Intelligent AI routing platform for optimizing business AI costs and performance
Sansa is an intelligent AI routing platform designed specifically for businesses building AI-powered products like customer service bots, AI agents, and other API-driven applications. It's positioned as infrastructure for AI product companies, not a consumer tool.
Sansa helps businesses optimize their AI pipeline costs and performance by intelligently routing API calls between different AI models based on real-time analysis of request complexity and performance capabilities.
You don't know if a request is simple or complex until it arrives, so every call uses your most expensive model. Without real-time classification, you can't route strategically, so you're forced to choose between quality and cost.
Sansa is essentially a lightweight machine learning model trained specifically on your data. It acts as an intelligent routing gate that makes real-time decisions about which AI model to use for each request.
Unlike generic routing systems, Sansa is trained individually for each customer. It learns from your specific usage patterns, understanding which types of requests perform equally well on less expensive models versus when your premium baseline model is truly needed.
Sansa analyzes your actual usage by shadow-testing requests on less expensive models against your baseline (premium) model, building a personalized routing model based on your unique data patterns.
For each incoming request, Sansa's trained ML gate analyzes the prompt content in real-time, determines semantic complexity and requirements, and routes to the most cost-effective model that can deliver equivalent quality. Routing decisions happen in 50ms with negligible latency.
Users set confidence thresholds for routing decisions, ensuring conservative routing where accuracy matters most.
Intelligent routing that optimizes for cost, performance, and accuracy across multiple AI providers
Selects the most efficient model in 50ms with no meaningful performance impact on applications
Full control over routing decisions with configurable confidence thresholds and performance monitoring
Starts learning and routing immediately from actual usage patterns without evaluation setup
Sansa is a separate SDK that replaces existing AI provider SDKs. Install the npm package, configure your API keys, and replace existing SDK calls with Sansa calls. No major infrastructure changes required.
// Install and import Sansa
import { Sansa } from 'sansa';
// Initialize with your API keys
const sansa = new Sansa({
apiKey: process.env.SANSA_API_KEY,
providers: {
anthropic: { apiKey: process.env.ANTHROPIC_API_KEY },
openai: { apiKey: process.env.OPENAI_API_KEY },
}
});
// Make your call - Sansa handles the routing
const result = await sansa.create({
callName: 'customer-support',
messages: [...],
llmProviders: 'auto',
llmBaseline: {
provider: 'anthropic',
model: 'claude-sonnet-4-5-20240929'
}
});Sansa targets B2B companies building AI products, not individual consumers. It's infrastructure that enables:
Sansa is built around a lightweight ML model that serves as your personal routing gate:
Unlike generic routing systems, Sansa becomes an extension of your AI infrastructure - a smart gatekeeper that's trained on your specific data and routing preferences, automatically finding the optimal cost-performance balance for each request.
Orchestrate multiple models with routing, evals, and observability
Join teams from:
saves you time and money
Intelligent routing that optimizes for cost, performance, and accuracy
Select the most efficient model in 50ms
Debug this complex TypeScript error...
Full control over what gets routed
Starts learning and routing immediately with no evaluation required
Here's a comprehensive solution with error handling...
I've created a thorough implementation that includes error management...
Use Sansa with the workflow you already have
Drop-in replacement for your existing AI provider SDKs.
// Install and import Sansa
import { Sansa } from sansa;
// Initialize with your API keys
const sansa = new Sansa({
apiKey: process.env.SANSA_API_KEY,
providers: {
anthropic: { apiKey: process.env.ANTHROPIC_API_KEY },
openai: { apiKey: process.env.OPENAI_API_KEY },
}
});
// Make your call - Sansa handles the routing
const result = await sansa.create({
// Identifies this use case for routing & analytics
callName: customer-support,
messages: [
{ role: system, content: You are a helpful assistant. },
{ role: user, content: Hello! }
],
// Auto-route across all configured providers
llmProviders: auto,
// Baseline Model:
// - Model to call by default
// - Serves as a baseline quality target
llmBaseline: {
provider: anthropic,
model: claude-sonnet-4-5-20250929,
},
});We've got answers
Join the waitlist to be among the first to access intelligent routing.