Qwen: Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b
80th smartest of 182ReasoningToolsJSONVision
Intelligence
32.3
80th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.260
124th cheapest
Context
262K
66K max out
How it compares
Smarter than56%
of all ranked models
Cheaper than63%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis79th percentile
Intelligence Index
32.3
Coding Index
45.7
GPQA Diamond
86%
Humanity's Last Exam
23%
SciCode
42%
Tau²-Bench (agentic)
94%
Providers & pricing (5)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| SiliconFlowfp8 | $0.260 | $2.08 | 262K | 100% |
| Alibabafp8 | $0.260 | $2.08 | 262K | 99.9% |
| DeepInfrafp4 | $0.290 | $2.40 | 262K | 82.1% |
| AtlasCloudfp8 | $0.300 | $2.40 | 262K | 99.8% |
| Novitabf16 | $0.400 | $3.20 | 262K | 99.7% |
Specifications
Context window262K
Max output66K
Knowledge cutoff—
Input modalitiestext, image, video
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3.5-122B-A10B ↗
Qwen3.5-122B-A10B FAQ
How much does Qwen3.5-122B-A10B cost?
Qwen3.5-122B-A10B costs $0.260 per million input tokens and $2.08 per million output tokens via OpenRouter, making it 124th cheapest of 332 paid models.
How smart is Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B scores 32.3 on the Artificial Analysis Intelligence Index, ranking 80th of 182 benchmarked models, with a GPQA Diamond score of 86%.
What is Qwen3.5-122B-A10B's context window?
Qwen3.5-122B-A10B supports a 262K-token context window and can output up to 66K tokens. It accepts text, image, video input.