--- title: Use Z Image in WorkBuddy via RunAPI — Image API Guide | RunAPI description: Generate images with Alibaba Z Image in WorkBuddy via the RunAPI MCP server. One API key, bilingual text rendering, fast text-to-image from the workbench. url: https://runapi.ai/workbuddy-z-image.md canonical: https://runapi.ai/workbuddy-z-image locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-z-image zh-CN: https://runapi.ai/zh-CN/workbuddy-z-image es: https://runapi.ai/es/workbuddy-z-image ja: https://runapi.ai/ja/workbuddy-z-image de: https://runapi.ai/de/workbuddy-z-image fr: https://runapi.ai/fr/workbuddy-z-image pt-BR: https://runapi.ai/pt-BR/workbuddy-z-image ko: https://runapi.ai/ko/workbuddy-z-image it: https://runapi.ai/it/workbuddy-z-image nl: https://runapi.ai/nl/workbuddy-z-image pl: https://runapi.ai/pl/workbuddy-z-image tr: https://runapi.ai/tr/workbuddy-z-image zh-TW: https://runapi.ai/zh-TW/workbuddy-z-image zh-HK: https://runapi.ai/zh-HK/workbuddy-z-image ar: https://runapi.ai/ar/workbuddy-z-image x-default: https://runapi.ai/workbuddy-z-image model: z-image --- > HTML version: https://runapi.ai/workbuddy-z-image > Site index for agents: https://runapi.ai/llms.txt # Use Z Image in WorkBuddy. Z Image is Alibaba's fast image generation model with bilingual text rendering in Chinese and English. WorkBuddy speaks MCP natively — add RunAPI as an MCP server once, and the workbench agent can call Z Image as a tool with the same RUNAPI_API_KEY used for every other model. - [Get API Key](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · one API key · async task handled by the agent ### Prompt ```text Use the runapi MCP server to generate an image with Z Image. Requirements: - Call the RunAPI text-to-image tool with model set to "z-image". - Prompt: "A neon-lit Tokyo street at night with Japanese shop signs, cinematic lighting, 8K detail". - Wait until the task completes, then give me the final image URL. ``` ### MCP config ```bash { "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer ${RUNAPI_API_KEY}" } } } } ``` ### Result ```json { "task_id": "tsk_abc123", "status": "completed", "model": "z-image", "output": { "image_url": "https://runapi.ai/files/tsk_abc123.png" } } ``` ## Use Z Image in WorkBuddy in three steps 1. **Add the RunAPI MCP server** - Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected for other models, skip this step — the same server exposes Z Image. `url: https://runapi.ai/mcp` 2. **Prompt the workbench agent** - Paste the prompt into WorkBuddy and ask it to use the runapi MCP server with model set to z-image. Z Image accepts prompts in Chinese, English, or both, and renders text in either script accurately. `model: z-image` 3. **Let the agent return the result** - WorkBuddy calls the RunAPI text-to-image tool, which creates an async task. The agent handles the waiting for you and drops the finished image URL back into the conversation when the task completes. `task_id: tsk_abc123` ## Z Image API parameters | Parameter | Type | Description | | --- | --- | --- | | `model` | `string` | Required. Use z-image. | | `prompt` | `string` | Text description. Supports Chinese and English. | | `negative_prompt` | `string` | Optional. What to avoid in the image. | | `size` | `string` | Optional. Output dimensions, e.g. 1024x1024. | | `callback_url` | `string` | Optional. Webhook URL for async completion notification. | ## What is Z Image on WorkBuddy? Z Image is the speed-optimized image model that users call "amazing" for its sub-second generation and ultra-realistic output. It runs on Apache 2.0 open source, renders bilingual text in Chinese and English, and captures subtle facial details that other fast models miss. At around $0.004 per image through RunAPI, it is one of the cheapest options available. In WorkBuddy it appears as a tool on the runapi MCP server, so the workbench agent can generate images mid-task without leaving the conversation. ## Z Image use cases - **Concept exploration and rapid prototyping** - Ask WorkBuddy for a dozen visual directions and get them back in seconds at fractions of a cent each — explore broadly before committing a more expensive model to final output. - **Bilingual marketing campaigns** - Create marketing visuals with accurately rendered Chinese and English text in a single image, useful for cross-border e-commerce and multilingual social media produced straight from the workbench. - **Fashion and product photography mockups** - Generate realistic product photography mockups with accurate material textures and lighting, fast enough to iterate on compositions live while you refine the brief with the agent. ## Z Image + WorkBuddy questions ### Can I use Z Image in WorkBuddy? Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, and the workbench agent can call the text-to-image tool with model set to z-image. ### Do I need a separate API key for Z Image? No. The same RUNAPI_API_KEY behind the runapi MCP server also covers Z Image. All RunAPI models share one key and one credits balance, so nothing extra to configure per model. ### Is Z Image async or sync? Z Image is async. The tool call returns a task_id immediately, and the WorkBuddy agent handles the follow-up for you — it waits for the task to complete and returns the image URL in the conversation. ### What does Z Image cost? Z Image uses pay-as-you-go pricing at around $0.004 per image, making it one of the cheapest options on RunAPI. Check the RunAPI pricing page for the current rate. There is no monthly subscription or minimum spend. ### How does Z Image compare to Flux or Nano Banana? Z Image wins on speed and cost — sub-second generation at a fraction of a cent per image. Flux 2 and Nano Banana produce higher-fidelity output but cost 5-10x more and take longer. Use Z Image for volume work and concept exploration, then switch models in the same MCP server for final selects. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [Z Image models →](https://runapi.ai/models/z-image.md) - See all Z Image variants, pricing, and API docs. ## Try Z Image in WorkBuddy today. Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating images with bilingual text rendering from 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 Z Image for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Generate images with Alibaba Z Image in WorkBuddy via the RunAPI MCP server. One API key, bilingual text rendering, fast text-to-image from the workbench.", "url": "https://runapi.ai/workbuddy-z-image" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Can I use Z Image in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, and the workbench agent can call the text-to-image tool with model set to z-image." } }, { "@type": "Question", "name": "Do I need a separate API key for Z Image?", "acceptedAnswer": { "@type": "Answer", "text": "No. The same RUNAPI_API_KEY behind the runapi MCP server also covers Z Image. All RunAPI models share one key and one credits balance, so nothing extra to configure per model." } }, { "@type": "Question", "name": "Is Z Image async or sync?", "acceptedAnswer": { "@type": "Answer", "text": "Z Image is async. The tool call returns a task_id immediately, and the WorkBuddy agent handles the follow-up for you — it waits for the task to complete and returns the image URL in the conversation." } }, { "@type": "Question", "name": "What does Z Image cost?", "acceptedAnswer": { "@type": "Answer", "text": "Z Image uses pay-as-you-go pricing at around $0.004 per image, making it one of the cheapest options on RunAPI. Check the RunAPI pricing page for the current rate. There is no monthly subscription or minimum spend." } }, { "@type": "Question", "name": "How does Z Image compare to Flux or Nano Banana?", "acceptedAnswer": { "@type": "Answer", "text": "Z Image wins on speed and cost — sub-second generation at a fraction of a cent per image. Flux 2 and Nano Banana produce higher-fidelity output but cost 5-10x more and take longer. Use Z Image for volume work and concept exploration, then switch models in the same MCP server for final selects." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use Z Image in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy, then prompt the workbench agent to generate images with Alibaba Z Image through the RunAPI text-to-image tool.", "step": [ { "@type": "HowToStep", "position": 1, "name": "Add the RunAPI MCP server", "text": "Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected for other models, skip this step — the same server exposes Z Image.", "url": "https://runapi.ai/workbuddy-z-image#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Prompt the workbench agent", "text": "Paste the prompt into WorkBuddy and ask it to use the runapi MCP server with model set to z-image. Z Image accepts prompts in Chinese, English, or both, and renders text in either script accurately.", "url": "https://runapi.ai/workbuddy-z-image#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Let the agent return the result", "text": "WorkBuddy calls the RunAPI text-to-image tool, which creates an async task. The agent handles the waiting for you and drops the finished image URL back into the conversation when the task completes.", "url": "https://runapi.ai/workbuddy-z-image#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 Z Image for WorkBuddy", "item": "https://runapi.ai/workbuddy-z-image" } ] } ] ```