Qwen/Qwen3-Coder-480B-A35B-Instruct

Qwen3-Coder-480B-A35B-Instruct is Alibaba's flagship open-source coding model powered by a sparse Mixture-of-Experts (MoE) architecture with 480B total parameters and 35B activated per forward pass. It achieves state-of-the-art (SOTA) performance among open-source models, supporting up to 256K context. Ideal for agentic coding, complex refactoring, and large-scale software engineering.

Alibaba Cloud Code 256K Tokens
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

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-480B-A35B-Instruct",
  "messages": [
    {
      "role": "user",
      "content": "Write a Python function to calculate fibonacci sequence"
    }
  ],
  "temperature": 0.1,
  "max_tokens": 8192,
  "stream": true,
  "top_p": 1
}'

Technical Specifications

Model Architecture & Performance

Variant Coder Instruct
Model Size 480B params (35B active)
Context Length 256K Tokens
Quantization fp16 / bf16
Tokens/Second 80
Architecture Sparse Mixture-of-Experts (MoE) Transformer
Precision fp16 / bf16
License Apache 2.0
Release Date 2025
Developers Alibaba Cloud (QwenLM)

Pricing

Pay-per-use, no commitments

Input Tokens $0.0015/1K Tokens
Output Tokens $0.0075/1K Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.1 Lower temperature for more deterministic code generation.
max_tokens number 8192 Maximum number of tokens the model can generate.
top_p number 1 Controls nucleus sampling for more predictable output.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
SOTA open-source coding model
480B MoE with only 35B active per token
Up to 256K context window
Strong agentic and tool-calling capabilities
Apache 2.0 license
High GPU memory requirements
Higher latency than smaller variants
MoE routing may vary on niche tasks

Use cases

Recommended applications for this model

Large codebase refactoring
Multi-file code generation
Complex algorithm design
System architecture
Advanced debugging
Tool-calling agent workflows

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid scaled our personalized outreach from hundreds to tens of thousands of prospects. AI-driven research and content generation doubled our campaign velocity without sacrificing quality."

Demand Generation Team

Marketing & Sales Operations