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 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.
stepfun/step-5-preview
- Contexto
- 1M tokens
- Máx. completion
- 64,000
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-10-08
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stepfun/step-5-preview",
"messages": [{"role": "user", "content": "Hola"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es 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 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. Step 5 Preview corre en el API de Geek Hub (compatible con OpenAI). Id: stepfun/step-5-preview.
- ¿Step 5 Preview es gratis?
- No. El input cuesta $1.0901 / 1M tokens y el output $2.9432 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Step 5 Preview?
- Step 5 Preview tiene una ventana de 1M tokens. Soporta hasta 64,000 tokens de completion.
- ¿Step 5 Preview soporta tool calling y structured outputs?
- Step 5 Preview acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Step 5 Preview?
- Step 5 Preview se lanzó el 8 de octubre de 2026.
Más modelos de Stepfun
Step 3.5 FlashStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parame
Step 3.7 FlashStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video