Zorveus Documentation

Overview of OpenAI-compatible inference capabilities supported on api.zorveus.com/v1.

Zorveus routes AI inference requests through a high-performance proxy on https://api.zorveus.com/v1. It supports the OpenAI SDK specification across text generation, reasoning, multimodal inputs, structured responses, embeddings, and real-time audio.

Inference Key TesterInteractive

Paste your Zorveus key to dynamically update all code snippets below.

Supported Inference Modalities

Chat Completions

Standard and reasoning completions across OpenAI, Anthropic, Gemini, and open models.

Streaming Completions

Low-latency Server-Sent Events (SSE) token streaming.

Tool Calling & Function Calling

Structured schema execution and agentic tool invocation.

Responses API

Next-generation stateful responses and conversational threads.

Embeddings

Dense text embeddings for semantic search and retrieval (RAG).

Model Discovery

Inspect dynamically available models and routing policy status.

SDK Configuration

Point any official OpenAI client to https://api.zorveus.com/v1:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.zorveus.com/v1",
    api_key="zrv_your_inference_key",
)

Was this page helpful?

Edit this page on GitHub

Inference Overview