S
stepfun/step-5-preview

stepfun/step-5-preview

Data de lançamento: 2026-10-08

1,048,576 context · $1.00/M input tokens · $2.70/M output tokens

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...

Preços

Pagamento por uso

Sem custo inicial, pague apenas pelo que usar

Entrada$1.00 / M Tokens
Saída$2.70 / M Tokens
Cache Read$0.10 / M Tokens

Experimentar o modelo

stepfun/step-5-preview
Online
S
Olá! Sou um assistente de IA útil. Em que posso ajudar?
Pronto para usar este modelo em um coding agent local?Setup do agente

Uso da API

Use os exemplos de código abaixo para integrar com nossa API:

import OpenAI from 'openai';

if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
  apiKey: process.env.WAVESPEED_API_KEY,
  baseURL: 'https://llm.wavespeed.ai/v1',
  timeout: 120_000,
  maxRetries: 0,
});

try {
  const response = await client.chat.completions.create({
    model: 'stepfun/step-5-preview',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
  const body = response as typeof response & { error?: { message?: string } };
  if (body.error) throw new Error(body.error.message || 'LLM generation failed');
  console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
  console.error('LLM request failed:', error);
  process.exitCode = 1;
}

Introdução do modelo

StepFun: Step 5 Preview

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...

This model is available through the WaveSpeed AI OpenAI-compatible API for chat completions and compatible application workflows.


Why It Looks Great

  • text+image+video->text architecture for Text, Image, Video to Text workloads
  • 1048576 context window for long prompts, document analysis, and multi-turn workflows
  • Vision input support for image understanding and multimodal tasks
  • Function calling and tool-use support for agentic application workflows
  • Structured output support for JSON responses and schema-constrained generation
  • Reasoning controls available through supported parameters

Key Features

  • Context Window: 1048576 tokens
  • Max Input: 984576 tokens
  • Max Output: 64000 tokens
  • Vision: Supported
  • Function Calling: Supported
  • Structured Outputs: Supported
  • Image Generation: Not listed
  • Audio Input: Not listed
  • Supported Parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Specifications

SpecificationValue
Providerstepfun
Model TypeChat Completions model
Architecturetext+image+video->text
Context Window1048576 tokens
Max Input984576 tokens
Max Output64000 tokens
InputText, Image, Video
OutputText
VisionSupported
Function CallingSupported
Structured OutputsSupported
Release DateOctober 8, 2026

How to Use

  1. Write your prompt - describe the task, provide context, and specify the desired output format.
  2. Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: stepfun/step-5-preview


API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="stepfun/step-5-preview",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "stepfun/step-5-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: stepfun/step-5-preview
  • Provider: stepfun

Info

Provedorstepfun
Tipollm

Funcionalidades suportadas

Entrada
TextoImagem
Saída
Texto
Contexto1,048,576
Saída máx.64,000
Vision✓ Suportado
Function Calling✓ Suportado

Guia de acesso à API

Base URLhttps://llm.wavespeed.ai/v1
API Endpointchat/completions
ID do modelostepfun/step-5-preview

Step 5 Preview API

stepfun/step-5-preview

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...

Entrada

$1 /M

Saída

$2.7 /M

Contexto

1049K

Saída máx.

64K

Vision

Suportado

Uso de ferramentas

Suportado

Experimente Step 5 Preview no WaveSpeedAI

Acesse Step 5 Preview através da nossa API unificada — compatível com OpenAI, sem inicializações a frio, preços transparentes.

Perguntas frequentes sobre Step 5 Preview

Quanto custa Step 5 Preview via API?+

Preços no WaveSpeedAI: $1.00 por milhão de tokens de entrada e $2.70 por milhão de tokens de saída. Prompt caching e batch processing são cobrados separadamente e reduzem o custo efetivo em cargas longas e repetitivas.

Qual é a janela de contexto do Step 5 Preview?+

Step 5 Preview suporta até 1049K tokens de contexto e até 64K tokens de saída por requisição.

Step 5 Preview é compatível com OpenAI?+

O WaveSpeedAI disponibiliza Step 5 Preview em https://llm.wavespeed.ai/v1 pela interface Chat Completions compatível com OpenAI. Na maioria dos clientes OpenAI SDK, basta alterar a base URL e a chave API; campos opcionais dependem do modelo.

Como começo a usar o Step 5 Preview?+

Entre no WaveSpeedAI, crie uma chave API em Access Keys e envie uma requisição para https://llm.wavespeed.ai/v1/chat/completions com o model id mostrado acima. Consulte o catálogo atual para disponibilidade, recursos e preços.

APIs LLM relacionadas