Qwen: Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b
89th smartest of 182Cheaper than 78% of paidReasoningToolsJSONVision
Intelligence
29.3
89th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.140
74th cheapest
Context
262K
262K max out
How it compares
Smarter than51%
of all ranked models
Cheaper than78%
of all ranked models
Overview
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis74th percentile
Intelligence Index
29.3
GPQA Diamond
85%
Humanity's Last Exam
20%
SciCode
38%
Tau²-Bench (agentic)
89%
Providers & pricing (9)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.140 | $1.00 | 262K | 99.8% |
| AkashMLfp8 | $0.140 | $1.00 | 262K | 88.1% |
| Parasailfp8 | $0.150 | $1.00 | 262K | 99.9% |
| Alibabafp8 | $0.163 | $1.30 | 262K | 100% |
| NextBitfp8 | $0.220 | $1.40 | 262K | 81.7% |
| AtlasCloudfp8 | $0.225 | $1.80 | 262K | 99.8% |
| SiliconFlowfp8 | $0.240 | $1.80 | 262K | — |
| CoreWeavefp8 | $0.250 | $1.25 | 262K | 100% |
| Venice | $0.313 | $1.25 | 256K | 100% |
Specifications
Context window262K
Max output262K
Knowledge cutoff—
Input modalitiestext, image, video
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsQwen/Qwen3.5-35B-A3B ↗
Qwen3.5-35B-A3B FAQ
How much does Qwen3.5-35B-A3B cost?
Qwen3.5-35B-A3B costs $0.140 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 74th cheapest of 332 paid models.
How smart is Qwen3.5-35B-A3B?
Qwen3.5-35B-A3B scores 29.3 on the Artificial Analysis Intelligence Index, ranking 89th of 182 benchmarked models, with a GPQA Diamond score of 85%.
What is Qwen3.5-35B-A3B's context window?
Qwen3.5-35B-A3B supports a 262K-token context window and can output up to 262K tokens. It accepts text, image, video input.