Qwen

Qwen3.5 122B-A10B

CTX262K

71Quality

Reasoning · Vision · Tools

Input$0.40/M

Output$3.20/M

Qwen vision-language model for visual reasoning, documents, and agent tasks

Open weightsApache 2.0795/1044

Drag to turn

QwenTextUncommon

Qwen3.5 122B-A10B

Qwen vision-language model for visual reasoning, documents, and agent tasks

qwen3.5-122b-a10b

Type: Text
Quality: 71 · Top 29% on the LMArena Text
Context window: 262,144 tokens
Max output: 65,536 tokens
Input price: $0.40 / 1M tokens
Output price: $3.20 / 1M tokens
Cache read: —
Cache write: —
Parameters: 125B (125,086,497,008)
Downloads: 700K in the last 30 days
Likes: 640
Access to weights: Open download
Released: Feb 23, 2026
Knowledge cutoff: —
Takes in: Text, Image, Audio, Video
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Open weights
License: Apache 2.0
Rarity: Uncommon
Set number: 795/1044

Open Qwen docs Weights on Hugging Face Quality 71 Where to run it 21 Evolution 6/8 Race it 36 tok/s Meet its creature Battle GLM-5

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 Qwen3.5 122B-A10B, refreshed daily from Epoch AI and LMArena.

Top 29% of the 416 models on the LMArena Text: #123.

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#123 of 416
People compare two anonymous answers and vote for the better one.1,417 rating
LMArena Text · Coding#126 of 411
The text arena’s coding prompts only.1,436 rating
LMArena Text · Math#97 of 400
The text arena’s math prompts only.1,431 rating
LMArena Text · Creative writing#144 of 414
The text arena’s creative writing prompts only.1,368 rating
LMArena WebDev#109 of 145
Each model builds a web app from the same prompt; people pick the better one.1,361 rating
LMArena Vision#70 of 165
Questions about images, voted by people.1,245 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

20 providers sell Qwen3.5 122B-A10B through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

CheapestAIHubMix$0.11 in · $0.90 out
Free to try1 providerNvidia
From the labAlibaba$0.40 in · $3.20 out
Fastest on Hugging FaceDeepInfra36 tokens/s

API providers

Provider	Input	Output	Context
NvidiaFree`qwen/qwen3.5-122b-a10b`	Free	Free	262K
AIHubMixCheapest paid`qwen3.5-122b-a10b`	$0.11	$0.90	262K
EmpirioLabs AI`qwen3-5-122b-a10b`	$0.12	$0.92	256K
Merge Gateway`qwen/qwen3.5-122b-a10b`	$0.12	$0.92	131K
OrcaRouter`qwen/qwen3.5-122b-a10b`	$0.12	$0.92	262K
Kilo Gateway`qwen/qwen3.5-122b-a10b`	$0.26	$2.08	262K
NanoGPT`qwen/qwen3.5-122b-a10b`	$0.26	$2.08	262K
OpenRouter`qwen/qwen3.5-122b-a10b`	$0.26	$2.08	262K
SiliconFlow`Qwen/Qwen3.5-122B-A10B`	$0.26	$2.08	262K
Neon`qwen35-122b-a10b`	$0.22	$2.20	262K

Show 10 more providers

Provider	Input	Output	Context
Ofox`qwen/qwen3.5-122b-a10b`	$0.29	$2.29	256K
SiliconFlow (China)`Qwen/Qwen3.5-122B-A10B`	$0.29	$2.32	262K
Deep Infra`Qwen/Qwen3.5-122B-A10B`	$0.29	$2.40	262K
AlibabaOfficial`qwen3.5-122b-a10b`	$0.40	$3.20	262K
DevPass (LLM Gateway)`qwen3.5-122b-a10b`	$0.40	$3.20	262K
Jalapeno Cloud`Qwen3.5-122B-A10B`	$0.40	$3.20	262K
LLM Gateway`novita/qwen3.5-122b-a10b`	$0.40	$3.20	262K
Mixlayer`qwen/qwen3.5-122b-a10b`	$0.40	$3.20	262K
Novita AI`qwen/qwen3.5-122b-a10b`	$0.40	$3.20	262K
TensorX`qwen/qwen3.5-122b-a10b`	$0.50	$3.50	262K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.29	$2.40	262K	36 tok/s	0.3s

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.

Qwen3.5 122B-A10B

Qwen3.5 122B-A10B

How good is it?

Leaderboards

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