StepFun: Step3 API

Add AI to your application with Puter.js.

Explore Other Models

Model Card

Step3 is a multimodal reasoning model from StepFun built on a Mixture-of-Experts architecture with 321B total parameters (38B active), designed for cost-effective vision-language reasoning. It features innovative Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD) for efficient inference across various hardware. The model excels at visual interpretation, complex reasoning, and is available via API or as open-source checkpoints on Hugging Face.

Context Window N/A

tokens

Max Output 66K

tokens

Input Cost $0.57

per million tokens

Output Cost $1.42

per million tokens

Release Date Jul 28, 2025

 

API Usage Example

Add AI to your app with just a few lines of code.
No API keys, no backend, no configuration required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms").then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

More Models from StepFun

Chat

StepFun: Step 3.5 Flash

Step 3.5 Flash is StepFun's open-source reasoning model built on a sparse Mixture of Experts archite...

View all StepFun models →

Frequently Asked Questions

What is this StepFun: Step3 API about?

The StepFun: Step3 API gives you access to StepFun's chat model through Puter.js. With just a few lines of JavaScript, you can integrate StepFun: Step3 into any web app or Node.js project — no API keys, no backend, and no configuration required.

Who created StepFun: Step3?

StepFun: Step3 was created by StepFun and released on Jul 28, 2025.

What is the max output length of StepFun: Step3?

StepFun: Step3 can generate up to 66K tokens in a single response.

How much does it cost?
The StepFun: Step3 API is available through the User-Pays Model. As a developer, you can add the StepFun: Step3 API to your app for free — your users pay for their own AI costs directly.
Price per 1M tokens
Input$0.57
Output$1.42
How do I access the StepFun: Step3 API?

You can access the StepFun: Step3 API with just a few lines of JavaScript — no API keys, no backend, and no configuration required. Include the Puter.js library in your project and start making calls right away. For more details, check out our documentation.

Does the StepFun: Step3 API work with React / Vue / Vanilla JS / Node / etc.?

Yes — the StepFun: Step3 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add AI to your application without worrying about API keys or setup.

Explore Models View Tutorials