Skip to main content

​
About the Provider

Qwen is an AI model family developed by Alibaba Group, a major Chinese technology and cloud computing company. Through its Qwen initiative, Alibaba builds and open-sources advanced language, images and coding models under permissive licenses to support innovation, developer tooling, and scalable AI integration across applications.

​
Model Quickstart

This section helps you quickly get started with the Qwen/Qwen3-Coder-Next model on the Qubrid AI inferencing platform. To use this model, you need:
  • A valid Qubrid API key
  • Access to the Qubrid inference API
  • Basic knowledge of making API requests in your preferred language
Once authenticated with your API key, you can send inference requests to the Qwen/Qwen3-Coder-Next model and receive responses based on your input prompts. Below are example placeholders showing how the model can be accessed using different programming environments.
You can choose the one that best fits your workflow. 
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-Next",
    messages=[
      {
        "role": "user",
        "content": "Write a Python function to calculate fibonacci sequence"
      }
    ],
    max_tokens=8192,
    temperature=1,
    top_p=0.95,
    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)

​
Model Overview

Qwen3-Coder-Next is an open-weight MoE language model designed specifically for coding agents.
  • With only 3B activated parameters out of 79.7B total, it achieves performance comparable to models with 10–20x more active parameters.
  • It features a hybrid Gated Attention + Gated DeltaNet MoE architecture with 512 experts (10 active per token), 262K native context, and achieves 74.2% on SWE-Bench Verified — making it highly cost-effective for production agent deployment.

​
Model at a Glance

FeatureDetails
Model IDQwen/Qwen3-Coder-Next
ProviderAlibaba Cloud (Qwen Team)
ArchitectureHybrid Gated Attention + Gated DeltaNet MoE Transformer, 512 experts / 10 active per token, 48 layers
Model Size79.7B params (3B active)
Parameters4
Context Length262K Tokens
Release DateFebruary 1, 2026
LicenseApache 2.0
Training DataCode-centric and agent-centric corpora with long-horizon reasoning and execution failure recovery training

​
When to use?

You should consider using Qwen3 Coder Next if:
  • You need agentic software development and long-horizon coding
  • Your application requires complex tool use and function orchestration
  • You are building workflows with execution failure recovery
  • Your use case involves repository-scale navigation and bug fixing
  • You need automated testing, refactoring, and documentation
  • Your workflow involves CI/CD pipeline integration for code generation

​
Inference Parameters

Parameter NameTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output.
Temperaturenumber1Controls randomness in output.
Max Tokensnumber8192Maximum tokens to generate.
Top Pnumber0.95Controls nucleus sampling.

​
Key Features

  • 74.2% SWE-Bench Verified: 63.7% SWE-Bench Multilingual — state-of-the-art performance for an open-weight coding agent.
  • 10–20x Parameter Efficiency: Only 3B active parameters from 79.7B total, performing like 30–60B dense models.
  • Hybrid MoE Architecture: Gated Attention + Gated DeltaNet with 512 experts and 10 active per token for efficient long-context reasoning.
  • 262K Native Context: Supports repository-scale navigation, long-horizon task execution, and complex multi-file workflows.
  • Advanced Tool Calling: Complex function orchestration for production agent deployment and CI/CD integration.

​
Summary

Qwen3-Coder-Next is Alibaba’s open-weight coding agent model built for production agentic software development.
  • It uses a Hybrid Gated Attention + Gated DeltaNet MoE architecture with 79.7B total and 3B active parameters, with 512 experts and 10 active per token.
  • It achieves 74.2% on SWE-Bench Verified with 262K native context and advanced tool calling support.
  • The model delivers 10–20x parameter efficiency over comparable dense models for cost-effective agent deployment.
  • Licensed under Apache 2.0 for full commercial use.