modelgrep
Q

Qwen: Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

40th smartest of 180ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
40.1
40th of 180
Design Elo
1242
3D
Speed
134
35th fastest
Latency
634ms
first token
Input price
$0.390
144th cheapest
Context
262K
66K max out

How it compares

Smarter than78%
of all ranked models
Faster than89%
of all ranked models
Cheaper than52%
of all ranked models

Overview

The Qwen3.5 series 397B-A17B 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. It delivers...

Benchmarks

independent · via OpenRouter
Artificial Analysis73th percentile
Intelligence Index
40.1
Coding Index
37.4
Agentic Index
53.3
GPQA Diamond
86%
Humanity's Last Exam
19%
SciCode
41%
Tau²-Bench (agentic)
84%
Design Arena · Elo4,148 tournaments
3D
1242
Website
1235
codecategories
1231
UI Component
1219
Data Viz
1219
Game Dev
1208
svg
1199

Providers & pricing (13)

ProviderIn $/MOut $/MUptime
Alibaba$0.390$2.3499.7%
Chutesfp8$0.450$3.0095.9%
DeepInfrafp8$0.450$3.0099.9%
Morph$0.500$3.5099%
Parasailfp8$0.500$3.6099.8%
AtlasCloudfp8$0.550$3.50
Phala$0.550$3.50
DigitalOcean$0.550$3.50
Novita$0.600$3.6099.2%
Together$0.600$3.6098.8%
StreamLake$0.600$3.60
GMICloudfp8$0.600$3.60
Venice$0.750$4.50

Specifications

Context window262K
Max output66K
Knowledge cutoff
Input modalitiestext, image, video
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3.5 397B A17B FAQ

How much does Qwen3.5 397B A17B cost?

Qwen3.5 397B A17B costs $0.390 per million input tokens and $2.34 per million output tokens via OpenRouter, making it 144th cheapest of 298 paid models.

How smart is Qwen3.5 397B A17B?

Qwen3.5 397B A17B scores 40.1 on the Artificial Analysis Intelligence Index, ranking 40th of 180 benchmarked models, with a GPQA Diamond score of 86%.

How fast is Qwen3.5 397B A17B?

Qwen3.5 397B A17B generates around 134 tokens per second with 634ms time-to-first-token (p50), the 35th fastest tracked model.

What is Qwen3.5 397B A17B's context window?

Qwen3.5 397B A17B supports a 262K-token context window and can output up to 66K tokens. It accepts text, image, video input.

Compare head-to-head