Skip to main content

Model overview

Reasoning models are designed for deep analytical work, including logic, mathematics, coding, and other complex tasks.

Models

A model’s context length limits the total input and output it can process in one request. See each model overview for its exact rules.

Get started with reasoning models

Developer guides

Reasoning model guide

Learn recommended patterns for complex tasks, tool calling, and long-context work.

Migrate from OpenAI

Move an OpenAI-compatible integration to StepFun with minimal changes.

Build multi-turn conversations

Manage message history and context for stable multi-turn experiences.

Output JSON

Return machine-readable structured JSON for application integration.

Stream responses

Render output as it arrives to reduce perceived wait time.

Use tool calling

Let a model call search, databases, or business functions.

Prompt caching

Reuse repeated context to lower cost and improve response time.