step-3.5-flash

Operational
Ranked #45 in the capability rankings
Reasoning
Tools
256K

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$0.1000 / 1M tokens
Completion price$0.3000 / 1M tokens
Cache read price$0.0200 / 1M tokens
Billing details
Vendor list price comparison

Description

StepFun step-3.5-flash — text-only reasoning model with 256K context, aimed at logic, mathematics, software engineering, and deep-research work where reasoning quality has to come with fast, reliable execution. Reasoning depth is selectable per request through reasoning_effort (low / medium / high). Supports tool calling, JSON Schema structured output, streaming, and prompt caching. For image or video input use step-3.7-flash.

Capabilities

Tasks
chat, reasoning

API endpoints

  • POST /v1/messages (anthropic)
  • POST /v1/chat/completions (openai)