> ## Documentation Index
> Fetch the complete documentation index at: https://platform.stepfun.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Step 3.7 Flash

StepFun's flagship multimodal reasoning model. Powered by a 198B-parameter / 11B-activation sparse MoE architecture, with native support for image and video understanding.

## Key facts

> [card] Model type
>
> Sparse MoE architecture\
> 198B total params / 11B activated params

> [card] Context length
>
> 256K tokens

> [card] Best for
>
> High-throughput reasoning + native multimodal\
> Optimized for agent and coding workloads

## Core capabilities

> [card] 👁️ Native multimodal
>
> Native support for image and video understanding. Drop a file straight into the chat — no separate vision model required inside your Agent framework.

> [card] 🚀 High-throughput reasoning
>
> Sparse MoE architecture delivers high throughput and low latency, ideal for real-time agent workflows and high-volume calls.

> [card] 🛠️ Tool calling
>
> Reliable `tools` / `tool_choice` orchestration, supports multi-step task decomposition and plan execution.

> [card] 🧠 Complex reasoning
>
> Handles logical reasoning, math, software engineering, and deep research — a dependable foundation for long-chain agent reasoning.

## Reasoning effort

`step-3.7-flash` supports three reasoning effort levels — pick one to match task complexity:

| Effort | Best for |
| :- | :- |
| `low` | Simple Q\&A, summarization, rewriting, information extraction |
| `medium` | Default. General reasoning and multi-step tasks |
| `high` | Complex reasoning, math, planning, code analysis |

> [!NOTE]
>
> The Chat Completions API uses `reasoning_effort` to control the effort level; the Messages API uses `output_config.effort`. See the [Quickstart](https://platform.stepfun.ai/docs/en/quickstart/overview.md) for basic call examples.

## Get started

> [card] [Quickstart](https://platform.stepfun.ai/docs/en/quickstart/overview.md)
>
> Get started with images, video, local files, and reasoning-effort control.

> [card] [Chat Completion](https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create.md)
>
> `POST /v1/chat/completions`\
> OpenAI-compatible, with streaming and tool calling.

## Pricing

| Item | Price (per million tokens) |
| :- | :- |
| Input (cache hit) | \$0.04 |
| Input (cache miss) | \$0.20 |
| Output | \$1.15 |

## Framework support

`step-3.7-flash` plugs reliably into popular Coding and Agent tools, well-suited to code generation, file editing, and complex task coordination in the terminal, IDE, or Agent workflows.

{frameworkTools.map((tool) => (
    <a key={tool.href} className="step-plan-tool-card step-plan-tool-card--link" href={tool.href}>
      <div className="step-plan-tool-card__top">
        <span className="step-plan-tool-card__logo-shell" aria-hidden="true">
          <img className="step-plan-tool-card__logo" src={tool.logo} alt="" loading="lazy" />
        </span>
      </div>
      <div className="step-plan-tool-card__body">
        <h3>{tool.title}</h3>
        <p>{tool.description}</p>
      </div>
    </a>
  ))}

[View Step Plan integration guide →](https://platform.stepfun.ai/docs/en/step-plan/quick-start.md)

## Related reading

> [card] [Reasoning model guide](https://platform.stepfun.ai/docs/en/guides/developer/reasoning.md)
>
> Recommended usage of reasoning models for complex tasks, tool calling, and long contexts.

> [card] [Image understanding best practices](https://platform.stepfun.ai/docs/en/guides/developer/image-chat.md)
>
> A deeper look at image understanding API params, the detail setting, and best practices.

> [card] [Video understanding best practices](https://platform.stepfun.ai/docs/en/guides/developer/video-chat.md)
>
> A deeper look at video understanding API params, file limits, and common pitfalls.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.