Can I run Step 5 Preview locally?

No. The weights are not public and StepFun has not released a Hugging Face repository, so it is API access only.

What does Step 5 Preview cost and how large is the context?

Pricing is $1.00 per million input tokens and $2.70 per million output tokens, with a one-million-token context window.

How does Step 5 Preview differ from smaller or cheaper alternatives?

Its main differentiators are the one-million-token context and the MoE architecture tuned for agentic, multi-step work — particularly in finance and software engineering — rather than general-purpose chat.

▲

88.2%

this week

Step 5 Preview

9275°

#llm #stepfun #vision #video #reasoning #coding

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

StepFun | 1,048,576 token context | $1.00/M input, $2.70/M output. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

Guides for this model

How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Step 5 Preview is StepFun's flagship closed model, built on a sparse Mixture-of-Experts architecture with 27B active parameters drawn from a 600B total pool. It targets agentic workflows: long multi-step tasks across large codebases and documents, with particular strength in finance and software engineering. The one-million-token context window makes it a serious option when other models run out of room.

Known for

One-million-token context window for very large codebases and documents
Sparse MoE design: 27B active / 600B total parameters
Strong in software engineering and professional knowledge work
Particular depth in finance-domain tasks
Built for multi-step agentic tasks with tool use

Watch out for

Closed weights only — no local deployment, no self-hosting.
Output pricing at $2.70/M is moderate but long-context runs can generate large output bills quickly.
Tagged for vision and video, but StepFun has not published detail on those capabilities here.

Best for

Prompts to try

Audit a large codebase

I'm pasting a large Python codebase below. Identify any security vulnerabilities, suggest refactors for the three most complex functions, and produce a prioritised list of changes with brief rationale for each. Work through the files systematically before drawing conclusions.

Financial document analysis

Here is a 10-K filing. Extract the key revenue drivers, flag any material risk factors that changed year-over-year, and summarise the cash flow position in plain language a non-accountant can act on. Cite the relevant sections.

Multi-step research agent

You have access to search and a code interpreter. Research the current competitive landscape for cloud database pricing, write a comparison table, then write a short Python script that takes a monthly query volume as input and returns the estimated monthly cost for each provider.

Compare with

Step 3.5 Flash
Open-weights model
262,144 token context · $0.10/M input, $0.30/M output
Step 3.7 Flash
Open-weights model
262,144 token context · $0.20/M input, $1.15/M output
GPT-6 Luna
API-only model
1,050,000 token context · $0.10/M input, $0.50/M output
GPT-5.6 Luna
API-only model
1,050,000 token context · $0.20/M input, $1.20/M output

More text models from stepfun

Questions people ask

Can I run Step 5 Preview locally?: No. The weights are not public and StepFun has not released a Hugging Face repository, so it is API access only.
What does Step 5 Preview cost and how large is the context?: Pricing is $1.00 per million input tokens and $2.70 per million output tokens, with a one-million-token context window.
How does Step 5 Preview differ from smaller or cheaper alternatives?: Its main differentiators are the one-million-token context and the MoE architecture tuned for agentic, multi-step work — particularly in finance and software engineering — rather than general-purpose chat.

Captain's verdict
If you need a model that can hold an entire large codebase or financial document in context and act on it over multiple steps, Step 5 Preview is worth the price.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #19 Hottest AI model · #7 Hottest Text / LLM model · #7 Hottest Text / LLM text model

Not this creator?

Get your own badge

Step 5 Preview Popularity Trend

Heat score since 8 Oct 2026

Heat score

9,275°

This week

▲

88.2%

9,193° then, 9,275° now

This month

n/a

Wasn't released/tracked

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,891°

OpenRouter tokens

20,114,388,806,215 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 2,011,438 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).

+384°

Adoption rate

About 132,511 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 9,275°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
2,011,438 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,891°
8,891°
running total
3
Add the adoption rate.
About 132,511 downloads a day right now, measured between two readings, at a quarter of the weight.
+384°
9,275°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
9,275°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Similar Models

AI Models for Image, Video & Text Generation

Step 5 Preview is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm stepfun vision video reasoning coding agents long context

Browse by Model Family