Skip to content

Qwen3.5-122B-A10B

ModelOpen sourceActive
by Alibaba (Qwen) · family “qwen3b-a10b”

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... (description from the OpenRouter listing)

in: textin: imagein: videoout: textReasoningTool useStructured output
Epoch Capabilities Index
Not scored by Epoch AI
Listing ↗
Released
25 Feb 2026
Context window
262K tokens
Max output
236K tokens
Input $ / 1M tokens
$0.26
Output $ / 1M tokens
$2.08
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (3)

BenchmarkDomainScorevs best recordedSettingRunSource
LMCAagents32.2%
47%
none—External ↗
DTBenchreasoning84.3%
85%
none—External ↗
Mystery Game Puzzlesgames17.0% ±3.8
20%
none27 Aug 2026Epoch ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

8 recorded prices on 3 Mar 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.

Events