--- title: Use Hailuo in WorkBuddy via RunAPI — Video MCP Guide | RunAPI description: Generate video with MiniMax Hailuo in WorkBuddy through the RunAPI MCP server. Text or image to video, 6 variants, native 1080p, one API key. url: https://runapi.ai/workbuddy-hailuo.md canonical: https://runapi.ai/workbuddy-hailuo locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-hailuo zh-CN: https://runapi.ai/zh-CN/workbuddy-hailuo es: https://runapi.ai/es/workbuddy-hailuo ja: https://runapi.ai/ja/workbuddy-hailuo de: https://runapi.ai/de/workbuddy-hailuo fr: https://runapi.ai/fr/workbuddy-hailuo pt-BR: https://runapi.ai/pt-BR/workbuddy-hailuo ko: https://runapi.ai/ko/workbuddy-hailuo it: https://runapi.ai/it/workbuddy-hailuo nl: https://runapi.ai/nl/workbuddy-hailuo pl: https://runapi.ai/pl/workbuddy-hailuo tr: https://runapi.ai/tr/workbuddy-hailuo zh-TW: https://runapi.ai/zh-TW/workbuddy-hailuo zh-HK: https://runapi.ai/zh-HK/workbuddy-hailuo ar: https://runapi.ai/ar/workbuddy-hailuo x-default: https://runapi.ai/workbuddy-hailuo model: hailuo --- > HTML version: https://runapi.ai/workbuddy-hailuo > Site index for agents: https://runapi.ai/llms.txt # Use Hailuo in WorkBuddy. Hailuo is MiniMax's video generation model producing native 1080p footage with accurate physics simulation across 6 variants — Hailuo 02 and 2.3, each with text-to-video and image-to-video endpoints in pro and standard tiers. WorkBuddy speaks MCP natively — add RunAPI as an MCP server once, ask the workbench agent for a video, and it calls the Hailuo tool and returns the finished URL. - [Get API Key](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · text to video + image to video · native 1080p ### Prompt ```text Generate a video with MiniMax Hailuo 02 Pro through the runapi MCP server. Requirements: - Use the runapi MCP server's video generation tool. - Set model to "hailuo-02-text-to-video-pro". - Prompt: "A glass marble rolls across a wooden desk, catches the edge, and falls in slow motion. Camera follows the marble. Soft window light, shallow depth of field." - The task is async — wait for it to complete and give me the video URL. ``` ### MCP config ```bash { "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ``` ### Response ```json { "task_id": "tsk_abc123", "status": "completed", "model": "hailuo-02-text-to-video-pro", "output": { "video_url": "https://media.runapi.ai/videos/tsk_abc123.mp4" } } ``` ## Use Hailuo in WorkBuddy in three steps 1. **Add the RunAPI MCP server** - Register RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp, with the Authorization header reading your key from RUNAPI_API_KEY. If you already connected RunAPI to WorkBuddy, the same server exposes the Hailuo tools — no extra setup needed. `{ "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ` 2. **Prompt the workbench agent** - Describe the scene, camera movement, and lighting in plain language, and name the variant — hailuo-02-text-to-video-pro for the best text-to-video quality. For image-anchored video, attach or link a source image and the agent uses an image_to_video variant with first_frame_image_url to preserve your subject. `Generate a video with hailuo-02-text-to-video-pro: a glass marble rolls across a wooden desk and falls in slow motion, camera following, soft window light. ` 3. **Receive the video URL** - The Hailuo task is asynchronous. WorkBuddy polls it through the MCP server until the status is completed, then posts the generated video URL into your conversation. Typical turnaround is under two minutes for pro tier. `{ "task_id": "tsk_abc123", "status": "completed", "output": { "video_url": "https://media.runapi.ai/videos/tsk_abc123.mp4" } } ` ## Hailuo tool parameters | Parameter | Type | Description | | --- | --- | --- | | `model` | `string` | Required. One of: hailuo-02-text-to-video-pro, hailuo-02-text-to-video-standard, hailuo-02-image-to-video-pro, hailuo-02-image-to-video-standard, hailuo-2.3-image-to-video-pro, hailuo-2.3-image-to-video-standard. | | `prompt` | `string` | Required. Text description of the video scene, camera movement, and lighting. | | `first_frame_image_url` | `string` | Required for image_to_video variants. URL of the source image used as the first frame. | | `last_frame_image_url` | `string` | Optional. URL of an image used as the last frame. Available on Hailuo 02 image-to-video only. | | `duration_seconds` | `integer` | Optional. Video length in seconds. Accepted values: 6 or 10. Defaults to 10 on standard, fixed on pro. | | `output_resolution` | `string` | Optional. Output resolution. 512p or 768p for 02 standard; 768p or 1080p for 2.3 variants. | ## What is Hailuo on WorkBuddy? Hailuo by MiniMax is one of the fastest video generators in its class, producing native 1080p footage with smooth believable motion and good detail retention. It handles physics simulation well — object permanence, motion coherence, and material interactions — and offers dedicated anime and stylized content modes through Hailuo 2.3. WorkBuddy reaches all 6 variants through the runapi MCP server, the same server and RUNAPI_API_KEY that power every other model in the workbench. ## Hailuo use cases - **Short-form social content** - Ask WorkBuddy for quick video clips for TikTok, Reels, or YouTube. Hailuo's fast generation speed makes it practical to produce multiple variations from the workbench and pick the best one. - **Explainer and marketing videos** - Create explainer videos and marketing clips from a plain-language brief. Hailuo maintains subject consistency and handles product close-ups with realistic lighting. - **Anime and stylized content** - Use Hailuo 2.3 variants for anime-style or illustration-based video with dedicated rendering modes not available in other video models — just name the variant in your WorkBuddy prompt. ## Hailuo + WorkBuddy questions ### Can I use Hailuo video generation in WorkBuddy? Yes. Add RunAPI as an MCP server with your RUNAPI_API_KEY, and the Hailuo tools appear alongside every other RunAPI model. Ask the workbench agent for a video with a scene description and a variant name, and it handles the call and the async polling for you. ### What is the difference between Hailuo 02 and Hailuo 2.3? Hailuo 02 supports both text-to-video and image-to-video with first-frame and last-frame control. Hailuo 2.3 is image-to-video only but adds improved body motion, micro-expressions, and dedicated anime and illustration rendering styles not available in 02. WorkBuddy can switch between them per request. ### How does pro vs standard pricing work? Hailuo 02 Pro text-to-video costs 57 cents per generation regardless of duration. Standard uses duration-based pricing — 30 cents for 6 seconds, 50 cents for 10 seconds. Image-to-video standard pricing also factors in output_resolution. Check the RunAPI pricing page for current rates. ### Does WorkBuddy wait for the video, or do I poll myself? The workbench agent handles it. Hailuo tasks are asynchronous — the tool returns a task_id, and WorkBuddy polls the task through the MCP server until the status is completed, then posts the video URL into your conversation. Typical generation time is 60-120 seconds. ### What resolution does Hailuo output? Hailuo 02 Pro outputs native 1080p. Standard outputs at 512p or 768p depending on the output_resolution parameter. Hailuo 2.3 variants support 768p or 1080p. No post-process upscaling is applied. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [Hailuo on RunAPI →](https://runapi.ai/models/hailuo.md) - See all Hailuo variants, pricing tiers, and API docs. ## Try Hailuo in WorkBuddy today. Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating native 1080p video with MiniMax Hailuo without leaving the workbench. [Browse models →](https://runapi.ai/models.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "RunAPI Hailuo for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Generate video with MiniMax Hailuo in WorkBuddy through the RunAPI MCP server. Text or image to video, 6 variants, native 1080p, one API key.", "url": "https://runapi.ai/workbuddy-hailuo" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Can I use Hailuo video generation in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Add RunAPI as an MCP server with your RUNAPI_API_KEY, and the Hailuo tools appear alongside every other RunAPI model. Ask the workbench agent for a video with a scene description and a variant name, and it handles the call and the async polling for you." } }, { "@type": "Question", "name": "What is the difference between Hailuo 02 and Hailuo 2.3?", "acceptedAnswer": { "@type": "Answer", "text": "Hailuo 02 supports both text-to-video and image-to-video with first-frame and last-frame control. Hailuo 2.3 is image-to-video only but adds improved body motion, micro-expressions, and dedicated anime and illustration rendering styles not available in 02. WorkBuddy can switch between them per request." } }, { "@type": "Question", "name": "How does pro vs standard pricing work?", "acceptedAnswer": { "@type": "Answer", "text": "Hailuo 02 Pro text-to-video costs 57 cents per generation regardless of duration. Standard uses duration-based pricing — 30 cents for 6 seconds, 50 cents for 10 seconds. Image-to-video standard pricing also factors in output_resolution. Check the RunAPI pricing page for current rates." } }, { "@type": "Question", "name": "Does WorkBuddy wait for the video, or do I poll myself?", "acceptedAnswer": { "@type": "Answer", "text": "The workbench agent handles it. Hailuo tasks are asynchronous — the tool returns a task_id, and WorkBuddy polls the task through the MCP server until the status is completed, then posts the video URL into your conversation. Typical generation time is 60-120 seconds." } }, { "@type": "Question", "name": "What resolution does Hailuo output?", "acceptedAnswer": { "@type": "Answer", "text": "Hailuo 02 Pro outputs native 1080p. Standard outputs at 512p or 768p depending on the output_resolution parameter. Hailuo 2.3 variants support 768p or 1080p. No post-process upscaling is applied." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use Hailuo in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy, prompt the workbench agent to generate video with a Hailuo text-to-video or image-to-video variant, and receive the finished video URL.", "step": [ { "@type": "HowToStep", "position": 1, "name": "Add the RunAPI MCP server", "text": "Register RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp, with the Authorization header reading your key from RUNAPI_API_KEY. If you already connected RunAPI to WorkBuddy, the same server exposes the Hailuo tools — no extra setup needed.", "url": "https://runapi.ai/workbuddy-hailuo#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Prompt the workbench agent", "text": "Describe the scene, camera movement, and lighting in plain language, and name the variant — hailuo-02-text-to-video-pro for the best text-to-video quality. For image-anchored video, attach or link a source image and the agent uses an image_to_video variant with first_frame_image_url to preserve your subject.", "url": "https://runapi.ai/workbuddy-hailuo#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Receive the video URL", "text": "The Hailuo task is asynchronous. WorkBuddy polls it through the MCP server until the status is completed, then posts the generated video URL into your conversation. Typical turnaround is under two minutes for pro tier.", "url": "https://runapi.ai/workbuddy-hailuo#how-step-3" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "RunAPI Hailuo for WorkBuddy", "item": "https://runapi.ai/workbuddy-hailuo" } ] } ] ```