Qwen: Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b
82nd smartest of 182Cheaper than 79% of paidReasoningToolsJSONVision
Intelligence
31.6
82nd of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.140
71st cheapest
Context
262K
262K max out
How it compares
Smarter than55%
of all ranked models
Cheaper than79%
of all ranked models
Overview
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis78th percentile
Intelligence Index
31.6
Coding Index
41.9
GPQA Diamond
84%
Humanity's Last Exam
20%
SciCode
36%
Tau²-Bench (agentic)
95%
Providers & pricing (9)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.100 | $0.950 | 262K | 100% |
| Venicefp8 | $0.100 | $1.00 | 256K | 100% |
| AkashMLfp8 | $0.140 | $1.00 | 262K | 99.9% |
| Parasailfp8 | $0.150 | $1.00 | 262K | 99.5% |
| AtlasCloudfp8 | $0.186 | $1.11 | 262K | 99.7% |
| Phala | $0.200 | $1.27 | 262K | 75.2% |
| SiliconFlowfp8 | $0.200 | $1.60 | 262K | 97.2% |
| CoreWeavefp8 | $0.250 | $1.25 | 262K | 100% |
| Io Netfp8 | $0.325 | $2.09 | 262K | 100% |
Specifications
Context window262K
Max output262K
Knowledge cutoff—
Input modalitiestext, image, video
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3.6-35B-A3B ↗
Qwen3.6 35B A3B FAQ
How much does Qwen3.6 35B A3B cost?
Qwen3.6 35B A3B costs $0.140 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 71st cheapest of 332 paid models.
How smart is Qwen3.6 35B A3B?
Qwen3.6 35B A3B scores 31.6 on the Artificial Analysis Intelligence Index, ranking 82nd of 182 benchmarked models, with a GPQA Diamond score of 84%.
What is Qwen3.6 35B A3B's context window?
Qwen3.6 35B A3B supports a 262K-token context window and can output up to 262K tokens. It accepts text, image, video input.