Skip to main content
Qubrid AI
Alibaba Cloud ยท Chat / LLM ยท Up to 1M ContextQubrid Playground License HuggingFaceStreaming Multilingual Long Context Chat Instruction Following

Overview

Qwen3 Plus is Alibaba Cloudโ€™s balanced general-purpose model for everyday chat and analysis tasks โ€” built for speed, reliability, and broad multilingual coverage. Developed by Alibaba Cloud, the cloud computing arm of Alibaba Group and creator of the Qwen model family, it is built on a Transformer decoder-only architecture with up to 1M token context and instruction tuning on multilingual web data. Whether youโ€™re building customer support bots, automating business writing, or running ideation workflows, Qwen3 Plus delivers fast, consistent responses across languages and tasks. Served instantly via the Qubrid AI Serverless API.
๐ŸŒ Fast. Reliable. Multilingual. 1M token context. Start building on Qubrid AI in minutes.

Model Specifications

FieldDetails
Model IDQwen/Qwen3-Plus
ProviderAlibaba Cloud (Qwen Team)
KindChat / LLM
ArchitectureTransformer decoder-only
ParametersN/A
Context LengthUp to 1,000,000 Tokens
MoENo
Release Date2025
LicenseApache 2.0
Training DataMultilingual web data with instruction tuning
Function CallingNot Supported
Image SupportN/A
Serverless APIAvailable
Fine-tuningComing Soon
On-demandComing Soon
State๐ŸŸข Ready

Pricing

๐Ÿ’ณ Access via the Qubrid AI Serverless API with pay-per-token pricing. No infrastructure management required.
Token TypePrice per 1M Tokens
Input Tokens$0.40
Output Tokens$1.20

Quickstart

Prerequisites

  1. Create a free account at platform.qubrid.com
  2. Generate your API key from the API Keys section
  3. Replace QUBRID_API_KEY in the code below with your actual key

Python

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
    model="Qwen/Qwen3-Plus",
    messages=[
      {
        "role": "user",
        "content": "Explain quantum computing in simple terms"
      }
    ],
    max_tokens=4096,
    temperature=0.7,
    top_p=1,
    stream=True
)

# If stream = False comment this out
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

JavaScript

import OpenAI from "openai";

// Initialize the OpenAI client with Qubrid base URL
const client = new OpenAI({
  baseURL: "https://platform.qubrid.com/v1",
  apiKey: "QUBRID_API_KEY",
});

// Create a streaming chat completion
const stream = await client.chat.completions.create({
  model: "Qwen/Qwen3-Plus",
  messages: [
    {
      role: "user",
      content: "Explain quantum computing in simple terms",
    },
  ],
  max_tokens: 4096,
  temperature: 0.7,
  top_p: 1,
  stream: true,
});

// If stream = false comment this out
for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log("\n");

// If stream = true comment this out
console.log(stream.choices[0].message.content);

Go

package main

import (
	"bufio"
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
)

func main() {
	url := "https://platform.qubrid.com/v1/chat/completions"

	data := map[string]interface{}{
		"model": "Qwen/Qwen3-Plus",
		"messages": []map[string]string{
			{
				"role":    "user",
				"content": "Explain quantum computing in simple terms",
			},
		},
		"temperature": 0.7,
		"max_tokens":  4096,
		"stream":      true,
		"top_p":       1,
	}

	jsonData, _ := json.Marshal(data)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
	req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	res, _ := client.Do(req)
	defer res.Body.Close()

	scanner := bufio.NewScanner(res.Body)
	for scanner.Scan() {
		line := scanner.Text()
		if line != "" {
			fmt.Println(line)
		}
	}
}

cURL

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "Qwen/Qwen3-Plus",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": true,
  "top_p": 1
}'

Live Example

Prompt: Summarize the key points of the latest climate change report
Response:
Key Points โ€” Climate Change (Summary)

1. Global temperatures are rising faster than projected
   Average global surface temperature has increased by approximately 1.1ยฐC
   above pre-industrial levels. Without intervention, we are on track for
   1.5ยฐC by the early 2030s.

2. Extreme weather events are intensifying
   Heatwaves, droughts, floods, and wildfires are becoming more frequent
   and severe. Vulnerable regions โ€” particularly sub-Saharan Africa,
   South Asia, and small island states โ€” face disproportionate impacts.

3. Sea levels are accelerating
   Ice sheet loss from Greenland and Antarctica is accelerating. Sea level
   rise threatens hundreds of millions of coastal residents by 2100.

4. Emissions must peak before 2025 to limit warming to 1.5ยฐC
   Global greenhouse gas emissions need to fall 43% by 2030 (vs 2019 levels)
   to stay on the 1.5ยฐC pathway. Current commitments fall significantly short.

5. Adaptation is now unavoidable
   Even under optimistic scenarios, significant adaptation investment is
   required for agriculture, water systems, infrastructure, and public health.

6. Financing remains the critical gap
   Developing nations require $1โ€“1.3 trillion/year by 2030 in climate finance.
   Current flows represent a fraction of that need.

Bottom line: The window to avoid the worst outcomes is narrowing rapidly.
Immediate, large-scale action on emissions reduction and adaptation financing
is required across all sectors and geographies.
Try it yourself in the Qubrid AI Playground โ†’

Playground Features

The Qubrid AI Playground lets you interact with Qwen3 Plus directly in your browser โ€” no setup, no code, no cost to explore.

๐Ÿง  System Prompt

Set the modelโ€™s role, tone, and language preferences before the conversation begins โ€” ideal for multilingual customer support bots, branded writing assistants, or scoped analysis tools.
Example: "You are a multilingual customer support agent for a global SaaS
platform. Respond in the same language the user writes in. Be concise,
friendly, and always offer a next step or resolution."
Set your system prompt once in the Qubrid Playground and it applies across every turn of the conversation.

๐ŸŽฏ Few-Shot Examples

Show the model your preferred tone, format, and output style with concrete examples โ€” no fine-tuning, no retraining required.
User InputAssistant Response
Write a subject line for a product launch emailIntroducing [Product]: The smarter way to [key benefit] โ€” available now
Brainstorm 3 blog post ideas about remote work productivity1. "The 5-Hour Workday: How Deep Work Beats Longer Hours" 2. "Remote Onboarding Done Right: What the Best Teams Do Differently" 3. "Async-First: Why Your Team Doesn't Need Another Meeting"
๐Ÿ’ก Add few-shot examples in the Qubrid Playground to lock in tone, format, and domain focus โ€” no fine-tuning required.

Inference Parameters

ParameterTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output
Temperaturenumber0.7Controls randomness. Higher values mean more creative but less predictable output
Max Tokensnumber4096Maximum number of tokens to generate in the response
Top Pnumber1Nucleus sampling: considers tokens with top_p probability mass

Use Cases

  1. Customer support chatbots that resolve common issues and FAQs across multiple languages
  2. Business and marketing writing such as emails, blog posts, social copy, and internal docs
  3. Brainstorming and ideation for product features, campaign concepts, and content outlines

Strengths & Limitations

StrengthsLimitations
Fast, low-latency responses for everyday chat and analysisNot as strong as Qwen Max on hard reasoning tasks
Strong multilingual support across diverse languagesFunction calling not supported
Up to 1M token context for long conversations and documentsParameter count not publicly disclosed
Apache 2.0 license โ€” fully open-source, unrestricted commercial use

Why Qubrid AI?

  • ๐Ÿš€ No infrastructure setup โ€” serverless API, pay only for what you use
  • ๐Ÿ” OpenAI-compatible โ€” drop-in replacement using the same SDK, just swap the base URL
  • ๐ŸŒ Multilingual by design โ€” Qwen3 Plusโ€™s broad language coverage pairs perfectly with Qubridโ€™s globally accessible API
  • ๐Ÿงช Built-in Playground โ€” prototype with system prompts and few-shot examples instantly at platform.qubrid.com
  • ๐Ÿ“Š Full observability โ€” API logs and usage tracking built into the Qubrid dashboard
  • ๐Ÿ’ฌ Multi-language SDK support โ€” Python, JavaScript, Go, cURL out of the box

Resources

ResourceLink
๐Ÿ“– Qubrid Docsdocs.platform.qubrid.com
๐ŸŽฎ PlaygroundTry Qwen3 Plus live
๐Ÿ”‘ API KeysGet your API Key
๐Ÿค— Hugging FaceQwen/Qwen3-Plus
๐Ÿ’ฌ DiscordJoin the Qubrid Community

Built with โค๏ธ by Qubrid AI

Frontier models. Serverless infrastructure. Zero friction.