Qwen3 Coder Plus

Alibaba Cloud · Code / LLM · Up to 1M Context · 386 tokens/s

Streaming Agentic Coding Tool Calling Long Context Code Generation Debugging

Overview

Qwen3 Coder Plus is a powerful Coding Agent built on Qwen3 by Alibaba Cloud — the cloud computing arm of Alibaba Group and creator of the Qwen model family. It excels in tool calling and environment interaction to achieve autonomous end-to-end programming, combining outstanding coding proficiency with versatile general-purpose abilities. With a Transformer decoder-only architecture, up to 1M token context, and a blazing 386 tokens/s throughput, it is purpose-built for code generation, debugging, refactoring, and API design workflows. Served instantly via the Qubrid AI Serverless API.

⚡ 386 tokens/s. Up to 1M context. Autonomous coding agent. Start building on Qubrid AI in minutes.

Model Specifications

Field	Details
Model ID	`Qwen/Qwen3-Coder-Plus`
Provider	Alibaba Cloud (Qwen Team)
Kind	Code
Architecture	Transformer decoder-only
Parameters	N/A
Context Length	Up to 1,000,000 Tokens
MoE	No
Throughput	386 tokens/s
Release Date	2025
License	Apache 2.0
Training Data	Code-focused datasets 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	$0.10
Output Tokens	$5.00

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

💡 Temperature note: Default is 0.1 — low temperature is recommended for deterministic, production-ready code generation.

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-Coder-Plus",
    messages=[
      {
        "role": "user",
        "content": "Write a Python function to calculate fibonacci sequence"
      }
    ],
    max_tokens=8962,
    temperature=0.1,
    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-Coder-Plus",
  messages: [
    {
      role: "user",
      content: "Write a Python function to calculate fibonacci sequence",
    },
  ],
  max_tokens: 8962,
  temperature: 0.1,
  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-Coder-Plus",
		"messages": []map[string]string{
			{
				"role":    "user",
				"content": "Write a Python function to calculate fibonacci sequence",
			},
		},
		"temperature": 0.1,
		"max_tokens":  8962,
		"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-Coder-Plus",
  "messages": [
    {
      "role": "user",
      "content": "Write a Python function to calculate fibonacci sequence"
    }
  ],
  "temperature": 0.1,
  "max_tokens": 8962,
  "stream": true,
  "top_p": 1
}'

Live Example

Prompt: Create me a modern Dashboard with interactive working buttons including graphs in HTML

Response:

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Analytics Dashboard</title>
    <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
    <style>
      * {
        margin: 0;
        padding: 0;
        box-sizing: border-box;
      }
      body {
        font-family: "Segoe UI", sans-serif;
        background: #0f172a;
        color: #e2e8f0;
      }
      .topbar {
        background: #1e293b;
        padding: 16px 32px;
        display: flex;
        justify-content: space-between;
        align-items: center;
        border-bottom: 1px solid #334155;
      }
      .topbar h1 {
        font-size: 1.4rem;
        color: #a78bfa;
      }
      .cards {
        display: grid;
        grid-template-columns: repeat(4, 1fr);
        gap: 16px;
        padding: 24px 32px;
      }
      .card {
        background: #1e293b;
        border-radius: 12px;
        padding: 20px;
        border: 1px solid #334155;
      }
      .card .label {
        font-size: 0.8rem;
        color: #94a3b8;
        margin-bottom: 8px;
      }
      .card .value {
        font-size: 2rem;
        font-weight: 700;
        color: #a78bfa;
      }
      .card .delta {
        font-size: 0.8rem;
        color: #34d399;
        margin-top: 4px;
      }
      .charts {
        display: grid;
        grid-template-columns: 2fr 1fr;
        gap: 16px;
        padding: 0 32px 24px;
      }
      .chart-box {
        background: #1e293b;
        border-radius: 12px;
        padding: 20px;
        border: 1px solid #334155;
      }
      .chart-box h3 {
        font-size: 0.95rem;
        color: #94a3b8;
        margin-bottom: 16px;
      }
      .btn-row {
        display: flex;
        gap: 10px;
        padding: 0 32px 24px;
      }
      .btn {
        padding: 10px 20px;
        border-radius: 8px;
        border: none;
        cursor: pointer;
        font-size: 0.85rem;
        font-weight: 600;
        transition: opacity 0.2s;
      }
      .btn:hover {
        opacity: 0.85;
      }
      .btn-primary {
        background: #7c3aed;
        color: white;
      }
      .btn-success {
        background: #059669;
        color: white;
      }
      .btn-danger {
        background: #dc2626;
        color: white;
      }
    </style>
  </head>
  <body>
    <div class="topbar">
      <h1>📊 Analytics Dashboard</h1>
      <span style="color:#94a3b8; font-size:0.85rem"
        >Last updated: just now</span
      >
    </div>

    <div class="cards">
      <div class="card">
        <div class="label">Total Revenue</div>
        <div class="value" id="revenue">$84,200</div>
        <div class="delta">↑ 12.4% vs last month</div>
      </div>
      <div class="card">
        <div class="label">Active Users</div>
        <div class="value" id="users">3,821</div>
        <div class="delta">↑ 8.1% vs last month</div>
      </div>
      <div class="card">
        <div class="label">Conversions</div>
        <div class="value" id="conv">5.7%</div>
        <div class="delta">↑ 0.3% vs last month</div>
      </div>
      <div class="card">
        <div class="label">Avg Session</div>
        <div class="value">4m 12s</div>
        <div class="delta">↓ 0.5% vs last month</div>
      </div>
    </div>

    <div class="btn-row">
      <button class="btn btn-primary" onclick="refreshData()">
        🔄 Refresh Data
      </button>
      <button class="btn btn-success" onclick="exportCSV()">
        ⬇ Export CSV
      </button>
      <button class="btn btn-danger" onclick="resetData()">✕ Reset</button>
    </div>

    <div class="charts">
      <div class="chart-box">
        <h3>Monthly Revenue</h3>
        <canvas id="lineChart"></canvas>
      </div>
      <div class="chart-box">
        <h3>Traffic Sources</h3>
        <canvas id="doughnutChart"></canvas>
      </div>
    </div>

    <script>
      const lineCtx = document.getElementById("lineChart").getContext("2d");
      const lineChart = new Chart(lineCtx, {
        type: "line",
        data: {
          labels: [
            "Jan",
            "Feb",
            "Mar",
            "Apr",
            "May",
            "Jun",
            "Jul",
            "Aug",
            "Sep",
            "Oct",
            "Nov",
            "Dec",
          ],
          datasets: [
            {
              label: "Revenue ($)",
              data: [
                42000, 47000, 51000, 46000, 58000, 63000, 70000, 67000, 74000,
                79000, 82000, 84200,
              ],
              borderColor: "#7c3aed",
              backgroundColor: "rgba(124,58,237,0.1)",
              tension: 0.4,
              fill: true,
              pointRadius: 4,
            },
          ],
        },
        options: {
          responsive: true,
          plugins: { legend: { labels: { color: "#94a3b8" } } },
          scales: {
            x: { ticks: { color: "#94a3b8" }, grid: { color: "#1e293b" } },
            y: { ticks: { color: "#94a3b8" }, grid: { color: "#334155" } },
          },
        },
      });

      const dCtx = document.getElementById("doughnutChart").getContext("2d");
      new Chart(dCtx, {
        type: "doughnut",
        data: {
          labels: ["Organic", "Paid", "Referral", "Social"],
          datasets: [
            {
              data: [42, 28, 18, 12],
              backgroundColor: ["#7c3aed", "#06b6d4", "#10b981", "#f59e0b"],
            },
          ],
        },
        options: {
          responsive: true,
          plugins: { legend: { labels: { color: "#94a3b8" } } },
        },
      });

      function refreshData() {
        const newVal = (80000 + Math.random() * 10000).toFixed(0);
        document.getElementById("revenue").textContent =
          "$" + parseInt(newVal).toLocaleString();
        document.getElementById("users").textContent = (
          3500 + Math.floor(Math.random() * 500)
        ).toLocaleString();
        lineChart.data.datasets[0].data = lineChart.data.datasets[0].data.map(
          (v) => Math.max(40000, v + (Math.random() - 0.5) * 4000),
        );
        lineChart.update();
      }

      function exportCSV() {
        const csv =
          "Month,Revenue\n" +
          [
            "Jan",
            "Feb",
            "Mar",
            "Apr",
            "May",
            "Jun",
            "Jul",
            "Aug",
            "Sep",
            "Oct",
            "Nov",
            "Dec",
          ]
            .map((m, i) => `${m},${lineChart.data.datasets[0].data[i]}`)
            .join("\n");
        const a = document.createElement("a");
        a.href = "data:text/csv," + encodeURIComponent(csv);
        a.download = "dashboard.csv";
        a.click();
      }

      function resetData() {
        document.getElementById("revenue").textContent = "$84,200";
        document.getElementById("users").textContent = "3,821";
      }
    </script>
  </body>
</html>

Try it yourself in the Qubrid AI Playground →

Playground Features

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

🧠 System Prompt

Define the model’s coding language, style conventions, and output format before the conversation begins — essential for consistent autonomous coding sessions.

Example: "You are a senior full-stack engineer. Always write production-ready
code with proper error handling, type annotations, and inline comments.
Prefer functional patterns and include usage examples at the end."

Set your system prompt once in the Qubrid Playground and it applies across every turn of the conversation.

🎯 Few-Shot Examples

Establish your preferred code style and output format with concrete examples — no fine-tuning required.

User Input	Assistant Response
`Implement binary search tree in Go`	`type Node struct { Val int; Left, Right Node }; func insert(root Node, val int) *Node { if root == nil { return &Node{Val: val} }; if val < root.Val { root.Left = insert(root.Left, val) } else { root.Right = insert(root.Right, val) }; return root }`
`Explain async/await vs Promises in JavaScript`	`Promises use .then()/.catch() chains. async/await is syntactic sugar over Promises — it makes async code read like sync code. Both resolve to the same microtask queue behavior; async/await is preferred for readability in modern codebases.`

💡 Add few-shot examples in the Qubrid Playground to lock in code style, language preference, and output format — no fine-tuning required.

Inference Parameters

Parameter	Type	Default	Description
Streaming	boolean	`true`	Enable streaming responses for real-time output
Temperature	number	`0.1`	Lower temperature for more deterministic code generation
Max Tokens	number	`8962`	Maximum number of tokens the model can generate
Top P	number	`1`	Controls nucleus sampling for more predictable output

Use Cases

Code generation
Debugging
Refactoring
API design

Strengths & Limitations

Strengths	Limitations
Very strong coding ability across multiple languages	Less creative for storytelling or open-ended generation
Good long-context handling — up to 1M tokens	Function calling not supported via API
Autonomous coding agent with tool calling capability	Parameter count not publicly disclosed
386 tokens/s throughput for fast code generation
Apache 2.0 — fully open-source with 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
⚡ 386 tokens/s — Qwen3 Coder Plus’s high throughput is fully realized on Qubrid’s low-latency infrastructure
🧪 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 support — Python, JavaScript, Go, cURL out of the box

Resources

Resource	Link
📖 Qubrid Docs	docs.platform.qubrid.com
🎮 Playground	Try Qwen3 Coder Plus live
🔑 API Keys	Get your API Key
🤗 Hugging Face	Qwen/Qwen3-Coder-Plus
💬 Discord	Join the Qubrid Community

Built with ❤️ by Qubrid AI

Frontier models. Serverless infrastructure. Zero friction.

Getting started

GPU Compute

Inferencing

Qubrid AI Models

AI Tools

Overview

Model Specifications

Pricing

Quickstart

Prerequisites

Python

JavaScript

Go

cURL

Live Example

Playground Features

🧠 System Prompt

🎯 Few-Shot Examples

Inference Parameters

Use Cases

Strengths & Limitations

Why Qubrid AI?

Resources

Getting started

GPU Compute

Inferencing

Qubrid AI Models

AI Tools

​Overview

​Model Specifications

​Pricing

​Quickstart

​Prerequisites

​Python

​JavaScript

​Go

​cURL

​Live Example

​Playground Features

​🧠 System Prompt

​🎯 Few-Shot Examples

​Inference Parameters

​Use Cases

​Strengths & Limitations

​Why Qubrid AI?

​Resources

Overview

Model Specifications

Pricing

Quickstart

Prerequisites

Python

JavaScript

Go

cURL

Live Example

Playground Features

🧠 System Prompt

🎯 Few-Shot Examples

Inference Parameters

Use Cases

Strengths & Limitations

Why Qubrid AI?

Resources