectural tradition.
Four pricing bands (A-D) let you choose the right model for each task. Use Band A for simple queries, Band C for complex reasoning. One flat monthly fee.
Drop-in OpenAI SDK replacement. One API, 15+ providers. Stop reading 15 different API docs and integrate 500+ models through one elegant architectural interface.
Introducing Virtual Models: Ultra-reliable endpoints for your most critical tasks. Now in active development and available to all Founders.
Your app crashes. Not anymore.
A Virtual Model like zaguan/deepseek-r1-0528 intelligently routes across multiple providers. If one provider is down, we automatically re-route to another. Your user never notices.
Health checks, circuit breakers, and round-robin routing built-in.
Use it just like any other model. No complex code. We handle everything.
What's Next? We're building Premium Virtual Models for SOTA commercial LLMs (GPT-5, Claude Opus, o1). As a Founder, you'll be first to test them.
Virtual Models work with the standard OpenAI SDK
Standard Call
response = client.chat.completions.create(
model="claude-3-haiku",
messages=[...]
)Virtual Model (Beta)
# One architectural passage, zero downtime
response = client.chat.completions.create(
model="zaguan/deepseek-r1-0528",
messages=[...]
)One flat monthly price. No token billing surprises, no hidden costs. You know exactly what you'll pay.
No API key management. Just sign up and start building. Zaguán's architectural design handles the complexity.
Self-sustaining infrastructure. Not a side project that'll disappear. Built for the long haul.
Full access to each provider's features - Anthropic's structured prompts, Gemini's tuning, and more.
Early users help shape the roadmap. You're not just a customer - you're helping build what comes next.
Too many developers have been burned by services that shut down. Zaguán is different:
This isn't a side project. It's my full focus.
We handle authentication, rate limits, and API versioning across all providers. You focus on shipping features.
We're looking for the first architects to join our passage. Lock in your Founder's access pricing now before we open the courtyard to the public in 1-2 months.
Lock in this price forever. Standard pricing will be 39 €/month after the first founders join.
Compare:
• ChatGPT Plus: $20/month
• Claude Pro: $20/month
• Grok (xAI): $30/month
• Perplexity Pro: $20/month
• Total for 4 chatbot services: $90/month
Premium Tiers:
• ChatGPT Pro: $200/month (GPT-4o unlimited)
• Claude Max: €90/month (Claude Opus unlimited)
• Super Grok: $300/month (unlimited access)
• Total for 3 premium services: $590/month
Zaguán Founder's: €15/month (46 models, all providers)
Savings: 83-97% vs. premium subscriptions
Your founder price is locked in forever. No price increases, ever.
Stop managing keys and start building. Get access to the last AI gateway you'll ever need.
Join our newsletter for exclusive insights on AI development, new model releases, and tips for building better AI applications.