changelog•4 min read

stealth/ox-alpha is Live on Zorveus

Zorveus Engineering•21 August 2026

stealth/ox-alpha is Live on Zorveus

The high-performance reasoning model stealth/ox-alpha is live across the Zorveus Edge gateway, official TypeScript and Python SDKs, and connected application endpoints.

Featuring a 1-million-token context window and a sparse Mixture-of-Experts (MoE) architecture, stealth/ox-alpha provides frontier-level coding execution, deep step-by-step reasoning, and high throughput for multi-turn agentic workflows.

# Specifications & Economics

Metric	Specification
Model ID	`stealth/ox-alpha`
Context Window	1,000,000 tokens (1M context)
Architecture	Sparse MoE (320B total parameters / 18B active)
Modalities	Text, Code, Multimodal
Primary Strengths	Long-context repo analysis, complex tool calling, agentic coding
Billing	Automatic deduction from Organization Wallet or Product-User grants

# Using stealth/ox-alpha in Zorveus

You can start making calls to stealth/ox-alpha immediately using the official Zorveus SDKs, direct cURL requests, or any OpenAI-compatible client. Select your preferred integration method from the dropdown below:

Method:

import { Zorveus } from "@zorveus/sdk";

const client = new Zorveus({
  apiKey: process.env.ZORVEUS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "stealth/ox-alpha",
  messages: [
    {
      role: "user",
      content: "Analyze this distributed lock implementation for edge-case race conditions.",
    },
  ],
  max_tokens: 4096,
});

console.log(response.choices[0].message.content);

import os
from zorveus import Zorveus

client = Zorveus(api_key=os.environ["ZORVEUS_API_KEY"])

response = client.chat.completions.create(
    model="stealth/ox-alpha",
    messages=[
        {
            "role": "user",
            "content": "Audit this database schema and identify indexing bottlenecks.",
        }
    ],
    max_tokens=4096,
)

print(response.choices[0].message.content)

curl https://api.zorveus.com/v1/chat/completions \
  -H "Authorization: Bearer $ZORVEUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stealth/ox-alpha",
    "messages": [
      {
        "role": "user",
        "content": "Analyze this distributed lock implementation for race conditions."
      }
    ],
    "max_tokens": 4096
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.zorveus.com/v1",
    api_key=os.environ["ZORVEUS_API_KEY"],
)

response = client.chat.completions.create(
    model="stealth/ox-alpha",
    messages=[
        {"role": "user", "content": "Explain raft log compaction in distributed systems."}
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.zorveus.com/v1",
  apiKey: process.env.ZORVEUS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "stealth/ox-alpha",
  messages: [
    { role: "user", content: "Explain raft log compaction in distributed systems." },
  ],
});

console.log(response.choices[0].message.content);

# Real-Time Streaming

For interactive chat applications, terminal tools, and low time-to-first-token (TTFT) agent loops, stealth/ox-alpha supports Server-Sent Event (SSE) token streaming. Select your SDK or integration method from the dropdown below:

Method:

import { Zorveus } from "@zorveus/sdk";

const client = new Zorveus({
  apiKey: process.env.ZORVEUS_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "stealth/ox-alpha",
  messages: [
    {
      role: "user",
      content: "Write a high-concurrency event bus in Go.",
    },
  ],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

import os
from zorveus import Zorveus

client = Zorveus(api_key=os.environ["ZORVEUS_API_KEY"])

stream = client.chat.completions.create(
    model="stealth/ox-alpha",
    messages=[
        {"role": "user", "content": "Refactor this async handler to use guard clauses."}
    ],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

curl -N https://api.zorveus.com/v1/chat/completions \
  -H "Authorization: Bearer $ZORVEUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stealth/ox-alpha",
    "messages": [
      {
        "role": "user",
        "content": "Write a high-concurrency event bus in Go."
      }
    ],
    "stream": true
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.zorveus.com/v1",
    api_key=os.environ["ZORVEUS_API_KEY"],
)

stream = client.chat.completions.create(
    model="stealth/ox-alpha",
    messages=[
        {"role": "user", "content": "Write a high-concurrency event bus in Go."}
    ],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.zorveus.com/v1",
  apiKey: process.env.ZORVEUS_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "stealth/ox-alpha",
  messages: [
    { role: "user", content: "Write a high-concurrency event bus in Go." },
  ],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

# Large Context Window & Caching

With a 1-million-token context window, stealth/ox-alpha can process entire codebases, multi-chapter books, or full system logs in a single prompt.

When routing high-volume queries through Zorveus:

Automatic Prefix Caching: Prompt prefixes repeated across multiple requests receive automated gateway cache discounts.
BYOK Routing & Failover: Organizations configured with custom keys can route stealth/ox-alpha traffic through their own accounts with automated fallback to the Zorveus Organization Wallet.
Credit Enforcement: Control user budgets using strict or fallback credit rules configured on your inference keys.

stealth/ox-alpha is enabled across all Zorveus accounts today.

Discuss Online

Nextzorveus/qwen3.8-27b is Live on Zorveus