AI model comparison

Qwen3.5-35B-A3B vs Qwen3.5 397B A17B

Side by side comparison of Qwen3.5-35B-A3B and Qwen3.5 397B A17B on pricing, benchmark scores, context window, and more.

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.

Input / 1M
$0.14
Output / 1M
$1
Context
262K

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.

Input / 1M
$0.45
Output / 1M
$3
Context
262K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

qwen logo

Qwen3.5-35B-A3B

3.1x cheaper for a typical chat

Higher intelligence score

qwen logo

Qwen3.5 397B A17B

21.4 vs 19.3 on Artificial Analysis

Larger context window

Tie

262K vs 262K tokens

Newer release

qwen logo

Qwen3.5-35B-A3B

Released February 25, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

qwen logoQwen3.5-35B-A3B19.3
qwen logoQwen3.5 397B A17B21.4

Coding index

qwen logoQwen3.5-35B-A3B37
qwen logoQwen3.5 397B A17B48.2

Agentic index

qwen logoQwen3.5-35B-A3BNot available
qwen logoQwen3.5 397B A17B8.3

Pricing

Qwen3.5-35B-A3B vs Qwen3.5 397B A17B API pricing

Per-token API rates. Cheaper option highlighted.

Metricqwen logoQwen3.5-35B-A3Bqwen logoQwen3.5 397B A17B
Input tokensPer 1M tokens$0.14$0.45
Output tokensPer 1M tokens$1$3
Cached input (read)Per 1M tokens$0.05$0.22
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

qwen logoQwen3.5-35B-A3B$0.78
qwen logoQwen3.5 397B A17B$2.40

Coding task

30K in, 4K out

qwen logoQwen3.5-35B-A3B$8.20$5.50 cached
qwen logoQwen3.5 397B A17B$25.50$18.60 cached

Long document summary

150K in, 2K out

qwen logoQwen3.5-35B-A3B$23$9.50 cached
qwen logoQwen3.5 397B A17B$73.50$39 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricqwen logoQwen3.5-35B-A3Bqwen logoQwen3.5 397B A17B
Context window262K tokens262K tokens
Max output82K tokens82K tokens
Input typesImage, Text, VideoImage, Text, Video
Output typesTextText
Reasoning effort levelsNot availableNot available
Default reasoning effortNot availableNot available
Release dateFebruary 25, 2026February 16, 2026

Features

Supported features

API features available for each model.

Metricqwen logoQwen3.5-35B-A3Bqwen logoQwen3.5 397B A17B
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Qwen3.5-35B-A3B is 3.1x cheaper for a typical chat. Qwen3.5 397B A17B scores higher on the Artificial Analysis Intelligence Index (21.4 vs 19.3). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Qwen3.5-35B-A3B or Qwen3.5 397B A17B cheaper?

Qwen3.5-35B-A3B is cheaper for a typical chat (2K input tokens and 500 output tokens). Qwen3.5-35B-A3B costs $0.14 per 1M input tokens and $1 per 1M output tokens, while Qwen3.5 397B A17B costs $0.45 per 1M input tokens and $3 per 1M output tokens.

Which has a bigger context window, Qwen3.5-35B-A3B or Qwen3.5 397B A17B?

Qwen3.5-35B-A3B supports up to 262K tokens of context, compared with 262K for Qwen3.5 397B A17B.

Is Qwen3.5-35B-A3B smarter than Qwen3.5 397B A17B?

On the Artificial Analysis Intelligence Index, Qwen3.5-35B-A3B scores 19.3 and Qwen3.5 397B A17B scores 21.4, putting Qwen3.5 397B A17B ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Qwen3.5-35B-A3B and Qwen3.5 397B A17B at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3.5-35B-A3B and Qwen3.5 397B A17B answer side by side and keep the better response.

qwen logoqwen logo

Why choose? Ask both.

Send one prompt to Qwen3.5-35B-A3B and Qwen3.5 397B A17B at the same time. Compare the answers side by side and keep the best one.