Qwen

Qwen3-Coder 480B-A35B Instruct

CTX262K

52Quality

Tools

Input$1.50/M

Output$7.50/M

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Open weightsApache 2.0528/1040

Drag to turn

QwenTextUncommon

Qwen3-Coder 480B-A35B Instruct

Open Qwen coding heavyweight for repository reasoning and agentic engineering

qwen3-coder-480b-a35b-instruct

Type: Text
Quality: 52 · Top 48% on the LMArena Text
Context window: 262,144 tokens
Max output: 65,536 tokens
Input price: $1.50 / 1M tokens
Output price: $7.50 / 1M tokens
Cache read: —
Cache write: —
Parameters: 480B (480,154,875,392)
Downloads: 42K in the last 30 days
Likes: 1.4K
Access to weights: Open download
Released: Apr 1, 2025
Knowledge cutoff: Apr 2025
Takes in: Text
Puts out: Text
Reasoning: No
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Uncommon
Set number: 528/1040

Open Qwen docs Weights on Hugging Face Quality 52 Where to run it 21 Evolution 2/2 Meet its creature Battle Mistral Medium 3.5

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3-Coder 480B-A35B Instruct, refreshed daily from Epoch AI and LMArena.

Top 48% of the 416 models on the LMArena Text: #200.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

LMArena Text#200 of 416
People compare two anonymous answers and vote for the better one.1,357 rating
LMArena Text · Coding#160 of 411
The text arena’s coding prompts only.1,412 rating
LMArena Text · Math#198 of 400
The text arena’s math prompts only.1,365 rating
LMArena Text · Creative writing#186 of 414
The text arena’s creative writing prompts only.1,333 rating
LMArena WebDev#126 of 144
Each model builds a web app from the same prompt; people pick the better one.1,275 rating

Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

21 providers sell Qwen3-Coder 480B-A35B Instruct through an API. Prices are per million tokens, cheapest first.

Cheapestsubmodel$0.20 in · $0.80 out
Free to try1 providerNvidia
From the labAlibaba$1.50 in · $7.50 out

API providers

Provider	Input	Output	Context
NvidiaFree`qwen/qwen3-coder-480b-a35b-instruct`	Free	Free	262K
submodelCheapest paid`Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`	$0.20	$0.80	262K
SiliconFlow`Qwen/Qwen3-Coder-480B-A35B-Instruct`	$0.25	$1.00	262K
SiliconFlow (China)`Qwen/Qwen3-Coder-480B-A35B-Instruct`	$0.25	$1.00	262K
Kilo Gateway`qwen/qwen3-coder`	$0.30	$1.00	262K
OpenRouter`qwen/qwen3-coder`	$0.30	$1.00	262K
Abacus`Qwen/Qwen3-Coder-480B-A35B-Instruct`	$0.29	$1.20	262K
Jiekou.AI`qwen/qwen3-coder-480b-a35b-instruct`	$0.29	$1.20	262K
DevPass (LLM Gateway)`qwen3-coder-480b-a35b-instruct`	$0.38	$1.55	262K
LLM Gateway`novita/qwen3-coder-480b-a35b-instruct`	$0.38	$1.55	262K

Show 11 more providers

Provider	Input	Output	Context
Eden AI`deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct`	$0.40	$1.60	262K
Merge Gateway`qwen/qwen3-coder-480b-a35b-instruct`	$0.22	$1.80	131K
Vercel AI Gateway`alibaba/qwen3-coder`	$0.22	$1.80	262K
Amazon Bedrock`qwen.qwen3-coder-480b-a35b-v1:0`	$0.45	$1.80	131K
Hugging Face`Qwen/Qwen3-Coder-480B-A35B-Instruct`	$2.00	$2.00	262K
Together AI`Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8`	$2.00	$2.00	262K
302.AI`qwen3-coder-480b-a35b-instruct`	$0.86	$3.43	262K
Alibaba (China)`qwen3-coder-480b-a35b-instruct`	$0.86	$3.44	262K
AI/ML API`alibaba/qwen3-coder-480b-a35b-instruct`	$1.38	$6.71	262K
AlibabaOfficial`qwen3-coder-480b-a35b-instruct`	$1.50	$7.50	262K
Qiniu`qwen3-coder-480b-a35b-instruct`	—	—	262K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.