> ## 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.

# Model Capability Overview

<section className="step-overview-board">
  <div className="step-overview-board__hero">
    <div className="step-overview-board__stats">
      <div className="step-overview-board__stat">
        <p className="step-overview-board__stat-label">Recommended</p>
        <p className="step-overview-board__stat-value">4</p>
      </div>

      <div className="step-overview-board__stat">
        <p className="step-overview-board__stat-label">Public models</p>
        <p className="step-overview-board__stat-value">5</p>
      </div>

      <div className="step-overview-board__stat">
        <p className="step-overview-board__stat-label">Max context</p>
        <p className="step-overview-board__stat-value">256K</p>
      </div>
    </div>
  </div>

  <div className="step-overview-board__controls">
    <p className="step-overview-board__result">
      <span>4 category views covering 5 public models</span>
    </p>
  </div>

  <div className="step-overview-board__tab-shell">
    <Tabs>
      <Tab title="Recommended models">
        <div className="step-overview-board__tab-panel">
          <section className="step-overview-section">
            <div className="step-overview-section__header">
              <p className="step-overview-section__eyebrow">Recommended</p>
              <h2>Recommended models</h2>
            </div>

            <div className="step-overview-board__list">
              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / multimodal</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">Step 3.7 Flash</p>
                          <p className="step-overview-card__subtitle">Flagship multimodal reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">StepFun's flagship multimodal reasoning model. Building on `step-3.5-flash`'s high-throughput reasoning and tool calling, it adds **native multimodal input**: understanding images and videos directly, without an additional vision MCP or auxiliary model. Three reasoning effort levels (low / medium / high) make it a fast and dependable choice for agent, coding, and multimodal workloads.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Multimodal</span>
                      <span className="step-overview-card__tag">Agent</span>
                      <span className="step-overview-card__tag">Image understanding</span>
                      <span className="step-overview-card__tag">Video understanding</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Step 3.7 Flash</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash-quickstart">
                        <p className="step-overview-card__link-type">Quickstart</p>
                        <p className="step-overview-card__link-label">Multimodal quickstart</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / text</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">step-3.5-flash</p>
                          <p className="step-overview-card__subtitle">Flagship reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">A flagship reasoning model built for agents, combining deep reasoning with ultra-fast responses and stable, reliable tool calling. On top of strong general reasoning, it excels at complex project planning and long-horizon task execution.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Tool Calling</span>
                      <span className="step-overview-card__tag">Web Search</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/reasoning">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Reasoning models</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech synthesis</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-tts</p>
                          <p className="step-overview-card__subtitle">Contextual TTS</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max input</p>
                        <p className="step-overview-card__metric-value">1,000 chars</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">Integrates contextual understanding into the full speech generation pipeline. Supports Global Context + Inline Context dual-level control via natural language descriptions for precise emotion and style control. Ideal for audiobooks, drama dubbing, ad narration, and other high-expressiveness scenarios.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech synthesis</span>
                      <span className="step-overview-card__tag">Context control</span>
                      <span className="step-overview-card__tag">Zero-shot Clone</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related links</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/audio">
                        <span className="step-overview-card__link-type">Models</span>
                        <span className="step-overview-card__link-label">Audio Models</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/tts">
                        <span className="step-overview-card__link-type">Guide</span>
                        <span className="step-overview-card__link-label">TTS Developer Guide</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/audio/create-audio">
                        <span className="step-overview-card__link-type">API Docs</span>
                        <span className="step-overview-card__link-label">Text-to-Speech API</span>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech understanding</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-chat</p>
                          <p className="step-overview-card__subtitle">End-to-end speech understanding</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Input</p>
                        <p className="step-overview-card__metric-value">Audio + text</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">An end-to-end speech-understanding model served through an OpenAI-compatible Chat Completion API. It accepts audio or text input and returns text, interpreting vocal cues such as intonation, hesitation, and laughter alongside the words. It suits voice assistants, call and meeting analysis, and voice message triage.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech understanding</span>
                      <span className="step-overview-card__tag">Paralinguistic cues</span>
                      <span className="step-overview-card__tag">Audio & text input</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/stepaudio-2.5-chat">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">StepAudio 2.5 Chat</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>
            </div>
          </section>
        </div>
      </Tab>

      <Tab title="All models">
        <div className="step-overview-board__tab-panel">
          <section className="step-overview-section">
            <div className="step-overview-section__header">
              <p className="step-overview-section__eyebrow">All models</p>
              <h2>All public models</h2>
            </div>

            <div className="step-overview-board__list">
              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / multimodal</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">Step 3.7 Flash</p>
                          <p className="step-overview-card__subtitle">Flagship multimodal reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">StepFun's flagship multimodal reasoning model. Building on `step-3.5-flash`'s high-throughput reasoning and tool calling, it adds **native multimodal input**: understanding images and videos directly, without an additional vision MCP or auxiliary model. Three reasoning effort levels (low / medium / high) make it a fast and dependable choice for agent, coding, and multimodal workloads.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Multimodal</span>
                      <span className="step-overview-card__tag">Agent</span>
                      <span className="step-overview-card__tag">Image understanding</span>
                      <span className="step-overview-card__tag">Video understanding</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Step 3.7 Flash</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash-quickstart">
                        <p className="step-overview-card__link-type">Quickstart</p>
                        <p className="step-overview-card__link-label">Multimodal quickstart</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / text</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">step-3.5-flash</p>
                          <p className="step-overview-card__subtitle">Flagship reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">A flagship reasoning model built for agents, combining deep reasoning with ultra-fast responses and stable, reliable tool calling. On top of strong general reasoning, it excels at complex project planning and long-horizon task execution.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Tool Calling</span>
                      <span className="step-overview-card__tag">Web Search</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/reasoning">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Reasoning models</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech synthesis</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-tts</p>
                          <p className="step-overview-card__subtitle">Contextual TTS</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max input</p>
                        <p className="step-overview-card__metric-value">1,000 chars</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">Integrates contextual understanding into the full speech generation pipeline. Supports Global Context + Inline Context dual-level control via natural language descriptions for precise emotion and style control. Ideal for audiobooks, drama dubbing, ad narration, and other high-expressiveness scenarios.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech synthesis</span>
                      <span className="step-overview-card__tag">Context control</span>
                      <span className="step-overview-card__tag">Zero-shot Clone</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related links</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/audio">
                        <span className="step-overview-card__link-type">Models</span>
                        <span className="step-overview-card__link-label">Audio Models</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/tts">
                        <span className="step-overview-card__link-type">Guide</span>
                        <span className="step-overview-card__link-label">TTS Developer Guide</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/audio/create-audio">
                        <span className="step-overview-card__link-type">API Docs</span>
                        <span className="step-overview-card__link-label">Text-to-Speech API</span>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech recognition</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-asr</p>
                          <p className="step-overview-card__subtitle">New-generation streaming ASR</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Model scale</p>
                        <p className="step-overview-card__metric-value">4B MTP</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">StepFun's new-generation streaming speech recognition model, based on a 4B MTP architecture that maintains SOTA transcription accuracy while sharply reducing latency. Supports Chinese and English recognition with ITN text normalization, and suits real-time captions, voice input, and meeting transcription where both speed and accuracy matter.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">SOTA accuracy</span>
                      <span className="step-overview-card__tag">Low latency</span>
                      <span className="step-overview-card__tag">Chinese & English</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/stepaudio-2.5-asr">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">StepAudio 2.5 ASR</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/audio/asr-sse">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Speech Recognition (Streaming Output)</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech understanding</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-chat</p>
                          <p className="step-overview-card__subtitle">End-to-end speech understanding</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Input</p>
                        <p className="step-overview-card__metric-value">Audio + text</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">An end-to-end speech-understanding model served through an OpenAI-compatible Chat Completion API. It accepts audio or text input and returns text, interpreting vocal cues such as intonation, hesitation, and laughter alongside the words. It suits voice assistants, call and meeting analysis, and voice message triage.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech understanding</span>
                      <span className="step-overview-card__tag">Paralinguistic cues</span>
                      <span className="step-overview-card__tag">Audio & text input</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/stepaudio-2.5-chat">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">StepAudio 2.5 Chat</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>
            </div>
          </section>
        </div>
      </Tab>

      <Tab title="Text & reasoning">
        <div className="step-overview-board__tab-panel">
          <section className="step-overview-section">
            <div className="step-overview-section__header">
              <p className="step-overview-section__eyebrow">Text & reasoning</p>
              <h2>Text and reasoning models</h2>
            </div>

            <div className="step-overview-board__list">
              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / multimodal</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">Step 3.7 Flash</p>
                          <p className="step-overview-card__subtitle">Flagship multimodal reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">StepFun's flagship multimodal reasoning model. Building on `step-3.5-flash`'s high-throughput reasoning and tool calling, it adds **native multimodal input**: understanding images and videos directly, without an additional vision MCP or auxiliary model. Three reasoning effort levels (low / medium / high) make it a fast and dependable choice for agent, coding, and multimodal workloads.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Multimodal</span>
                      <span className="step-overview-card__tag">Agent</span>
                      <span className="step-overview-card__tag">Image understanding</span>
                      <span className="step-overview-card__tag">Video understanding</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Step 3.7 Flash</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/models/step-3.7-flash-quickstart">
                        <p className="step-overview-card__link-type">Quickstart</p>
                        <p className="step-overview-card__link-label">Multimodal quickstart</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Reasoning / text</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">step-3.5-flash</p>
                          <p className="step-overview-card__subtitle">Flagship reasoning</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max context</p>
                        <p className="step-overview-card__metric-value">256K</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">A flagship reasoning model built for agents, combining deep reasoning with ultra-fast responses and stable, reliable tool calling. On top of strong general reasoning, it excels at complex project planning and long-horizon task execution.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Reasoning</span>
                      <span className="step-overview-card__tag">Tool Calling</span>
                      <span className="step-overview-card__tag">Web Search</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/reasoning">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">Reasoning models</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/reasoning">
                        <p className="step-overview-card__link-type">Guide</p>
                        <p className="step-overview-card__link-label">Reasoning model best practices</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>
            </div>
          </section>
        </div>
      </Tab>

      <Tab title="Audio">
        <div className="step-overview-board__tab-panel">
          <section className="step-overview-section">
            <div className="step-overview-section__header">
              <p className="step-overview-section__eyebrow">Audio</p>
              <h2>Audio models</h2>
            </div>

            <div className="step-overview-board__list">
              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech understanding</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-chat</p>
                          <p className="step-overview-card__subtitle">End-to-end speech understanding</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Input</p>
                        <p className="step-overview-card__metric-value">Audio + text</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">An end-to-end speech-understanding model served through an OpenAI-compatible Chat Completion API. It accepts audio or text input and returns text, interpreting vocal cues such as intonation, hesitation, and laughter alongside the words. It suits voice assistants, call and meeting analysis, and voice message triage.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech understanding</span>
                      <span className="step-overview-card__tag">Paralinguistic cues</span>
                      <span className="step-overview-card__tag">Audio & text input</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/stepaudio-2.5-chat">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">StepAudio 2.5 Chat</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/chat/chat-completion-create">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Chat Completion API</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech synthesis</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-tts</p>
                          <p className="step-overview-card__subtitle">Contextual TTS</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Max input</p>
                        <p className="step-overview-card__metric-value">1,000 chars</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">Integrates contextual understanding into the full speech generation pipeline. Supports Global Context + Inline Context dual-level control via natural language descriptions for precise emotion and style control. Ideal for audiobooks, drama dubbing, ad narration, and other high-expressiveness scenarios.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">Speech synthesis</span>
                      <span className="step-overview-card__tag">Context control</span>
                      <span className="step-overview-card__tag">Zero-shot Clone</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related links</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/audio">
                        <span className="step-overview-card__link-type">Models</span>
                        <span className="step-overview-card__link-label">Audio Models</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/guides/developer/tts">
                        <span className="step-overview-card__link-type">Guide</span>
                        <span className="step-overview-card__link-label">TTS Developer Guide</span>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/audio/create-audio">
                        <span className="step-overview-card__link-type">API Docs</span>
                        <span className="step-overview-card__link-label">Text-to-Speech API</span>
                      </a>
                    </div>
                  </div>
                </div>
              </div>

              <div className="step-overview-card">
                <div className="step-overview-card__summary step-overview-card__summary--static">
                  <div className="step-overview-card__summary-top">
                    <div className="step-overview-card__main">
                      <div className="step-overview-card__eyebrow">
                        <span className="step-overview-card__family">Speech recognition</span>
                        <span className="step-overview-card__recommended">Recommended</span>
                      </div>

                      <div className="step-overview-card__heading">
                        <div>
                          <p className="step-overview-card__title">stepaudio-2.5-asr</p>
                          <p className="step-overview-card__subtitle">New-generation streaming ASR</p>
                        </div>
                      </div>
                    </div>

                    <div className="step-overview-card__aside">
                      <div className="step-overview-card__metric">
                        <p className="step-overview-card__metric-label">Model scale</p>
                        <p className="step-overview-card__metric-value">4B MTP</p>
                      </div>
                    </div>
                  </div>

                  <div className="step-overview-card__summary-body">
                    <p className="step-overview-card__summary-text">StepFun's new-generation streaming speech recognition model, based on a 4B MTP architecture that maintains SOTA transcription accuracy while sharply reducing latency. Supports Chinese and English recognition with ITN text normalization, and suits real-time captions, voice input, and meeting transcription where both speed and accuracy matter.</p>

                    <div className="step-overview-card__tags">
                      <span className="step-overview-card__tag">SOTA accuracy</span>
                      <span className="step-overview-card__tag">Low latency</span>
                      <span className="step-overview-card__tag">Chinese & English</span>
                    </div>
                  </div>
                </div>

                <div className="step-overview-card__details step-overview-card__details--static">
                  <div className="step-overview-card__details-block">
                    <p className="step-overview-card__block-title">Related entry points</p>

                    <div className="step-overview-card__links">
                      <a className="step-overview-card__link" href="/en/guides/models/stepaudio-2.5-asr">
                        <p className="step-overview-card__link-type">Model page</p>
                        <p className="step-overview-card__link-label">StepAudio 2.5 ASR</p>
                      </a>

                      <a className="step-overview-card__link" href="/en/api-reference/audio/asr-sse">
                        <p className="step-overview-card__link-type">API reference</p>
                        <p className="step-overview-card__link-label">Speech Recognition (Streaming Output)</p>
                      </a>
                    </div>
                  </div>
                </div>
              </div>
            </div>
          </section>
        </div>
      </Tab>
    </Tabs>
  </div>
</section>