StepFun: Step3

This model is no longer available.

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 and 38B active per token. It accepts both text and image inputs, making it suitable for vision-language tasks.

The model is engineered for cost-effective decoding through two co-designed innovations: Multi-Matrix Factorization Attention (MFA) to reduce KV cache size, and Attention-FFN Disaggregation (AFD) for more efficient distributed inference. StepFun reports it achieves significantly higher tokens-per-GPU throughput than DeepSeek-V3 at comparable context lengths.

Step3 targets use cases that require grounded multimodal reasoning — interpreting diagrams, documents, and images alongside text — with reduced hallucination.

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

 

Code Example

Add AI to your app with the Puter.js AI API — no API keys or setup 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>

More AI Models From StepFun

Find other StepFun models →

Chat

Step 3.7 Flash

Step 3.7 Flash is a multimodal Mixture-of-Experts model from StepFun, combining a 196B-parameter language backbone with a 1.8B vision encoder and activating roughly 11B parameters per token. It natively processes text and images, supporting a 256K-token context window. The model is designed for agentic coding, tool orchestration, long-context reasoning, and search-intensive workflows. It exposes tunable reasoning tiers (low, medium, high) so developers can trade inference cost against answer depth on a per-call basis. Compared to Step 3.5 Flash, Step 3.7 Flash adds native vision input, improves cross-harness consistency, and achieves stronger performance on coding agent and terminal benchmarks. It targets developers building production pipelines that combine perception, retrieval, and multi-step execution.

 Chat

Step 3.5 Flash

Step 3.5 Flash is an open-source reasoning model from StepFun, built on a sparse Mixture-of-Experts (MoE) architecture with 196B total parameters but only 11B active per token. It supports a 256K-token context window and native tool calling. The model is purpose-built for agentic and coding workflows, with generation throughput of 100–300 tokens/sec in typical usage. It scores 74.4% on SWE-bench Verified, 97.3 on AIME 2025, 86.4% on LiveCodeBench-V6, and 88.2 on τ²-Bench. Step 3.5 Flash is a strong choice for developers building AI agents, code assistants, or multi-step reasoning pipelines who need frontier-level intelligence at low per-token cost.

Frequently Asked Questions

How do I use Step3?

You can access Step3 by StepFun through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Step3 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Step3 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Step3?
Step3 costs $0.57 per 1M input tokens and $1.42 per 1M output tokens.
Price per 1M tokens
Input$0.57
Output$1.42
Who created Step3?

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

What is the max output length of Step3?

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

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the 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