Qwen: Qwen3 Coder 480B A35B

by qwen

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion a...

37.4 Coding Index*#17 Code Mode‡34.3 tokens/sec*$0.22/1M input tokens†
*Artificial Analysis‡Kilo Code Leaderboard†OpenRouter
Release Date
July 22, 2025
Context Window
262,144 tokens
Max Output
262,144 tokens
Input Modalities
text

Coding Performance

Coding benchmarks and performance metrics for development tasks

Coding Benchmarks

Artificial Analysis Coding Index

37.4%

Overall coding capability score

LiveCodeBench

58.5%

Real-world coding task performance

SciCode

35.9%

Scientific computing & algorithms

TerminalBench Hard

17.7%

CLI & terminal command generation

LCR (Long Context Reasoning)

42.3%

Understanding large codebases

IFBench

40.5%

Instruction following accuracy

Speed & Efficiency

Output Speed

34.3 tokens/sec

Median output tokens per second

Performance metrics from Artificial Analysis

Real-World Usage

Real-world usage statistics from the Kilo Code community

Weekly Token Usage

Mode Rankings (Last Week)

Where this model ranks for each built-in mode

Architect

Plan and design before implementation

#16

Code

Write, modify, and refactor code

#17

Ask

Get answers and explanations

#18

Debug

Diagnose and fix software issues

#18

Orchestrator

Coordinate tasks across multiple modes

#22

Real-world metrics from the Kilo Code Leaderboard

Pricing

Cost per 1 million tokens

Input Tokens
$0.22
per 1M tokens
Output Tokens
$0.95
per 1M tokens

Example Cost

Analyzing a 10,000 line codebase (≈40k input tokens, 10k output tokens) costs approximately $0.0183

Coding Capabilities

Features and parameters relevant to coding tasks

Coding Features

Function Calling
Can call external functions/APIs
Tool Choice
Control over function selection
Structured Outputs
JSON schema validation
Reasoning Tokens
Extended thinking for complex problems

Pricing details from OpenRouter

Technical Details

Architecture and implementation specifications

Model ID
qwen/qwen3-coder
Artificial Analysis Slug
qwen3-coder-480b-a35b-instruct
Created
July 23, 2025
Tokenizer
Qwen3
Input Modalities
text
Context Window
262,144 tokens
Max Completion Tokens
262,144 tokens
Input Price
$0.22 per 1M tokens
Output Price
$0.95 per 1M tokens
Content Moderation
Disabled

Ready to try Qwen: Qwen3 Coder 480B A35B?

Install Kilo Code and start using Qwen: Qwen3 Coder 480B A35B for your coding projects today. Choose from 400+ AI models with complete freedom.