AI model comparison

Step 5 Preview vs Qwen3.6 35B A3B

Side by side comparison of Step 5 Preview and Qwen3.6 35B A3B on pricing, benchmark scores, context window, and more.

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).

Input / 1M: $1
Output / 1M: $2.70
Context: 1.05M

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.

Input / 1M: $0.10
Output / 1M: $0.90
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

Qwen3.6 35B A3B

5.2x cheaper for a typical chat

Higher intelligence score

Not available

Not enough benchmark data

Larger context window

Step 5 Preview

1.05M vs 262K tokens

Newer release

Step 5 Preview

Released October 8, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

Step 5 Preview28.5

Qwen3.6 35B A3BNot available

Coding index

Step 5 PreviewNot available

Qwen3.6 35B A3B41.9

Agentic index

Step 5 PreviewNot available

Qwen3.6 35B A3B13.1

Pricing

Step 5 Preview vs Qwen3.6 35B A3B API pricing

Per-token API rates. Cheaper option highlighted.

Metric	Step 5 Preview	Qwen3.6 35B A3B
Input tokensPer 1M tokens	$1	$0.10
Output tokensPer 1M tokens	$2.70	$0.90
Cached input (read)Per 1M tokens	$0.10	$0.03
Cache writePer 1M tokens	Not available	Not 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

Step 5 Preview$3.35

Qwen3.6 35B A3B$0.65

Coding task

30K in, 4K out

Step 5 Preview$40.80$13.80 cached

Qwen3.6 35B A3B$6.60$4.35 cached

Long document summary

150K in, 2K out

Step 5 Preview$155.40$20.40 cached

Qwen3.6 35B A3B$16.80$5.55 cached

Specs

Context window and capabilities

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

Metric	Step 5 Preview	Qwen3.6 35B A3B
Context window	1.05M tokens	262K tokens
Max output	64K tokens	236K tokens
Input types	Image, Text, Video	Image, Text, Video
Output types	Text	Text
Reasoning effort levels	High, Medium, Low	Not available
Default reasoning effort	Medium	Not available
Release date	October 8, 2026	April 27, 2026

Features

Supported features

API features available for each model.

Metric	Step 5 Preview	Qwen3.6 35B A3B
Tool calling	Supported	Supported
Structured outputs	Supported	Supported
JSON mode	Supported	Supported
Reasoning	Supported	Supported
Temperature	Supported	Supported
Stop sequences	Supported	Supported
Deterministic seed	Supported	Supported
Verbosity control	Not supported	Not supported

Our take

Qwen3.6 35B A3B is 5.2x cheaper for a typical chat. Step 5 Preview has the larger context window (1.05M vs 262K tokens). 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 Step 5 Preview or Qwen3.6 35B A3B cheaper?

Qwen3.6 35B A3B is cheaper for a typical chat (2K input tokens and 500 output tokens). Qwen3.6 35B A3B costs $0.10 per 1M input tokens and $0.90 per 1M output tokens, while Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens.

Which has a bigger context window, Step 5 Preview or Qwen3.6 35B A3B?

Step 5 Preview supports up to 1.05M tokens of context, compared with 262K for Qwen3.6 35B A3B.

Can I use Step 5 Preview and Qwen3.6 35B A3B at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Step 5 Preview and Qwen3.6 35B A3B answer side by side and keep the better response.

Why choose? Ask both.

Send one prompt to Step 5 Preview and Qwen3.6 35B A3B at the same time. Compare the answers side by side and keep the best one.

Get started See a preview