Step 3.5 Flash
Step 3.5 Flash is a foundation model developed by StepFun that utilizes a sparse Mixture of Experts architecture. It is designed to handle complex tasks with reasoning and tool-calling capabilities while processing large amounts of text data.
Step 3.5 Flash specs and pricing
- Provider: StepFun
- Released: January 29, 2026
- Context window: 262K tokens
- Max output: 66K tokens
- Input: text
- Output: text
- Price: $0.10 input / $0.30 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Step 3.5 Flash is good at
- Complex reasoning tasks
- Applications requiring tool integration
- Processing large text documents
To-dos to try with Step 3.5 Flash
- Analyze a long technical report and extract key arguments using its reasoning capabilities
- Use tool-calling to integrate the model into a workflow that retrieves real-time data
- Summarize a 200,000-token document into a concise executive brief
FAQ
- What is the underlying architecture of Step 3.5 Flash? It is built on a sparse Mixture of Experts architecture that activates 11B of its 196B parameters per token.
- Does this model support tool-calling? Yes, Step 3.5 Flash includes built-in support for tool-calling.
- How much does Step 3.5 Flash cost? Step 3.5 Flash costs $0.10 per million input tokens and $0.30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.32 credits ($1 = 100 credits).
- What is the context window of Step 3.5 Flash? Step 3.5 Flash can read up to 262K tokens at once and write up to 66K tokens in one reply.
- Can I use Step 3.5 Flash without coding? Yes. In todo.is you pick Step 3.5 Flash as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.