Alibaba

Qwen3-Coder 480B-A35B Instruct — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCE
Input Cost
$1.5/1M
Output Cost
$7.5/1M
Context Window
262K
Max Output
66K
Knowledge Cutoff
Apr 2025
Accepts
text

Qwen3-Coder 480B-A35B Instruct is an AI model by Alibaba. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Coding Benchmarks

Website Arena ELO
117166th of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)
Design Arena ELO
113574th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)

Cost Benchmarks

Input Cost
$1.5321st of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$7.5324th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
262K108th of 451

Maximum context window size

OpenRouter API

Available from 18 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 5 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Nvidia$0$0262K
submodel$0.2$0.8262K
Merge Gateway$0.22$1.8131K
Abacus$0.29$1.2262K
Jiekou.AI$0.29$1.2262K
DevPass (LLM Gateway)$0.38$1.55262K
LLM Gateway$0.38$1.55262K
NovitaAI$0.38$1.55262K
Charm Hyper$0.445$2.145$0.2225106K
Amazon Bedrock$0.45$1.8131KSupported
302.AI$0.86$3.43262K
Alibaba (China)$0.861$3.441262K
Alibaba$1.5$7.5262KSupported
Eden AI$1.5$7.5262K
Vercel AI Gateway$1.5$7.5$0.3262KSupported
Hugging Face$2$2262KSupported
Together AI$2$2262KSupported
Qiniu262K

Qwen3-Coder 480B-A35B Instruct — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Qwen3-Coder 480B-A35B Instruct — Frequently Asked Questions

How much does Qwen3-Coder 480B-A35B Instruct cost?

Qwen3-Coder 480B-A35B Instruct costs $1.5 per 1M input tokens and $7.5 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct was created by Alibaba. It is classified as a open source model in our catalogue.

Is Qwen3-Coder 480B-A35B Instruct open source?

Yes, Qwen3-Coder 480B-A35B Instruct is an open-source model. The model weights are publicly available for download and self-hosting.