Use your OpenAI client with ZenithAI

ZenithAI speaks the OpenAI chat format at /v1. If your code already uses the OpenAI libraries, change just two things: the base URL and the model name.

Python

from openai import OpenAI

client = OpenAI(base_url="https://dummydomain/v1", api_key="YOUR_API_KEY")
print([m.id for m in client.models.list()])

JavaScript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://dummydomain/v1", apiKey: process.env.API_KEY });
const models = await client.models.list();
console.log(models.data.map((m) => m.id));

Use Instant, Fast, Smart or Genius as the model. Any other name is refused with model_not_found.

What works

• POST /v1/chat/completions, with or without streaming
• GET /v1/models
• JSON answers with response_format; see Structured JSON output
• Images as data: URLs, on tiers whose capabilities.vision is true
• Function calling on Smart and Genius (tiers whose capabilities.tools is true)

Not available

There is no /v1/completions or /v1/responses. Requests with n other than 1, functions, function_call or logprobs are refused with a clear error.

Details and limits are in OpenAI-compatible chat.

Common questions

Does code written for the OpenAI API work with ZenithAI?

Most chat code works after two changes. Set the base URL to your server followed by /v1, and use a ZenithAI tier name such as Fast, Smart or Genius as the model.

Which OpenAI endpoints does ZenithAI support?

POST /v1/chat/completions, with or without streaming, and GET /v1/models. There is no /v1/completions or /v1/responses. For a single prompt without a message list, use the /generate endpoint.