changelog•4 min read

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

Zorveus Engineering•14 September 2026

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

The high-throughput reasoning model zorveus/qwen3.8-27b is live across all Zorveus Edge gateways, official SDKs, and connected application endpoints.

Featuring a 128,000-token context window and support for runtime thinking controls, zorveus/qwen3.8-27b combines deep reasoning with fast time-to-first-token performance. Whether powering customer-facing chat assistants, structured data extraction, or code analysis loops, the model delivers strong benchmark performance and is currently free to use across all Zorveus accounts during its introductory preview.

# Specifications & economics

Metric	Specification
Model ID	`zorveus/qwen3.8-27b`
Context Window	128,000 tokens (128K context)
Architecture	Dense Transformer (27B parameters)
Modalities	Text, Code, Structured JSON
Reasoning Controls	Configurable via `chat_template_kwargs.enable_thinking`
Strengths	Agentic workflows, high-throughput streaming, structured outputs
Pricing	Free during preview ($0.00 / 1M tokens)

# Controlling thinking mode

One of the key capabilities of zorveus/qwen3.8-27b is runtime control over its reasoning behavior. By default, the model can emit internal thought tokens to work through multi-step logic before producing its final answer.

For low-latency interactions or concise API responses where reasoning tokens are unnecessary, you can disable thinking mode using chat_template_kwargs.

# Disabling thinking mode

Set enable_thinking to false in your request parameters:

OpenAI Node / TypeScript SDK: Pass inside extra_body.chat_template_kwargs.
OpenAI Python SDK: Pass via extra_body={"chat_template_kwargs": {"enable_thinking": False}}.
REST / cURL: Include "chat_template_kwargs": {"enable_thinking": false} at the root of your JSON body.

When disabled, the model immediately outputs the final response, avoiding reasoning token generation and reducing latency.

# Using zorveus/qwen3.8-27b in Zorveus

You can start making calls to zorveus/qwen3.8-27b immediately using the official Zorveus SDKs, standard OpenAI client libraries, or direct HTTP requests. Select your integration method from the tabs 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: "zorveus/qwen3.8-27b",
  messages: [
    {
      role: "user",
      content: "Explain distributed consensus in two concise paragraphs.",
    },
  ],
  extra_body: {
    chat_template_kwargs: { enable_thinking: false },
  },
  max_tokens: 1024,
});

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="zorveus/qwen3.8-27b",
    messages=[
        {
            "role": "user",
            "content": "Explain distributed consensus in two concise paragraphs.",
        }
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
    max_tokens=1024,
)

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": "zorveus/qwen3.8-27b",
    "messages": [
      {
        "role": "user",
        "content": "Explain distributed consensus in two concise paragraphs."
      }
    ],
    "chat_template_kwargs": {
      "enable_thinking": false
    },
    "max_tokens": 1024
  }'

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="zorveus/qwen3.8-27b",
    messages=[
        {"role": "user", "content": "Explain distributed consensus in two concise paragraphs."}
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
    max_tokens=1024,
)

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: "zorveus/qwen3.8-27b",
  messages: [
    { role: "user", content: "Explain distributed consensus in two concise paragraphs." },
  ],
  extra_body: {
    chat_template_kwargs: { enable_thinking: false },
  },
  max_tokens: 1024,
});

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

# Real-time streaming

For conversational user interfaces, terminal tools, and low time-to-first-token agent loops, zorveus/qwen3.8-27b provides Server-Sent Event (SSE) streaming with fast token emission:

Method:

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

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

const stream = await client.chat.completions.create({
  model: "zorveus/qwen3.8-27b",
  messages: [
    {
      role: "user",
      content: "Write a thread-safe cache in TypeScript with TTL eviction.",
    },
  ],
  stream: true,
  extra_body: {
    chat_template_kwargs: { enable_thinking: false },
  },
});

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="zorveus/qwen3.8-27b",
    messages=[
        {"role": "user", "content": "Write a thread-safe cache in Python with TTL eviction."}
    ],
    stream=True,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)

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": "zorveus/qwen3.8-27b",
    "messages": [
      {
        "role": "user",
        "content": "Write a thread-safe cache in Python with TTL eviction."
      }
    ],
    "stream": true,
    "chat_template_kwargs": {
      "enable_thinking": false
    }
  }'

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="zorveus/qwen3.8-27b",
    messages=[
        {"role": "user", "content": "Write a thread-safe cache in Python with TTL eviction."}
    ],
    stream=True,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)

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: "zorveus/qwen3.8-27b",
  messages: [
    { role: "user", content: "Write a thread-safe cache in TypeScript with TTL eviction." },
  ],
  stream: true,
  extra_body: {
    chat_template_kwargs: { enable_thinking: false },
  },
});

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

# Free preview & workspace controls

zorveus/qwen3.8-27b is currently free to use with zero wallet balance or deposit required. You can generate an API key and start streaming completions immediately.

When building production and multi-tenant applications on Zorveus:

Per-user attribution: Every inference call can be attributed to specific internal features or end users via user metadata, providing clean usage analytics.
Hard spend caps: Pre-configure period-based hard caps to safeguard your budget when transitioning to standard billing.
Bring-Your-Own-Key (BYOK): Connect your own provider credentials with automatic fallback to your Zorveus organization wallet when upstream limits are hit.

zorveus/qwen3.8-27b is available immediately for all personal, developer, and business workspaces on Zorveus.

Discuss Online

Previousstealth/ox-alpha is Live on Zorveus Nextzorveus/gpt-oss-120b is Live on Zorveus