AI model comparison

Step 5 Preview vs Gemini 3.1 Pro Preview

Side by side comparison of Step 5 Preview and Gemini 3.1 Pro Preview 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
1M

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.

Input / 1M
$2
Output / 1M
$12
Context
1.05M

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

stepfun logo

Step 5 Preview

3.0x cheaper for a typical chat

Higher intelligence score

google logo

Gemini 3.1 Pro Preview

29.7 vs 28.5 on Artificial Analysis

Larger context window

google logo

Gemini 3.1 Pro Preview

1.05M vs 1M tokens

Newer release

stepfun logo

Step 5 Preview

Released October 8, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

stepfun logoStep 5 Preview28.5
google logoGemini 3.1 Pro Preview29.7

Coding index

stepfun logoStep 5 PreviewNot available
google logoGemini 3.1 Pro Preview68.8

Agentic index

stepfun logoStep 5 PreviewNot available
google logoGemini 3.1 Pro Preview8.2

Pricing

Step 5 Preview vs Gemini 3.1 Pro Preview API pricing

Per-token API rates. Cheaper option highlighted.

Metricstepfun logoStep 5 Previewgoogle logoGemini 3.1 Pro Preview
Input tokensPer 1M tokens$1$2
Output tokensPer 1M tokens$2.70$12
Cached input (read)Per 1M tokens$0.10$0.20
Cache writePer 1M tokensNot available$0.38
Long-context pricingPer 1M tokens, for very long promptsSame rate at any length$4 in / $18 out above 200K
Web searchPer requestNot available$0.014

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

stepfun logoStep 5 Preview$3.35
google logoGemini 3.1 Pro Preview$10

Coding task

30K in, 4K out

stepfun logoStep 5 Preview$40.80$13.80 cached
google logoGemini 3.1 Pro Preview$108$54 cached

Long document summary

150K in, 2K out

stepfun logoStep 5 Preview$155.40$20.40 cached
google logoGemini 3.1 Pro Preview$324$54 cached

Specs

Context window and capabilities

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

Metricstepfun logoStep 5 Previewgoogle logoGemini 3.1 Pro Preview
Context window1M tokens1.05M tokens
Max output64K tokens66K tokens
Input typesImage, Text, VideoAudio, File, Image, Text, Video
Output typesTextText
Reasoning effort levelsHigh, Medium, LowHigh, Medium, Low
Default reasoning effortMediumMedium
Release dateOctober 8, 2026February 19, 2026

Features

Supported features

API features available for each model.

Metricstepfun logoStep 5 Previewgoogle logoGemini 3.1 Pro Preview
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Step 5 Preview is 3.0x cheaper for a typical chat. Gemini 3.1 Pro Preview scores higher on the Artificial Analysis Intelligence Index (29.7 vs 28.5). Gemini 3.1 Pro Preview has the larger context window (1.05M vs 1M 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 Gemini 3.1 Pro Preview cheaper?

Step 5 Preview is cheaper for a typical chat (2K input tokens and 500 output tokens). Step 5 Preview costs $1 per 1M input tokens and $2.70 per 1M output tokens, while Gemini 3.1 Pro Preview costs $2 per 1M input tokens and $12 per 1M output tokens.

Which has a bigger context window, Step 5 Preview or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview supports up to 1.05M tokens of context, compared with 1M for Step 5 Preview.

Is Step 5 Preview smarter than Gemini 3.1 Pro Preview?

On the Artificial Analysis Intelligence Index, Step 5 Preview scores 28.5 and Gemini 3.1 Pro Preview scores 29.7, putting Gemini 3.1 Pro Preview ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Step 5 Preview and Gemini 3.1 Pro Preview at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Step 5 Preview and Gemini 3.1 Pro Preview answer side by side and keep the better response.

stepfun logogoogle logo

Why choose? Ask both.

Send one prompt to Step 5 Preview and Gemini 3.1 Pro Preview at the same time. Compare the answers side by side and keep the best one.