Qwen

Qwen3 32B

CTX131K

54Quality

Reasoning · Tools

Input$0.70/M

Output$2.80/M

Dense open Qwen model for self-hosted chat, reasoning, and coding

Open weightsApache 2.0525/1044

Drag to turn

QwenTextUncommon

Qwen3 32B

Dense open Qwen model for self-hosted chat, reasoning, and coding

qwen3-32b

Type: Text
Quality: 54 · Top 46% on the Epoch Capabilities Index
Context window: 131,072 tokens
Max output: 16,384 tokens
Input price: $0.70 / 1M tokens
Output price: $2.80 / 1M tokens
Cache read: —
Cache write: —
Parameters: 33B (32,762,123,264)
Downloads: 2.9M in the last 30 days
Likes: 770
Access to weights: Open download
Released: Apr 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: 525/1044

Open Qwen docs Weights on Hugging Face Quality 54 Where to run it 24 Evolution 5/8 Race it 48 tok/s Meet its creature Battle Nova 2 Lite

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 32B, refreshed daily from Epoch AI and LMArena.

Top 46% of the 277 models on the Epoch Capabilities Index: #129.

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

Epoch Capabilities Index#129 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.138.5 index
LMArena Text#213 of 416
People compare two anonymous answers and vote for the better one.1,340 rating
LMArena Text · Coding#223 of 411
The text arena’s coding prompts only.1,357 rating
LMArena Text · Math#158 of 400
The text arena’s math prompts only.1,399 rating
LMArena Text · Creative writing#220 of 414
The text arena’s creative writing prompts only.1,297 rating

Benchmarks Epoch AI runs

Scores from Epoch AI and 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 32B through an API, and 3 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestDeep Infra$0.08 in · $0.28 out
Free to try1 provideriFlow
From the labAlibaba$0.70 in · $2.80 out
Fastest on Hugging FaceNscale48 tokens/s

API providers

Provider	Input	Output	Context
iFlowFree`qwen3-32b`	Free	Free	128K
Deep InfraCheapest paid`Qwen/Qwen3-32B`	$0.08	$0.28	41K
Kilo Gateway`qwen/qwen3-32b`	$0.08	$0.28	41K
OpenRouter`qwen/qwen3-32b`	$0.08	$0.28	131K
Abacus`Qwen/Qwen3-32B`	$0.09	$0.29	131K
NanoGPT`qwen/qwen3-32b`	$0.10	$0.30	41K
Jiekou.AI`qwen/qwen3-32b-fp8`	$0.10	$0.45	41K
DigitalOcean`alibaba-qwen3-32b`	$0.25	$0.55	33K
SiliconFlow`Qwen/Qwen3-32B`	$0.14	$0.57	131K
SiliconFlow (China)`Qwen/Qwen3-32B`	$0.14	$0.57	131K

Show 11 more providers

Provider	Input	Output	Context
Helicone`qwen3-32b`	$0.29	$0.59	131K
Amazon Bedrock`qwen.qwen3-32b-v1:0`	$0.15	$0.60	33K
Merge Gateway`qwen/qwen3-32b`	$0.15	$0.60	131K
Vercel AI Gateway`alibaba/qwen-3-32b`	$0.15	$0.60	128K
Cortecs`qwen3-32b`	$0.18	$0.70	16K
DevPass (LLM Gateway)`qwen3-32b`	$0.36	$0.87	41K
LLM Gateway`scx-ai/qwen3-32b`	$0.36	$0.87	33K
Pioneer`Qwen/Qwen3-32B`	$0.90	$0.90	131K
Alibaba (China)`qwen3-32b`	$0.29	$1.15	131K
AlibabaOfficial`qwen3-32b`	$0.70	$2.80	131K
Qiniu`qwen3-32b`	—	—	40K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
NscaleFastestTools	$0.08	$0.25	41K	48 tok/s	0.6s
DeepInfraTools	$0.08	$0.28	41K	18 tok/s	0.4s
Featherless	—	—	—	—	—

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.

Qwen3 32B

Qwen3 32B

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

Face off

More from Qwen

Qwen-Image-2.1-Turbo

Qwen3.8 Omni Flash

Qwen-Image-2.1

Qwen3.8 Flash

Qwen3.8-Flash-Next

Qwen3.8-2.4T-A95B

Qwen3.8-27B

Qwen3.8 Max