{"slug": "step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input", "title": "Step 5 Preview: StepFun's frontier model with 1M context and video input", "summary": "StepFun released Step 5 Preview, a flagship model for agentic work that natively supports text, image, and video input and offers a 1M-token context window. StepFun says the model delivers frontier-level performance across software engineering and professional knowledge work, with particular strength in finance, and supports multi-step agent tasks, long-document processing, and multimodal understanding. Step 5 Preview is billed on actual input and output token usage and can be integrated via the StepFun Open Platform Chat Completions API or Claude Code with Step Plan.", "body_md": "**Step 5 Preview is StepFun’s flagship model for agentic work.** It delivers frontier-level performance across software engineering and professional knowledge work, with particular strength in finance. It natively supports text, image, and video input and provides a\n\n**1M-token context window**, making it suitable for tasks that require large amounts of information, tool calls, and continuous progress toward a deliverable.\n\n## At a glance\n\n## Core capabilities\n\n## Long-context understanding and reasoning\n\nAnalyze long documents, multiple source materials, and conversation history within a 1M-token context.\n\n**Typical tasks**: cross-document question answering and research material organization.\n## Programming and software engineering\n\nWork across multiple programming languages and engineering tasks, with tools to advance development, modification, and verification.\n\n**Typical tasks**: troubleshooting, code changes, and test creation.\n## Multi-step Agent tasks\n\nUse tools provided by an application to retrieve information, process documents, and continue through multi-step work.\n\n**Typical tasks**: deep research and analytical reporting.\n## Multimodal understanding\n\nCombine images, video, and text to extract and analyze multimodal information.\n\n**Typical tasks**: chart analysis, screenshot question answering, and video summarization.\n## Use cases\n\n- **Software development** : Combine code, dependency information, and error logs to locate problems, modify code, and recommend tests.\n- **Long-document processing** : Organize multiple sources in a long context, extract and summarize information, and cross-check details.\n- **Research and analysis** : Work with search, code execution, or document tools to break down tasks and produce structured results.\n- **Multimodal understanding** : Analyze screenshots, charts, and video, and output conclusions in a specified format.\n\n## Input and output\n\n### Image and video input\n\nSee the \n\n[Quickstart](https://platform.stepfun.ai/docs/en/quickstart/overview)for image and video request examples. For complete limits, see\n\n[Image understanding best practices](https://platform.stepfun.ai/docs/en/guides/developer/image-chat)and\n\n[Video understanding best practices](https://platform.stepfun.ai/docs/en/guides/developer/video-chat).\n\n## Features and configuration\n\n## Integration\n\n1. Create an API key on the StepFun Open Platform.\n2. Open the [Quickstart](https://platform.stepfun.ai/docs/en/quickstart/overview) , select Step 5 Preview, and switch between the text chat, image understanding, and video understanding examples.\n3. Send a request with cURL or Python and read the result from `choices[0].message.content` .\n4. Before going live, use the [API reference](https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create) to add timeout, retry, error-handling, and key-management logic.\n\n## Quickstart\n\nSee text, image, and video request examples.\n\n## Chat Completions API\n\nSee the complete request parameters, response fields, and usage information.\n\n## Claude Code integration\n\nConfigure Step Plan and enable 1M context.\n\n## Pricing and rate limits\n\nStep 5 Preview is billed based on actual input and output token usage. For current prices, cache billing rules, and account rate limits, see\n[Pricing and Rate Limits](https://platform.stepfun.ai/docs/en/guides/pricing/details#pricing-for-multimodal-reasoning-models).\n\n## More information\n\n[Quickstart](https://platform.stepfun.ai/docs/en/quickstart/overview)·\n\n[API reference](https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create)·\n\n[Claude Code integration](https://platform.stepfun.ai/docs/en/step-plan/integrations/claude-code)·\n\n[Pricing and Rate Limits](https://platform.stepfun.ai/docs/en/guides/pricing/details)", "url": "https://wpnews.pro/news/step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input", "canonical_source": "https://platform.stepfun.ai/docs/en/guides/models/step-5-preview", "published_at": "2026-09-21 13:43:22+00:00", "updated_at": "2026-09-21 13:53:59.393126+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-products", "generative-ai", "ai-tools"], "entities": ["StepFun", "Step 5 Preview", "StepFun Open Platform", "Claude Code", "Step Plan"], "alternates": {"html": "https://wpnews.pro/news/step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input", "markdown": "https://wpnews.pro/news/step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input.md", "text": "https://wpnews.pro/news/step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input.txt", "jsonld": "https://wpnews.pro/news/step-5-preview-stepfun-s-frontier-model-with-1m-context-and-video-input.jsonld"}}