We're excited to announce that Cencori is now an official adapter for TanStack AI.

This means developers using TanStack AI can now access OpenAI, Anthropic, Google, xAI, and more—all through a single, unified integration with built-in security and observability.

Why This Matters

TanStack AI is quickly becoming one of the go-to toolkits for building AI applications. It's framework-agnostic, lightweight, and designed for modern React and TypeScript workflows.

With Cencori as an adapter, you get:

Every major AI model through one SDK
Automatic PII detection and content filtering
Full request logging with tokens, cost, and latency
Provider failover when APIs go down

No need to manage multiple API keys or build your own safety layer—Cencori handles it.

Getting Started

It's two packages:

Codetext

npm install cencori @tanstack/ai

And a few lines of code:

Codetext

import { chat } from "@tanstack/ai";
import { cencori } from "cencori/tanstack";
 
for await (const chunk of chat({
  adapter: cencori("gpt-4o"),
  messages: [{ role: "user", content: "Hello!" }],
})) {
  process.stdout.write(chunk.delta);
}

Swap gpt-4o for claude-3-5-sonnet or gemini-2.5-flash—same code, different provider.

What's Next

This is just the beginning. We're working on deeper integrations with more frameworks and platforms. If you're building with TanStack AI, we'd love to hear how it goes.

Check out the docs: TanStack AI Adapter Documentation

Get your API key: cencori.com/dashboard