Skip to content

Change the base URL. Keep your client.

Itzi exposes the formats used by OpenAI and Anthropic clients, plus automatic caching and built-in tools behind one API key.

One connection surface

Authenticate with a Bearer token or x-api-key. Keys are displayed once and stored only as hashes.

POST/v1/chat/completionsOpenAI Chat Completions
POST/v1/responsesOpenAI Responses
POST/v1/messagesAnthropic Messages
GET/v1/modelsCustomer model catalog

OpenAI SDK example

Streaming, custom tools, vision and standard tool choice fields follow the client format you already use.

Node.js
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ITZI_API_KEY,
  baseURL: "https://itzi.app/v1",
});

const stream = await client.chat.completions.create({
  model: "gpt-5.6-terra",
  messages: [{ role: "user", content: "Summarize this dataset" }],
  stream: true,
  // Auto Cache is enabled automatically on supported models.
});

Itzi features travel with the request.

Use the native API fields where possible, with small Itzi extensions for gateway features.

Auto Cache

Enabled by default on supported models. Disable it per request with auto_cache: false or the x-itzi-auto-cache header.

Custom and built-in tools

Send standard function tools. Web Search and Python Studio can use native tool types or the itzi_tools extension.

Streaming

All three generation endpoints support server-sent event streams.

Safe errors and inspectable logs

Client errors never expose internal providers. Your Itzi request log still shows tokens, cache state, tools and the amount charged.

Ready to connect?

Create an account, generate a key and use https://itzi.app/v1 as the base URL.

Create account