Step 3.7 Flash

LLM
Stepfun

Step 3.7 Flash is a sparse MoE vision-language model built for agentic workflows combining perception, search, and reasoning. It supports a 256k context window and offers three selectable reasoning levels to balance speed and

Context tokens

262,144

Output tokens

8,192

Released

Jun 12, 2026

Schema

Supports three selectable reasoning levels (low, medium, and high) that let you balance speed and depth.

Schema documentation

Capabilities

Tool use
Structured output
Thinking
Multimodal

Supported input media

image
text

Supported tools

  • Seclai Content Tools

    Inspect source documents connected to your account. Includes tools for loading full content, reading character ranges, searching within documents, viewing stats, and listing available content sources. When a source_connection_content_version_id is provided in agent run metadata it is used as the default. Otherwise the model can discover content via list_content_sources.

  • Seclai Knowledge Base

    Search your knowledge bases using semantic similarity. Includes search_knowledge_base and list_knowledge_bases. When a knowledge_base_id is provided in the prompt or agent run metadata it is used as the default. Otherwise the model can discover available knowledge bases at runtime.

  • Seclai Memory Banks

    Manage persistent memory across agent runs. Includes tools for listing memory banks, writing entries, searching memory via semantic similarity, and loading entries in chronological order. Supports two memory types: 'conversation' (speaker-attributed turns) and 'general' (freeform text). Use key to organize entries by topic, session, or user.

Pricing

TypeCreditsUnits
Input2.66Credits per 1k tokens
Output15.295Credits per 1k tokens
Cache hit0.532Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Step 3.7 Flash in the model experiments page. You can compare it with other models side by side.