Documentation Index
Fetch the complete documentation index at: https://docs.platform.qubrid.com/llms.txt
Use this file to discover all available pages before exploring further.
Alibaba Cloud · Chat / LLM · Up to 1M Context

Streaming Multilingual Long Context Chat Instruction Following
Overview
Qwen3 Plus is Alibaba Cloud’s balanced general-purpose model for everyday chat and analysis tasks — 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 you’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.
🌐 Fast. Reliable. Multilingual. 1M token context.
Start building on Qubrid AI in minutes.
Model Specifications
| Field | Details |
|---|
| Model ID | Qwen/Qwen3-Plus |
| Provider | Alibaba Cloud (Qwen Team) |
| Kind | Chat / LLM |
| Architecture | Transformer decoder-only |
| Parameters | N/A |
| Context Length | Up to 1,000,000 Tokens |
| MoE | No |
| Release Date | 2025 |
| License | Apache 2.0 |
| Training Data | Multilingual web data with instruction tuning |
| Function Calling | Not Supported |
| Image Support | N/A |
| Serverless API | Available |
| Fine-tuning | Coming Soon |
| On-demand | Coming Soon |
| State | 🟢 Ready |
Pricing
💳 Access via the Qubrid AI Serverless API with pay-per-token pricing. No infrastructure management required.
| Token Type | Price per 1M Tokens |
|---|
| Input Tokens | $0.40 |
| Output Tokens | $1.20 |
Quickstart
Prerequisites
- Create a free account at platform.qubrid.com
- Generate your API key from the API Keys section
- 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);
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 — Climate Change (Summary)
1. Global temperatures are rising faster than projected
Average global surface temperature has increased by approximately 1.1°C
above pre-industrial levels. Without intervention, we are on track for
1.5°C by the early 2030s.
2. Extreme weather events are intensifying
Heatwaves, droughts, floods, and wildfires are becoming more frequent
and severe. Vulnerable regions — particularly sub-Saharan Africa,
South Asia, and small island states — 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 1.5°C
Global greenhouse gas emissions need to fall 43% by 2030 (vs 2019 levels)
to stay on the 1.5°C 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 $1–1.3 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 →
Playground Features
The Qubrid AI Playground lets you interact with Qwen3 Plus directly in your browser — no setup, no code, no cost to explore.
🧠 System Prompt
Set the model’s role, tone, and language preferences before the conversation begins — 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.
🎯 Few-Shot Examples
Show the model your preferred tone, format, and output style with concrete examples — no fine-tuning, no retraining required.
| User Input | Assistant Response |
|---|
Write a subject line for a product launch email | Introducing [Product]: The smarter way to [key benefit] — available now |
Brainstorm 3 blog post ideas about remote work productivity | 1. "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" |
💡 Add few-shot examples in the Qubrid Playground to lock in tone, format, and domain focus — no fine-tuning required.
Inference Parameters
| Parameter | Type | Default | Description |
|---|
| Streaming | boolean | true | Enable streaming responses for real-time output |
| Temperature | number | 0.7 | Controls randomness. Higher values mean more creative but less predictable output |
| Max Tokens | number | 4096 | Maximum number of tokens to generate in the response |
| Top P | number | 1 | Nucleus sampling: considers tokens with top_p probability mass |
Use Cases
- Customer support chatbots that resolve common issues and FAQs across multiple languages
- Business and marketing writing such as emails, blog posts, social copy, and internal docs
- Brainstorming and ideation for product features, campaign concepts, and content outlines
Strengths & Limitations
| Strengths | Limitations |
|---|
| Fast, low-latency responses for everyday chat and analysis | Not as strong as Qwen Max on hard reasoning tasks |
| Strong multilingual support across diverse languages | Function calling not supported |
| Up to 1M token context for long conversations and documents | Parameter count not publicly disclosed |
| Apache 2.0 license — fully open-source, unrestricted commercial use | |
Why Qubrid AI?
- 🚀 No infrastructure setup — serverless API, pay only for what you use
- 🔁 OpenAI-compatible — drop-in replacement using the same SDK, just swap the base URL
- 🌐 Multilingual by design — Qwen3 Plus’s broad language coverage pairs perfectly with Qubrid’s globally accessible API
- 🧪 Built-in Playground — prototype with system prompts and few-shot examples instantly at platform.qubrid.com
- 📊 Full observability — API logs and usage tracking built into the Qubrid dashboard
- 💬 Multi-language SDK support — Python, JavaScript, Go, cURL out of the box
Resources
Built with ❤️ by Qubrid AI
Frontier models. Serverless infrastructure. Zero friction.