Qwen

Qwen3-Next 80B-A3B (Thinking)

CTX131K

55Quality

Reasoning · Tools

Input$0.50/M

Output$6/M

Efficient Qwen thinking model for local reasoning, math, and coding agents

Open weightsApache 2.0648/1044

Drag to turn

QwenTextUncommon

Qwen3-Next 80B-A3B (Thinking)

Efficient Qwen thinking model for local reasoning, math, and coding agents

qwen3-next-80b-a3b-thinking

Type: Text
Quality: 55 · Top 45% on the LMArena Text
Context window: 131,072 tokens
Max output: 32,768 tokens
Input price: $0.50 / 1M tokens
Output price: $6.00 / 1M tokens
Cache read: —
Cache write: —
Parameters: 81B (81,324,862,720)
Downloads: 39K in the last 30 days
Likes: 500
Access to weights: Open download
Released: Sep 1, 2025
Knowledge cutoff: Apr 2025
Takes in: Text
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Uncommon
Set number: 648/1044

Open Qwen docs Weights on Hugging Face Quality 55 Where to run it 21 Evolution 5/8 Meet its creature Battle Grok 4.7

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3-Next 80B-A3B (Thinking), refreshed daily from Epoch AI and LMArena.

Top 45% of the 416 models on the LMArena Text: #187.

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#187 of 416
People compare two anonymous answers and vote for the better one.1,368 rating
LMArena Text · Coding#180 of 411
The text arena’s coding prompts only.1,392 rating
LMArena Text · Math#160 of 400
The text arena’s math prompts only.1,398 rating
LMArena Text · Creative writing#208 of 414
The text arena’s creative writing prompts only.1,315 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-Next 80B-A3B (Thinking) through an API. Prices are per million tokens, cheapest first.

CheapestAlibaba (China)$0.14 in · $0.57 out
Free to try1 providerNvidia
From the labAlibaba$0.50 in · $2.00 out

API providers

Provider	Input	Output	Context
NvidiaFree`qwen/qwen3-next-80b-a3b-instruct`	Free	Free	262K
Alibaba (China)Cheapest paid`qwen3-next-80b-a3b-instruct`	$0.14	$0.57	131K
NanoGPT`qwen/qwen3-next-80b-a3b-thinking`	$0.15	$0.65	256K
IO.NET`Qwen/Qwen3-Next-80B-A3B-Instruct`	$0.10	$0.80	262K
Hugging Face`Qwen/Qwen3-Next-80B-A3B-Instruct`	$0.25	$1.00	262K
Deep Infra`Qwen/Qwen3-Next-80B-A3B-Instruct`	$0.09	$1.10	262K
Eden AI`deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct`	$0.09	$1.10	262K
Kilo Gateway`qwen/qwen3-next-80b-a3b-instruct`	$0.09	$1.10	262K
OpenRouter`qwen/qwen3-next-80b-a3b-instruct`	$0.09	$1.10	262K
Merge Gateway`qwen/qwen3-next-80b-a3b-instruct`	$0.10	$1.10	131K

Show 11 more providers

Provider	Input	Output	Context
Amazon Bedrock`qwen.qwen3-next-80b-a3b`	$0.15	$1.20	262K
DevPass (LLM Gateway)`qwen3-next-80b-a3b-thinking`	$0.15	$1.20	131K
LLM Gateway`vertex-openai/qwen3-next-80b-a3b-thinking`	$0.15	$1.20	131K
Neon`qwen3-next-80b-a3b-instruct`	$0.15	$1.20	131K
Vercel AI Gateway`alibaba/qwen3-next-80b-a3b-thinking`	$0.15	$1.20	262K
Helicone`qwen3-next-80b-a3b-instruct`	$0.14	$1.40	262K
Jalapeno Cloud`Qwen3-Next-80B-A3B-Thinking`	$0.15	$1.50	131K
Jiekou.AI`qwen/qwen3-next-80b-a3b-thinking`	$0.15	$1.50	66K
AI/ML API`alibaba/qwen3-next-80b-a3b-instruct`	$0.21	$1.65	129K
AlibabaOfficial`qwen3-next-80b-a3b-instruct`	$0.50	$2.00	131K
Qiniu`qwen3-next-80b-a3b-thinking`	—	—	131K

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.