qwen3.5-122b-a10b

1417 Score third-party Elo · arena.ai / LMArena ?

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

LLM & Generative AI 1 model 3 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Cheapest DashScope no official benchmark Input$0.119 Output$0.948 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
qwen/qwen3.5-122b-a10b	OpenRouter	122b256k contextmultimodalreasoning	$0.260	$2.08
qwen3.5-122b-a10b	DashScope	122b	$0.119	$0.948
qwen/qwen3.5-122b-a10b	Novita	122b	$0.400	$3.20

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

No official Design Arena benchmark from this provider. Showing official architecture metadata only.

Input / Output modalities modality: text+image+video->text

text in+out
image input only
video input only

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
DashScope	qwen3.5-122b-a10b	$0.119	$0.948	—	—	—	2026-10-14 00:53:13
Novita	qwen/qwen3.5-122b-a10b	$0.400	$3.20	—	—	—	2026-10-14 00:54:15
OpenRouter	qwen/qwen3.5-122b-a10b	$0.260	$2.08	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	Qwen/Qwen3.5-122B-A10B-FP8	$0	$0	—	—	—	2026-10-14 00:53:13

4 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json