--- title: Use Imagen 4 in WorkBuddy via RunAPI — MCP Guide | RunAPI description: Generate images with Google Imagen 4 inside WorkBuddy through RunAPI. One MCP server exposes Fast, Standard, and Ultra tiers with async polling handled. url: https://runapi.ai/workbuddy-imagen-4.md canonical: https://runapi.ai/workbuddy-imagen-4 locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-imagen-4 zh-CN: https://runapi.ai/zh-CN/workbuddy-imagen-4 es: https://runapi.ai/es/workbuddy-imagen-4 ja: https://runapi.ai/ja/workbuddy-imagen-4 de: https://runapi.ai/de/workbuddy-imagen-4 fr: https://runapi.ai/fr/workbuddy-imagen-4 pt-BR: https://runapi.ai/pt-BR/workbuddy-imagen-4 ko: https://runapi.ai/ko/workbuddy-imagen-4 it: https://runapi.ai/it/workbuddy-imagen-4 nl: https://runapi.ai/nl/workbuddy-imagen-4 pl: https://runapi.ai/pl/workbuddy-imagen-4 tr: https://runapi.ai/tr/workbuddy-imagen-4 zh-TW: https://runapi.ai/zh-TW/workbuddy-imagen-4 zh-HK: https://runapi.ai/zh-HK/workbuddy-imagen-4 ar: https://runapi.ai/ar/workbuddy-imagen-4 x-default: https://runapi.ai/workbuddy-imagen-4 model: imagen-4 --- > HTML version: https://runapi.ai/workbuddy-imagen-4 > Site index for agents: https://runapi.ai/llms.txt # Use Imagen 4 in WorkBuddy. Imagen 4 is Google DeepMind's image generation model with accurate text rendering and high prompt fidelity. WorkBuddy calls it through the runapi MCP server — the same server and RUNAPI_API_KEY used for chat expose all three tiers as callable tools in the workbench, with no extra provider accounts. - [Get API Key](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · three quality tiers · async polling handled ### Prompt ```text Generate an image with Google Imagen 4 through the runapi MCP server. Requirements: - Call the image generation tool exposed by the runapi MCP server. - Set the model to "imagen-4". - Prompt: "A ceramic coffee mug on a wooden table with morning light, the text HELLO printed on the side in serif font, photorealistic." - Add aspect_ratio or negative_prompt if needed. - Wait for the task to complete and return the image 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": "imagen-4", "output": { "image_url": "https://media.runapi.ai/outputs/tsk_abc123.png" } } ``` ## Use Imagen 4 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 in WorkBuddy for chat, the same server exposes Imagen 4. `url: https://runapi.ai/mcp` 2. **Prompt the workbench agent** - Ask WorkBuddy to generate an image with model imagen-4 and a descriptive prompt. Add aspect_ratio or negative_prompt as needed. Switch the slug to imagen-4-fast for cheap draft rounds or imagen-4-ultra for maximum detail. `Generate a photorealistic image with Imagen 4` 3. **Get the result** - WorkBuddy calls the RunAPI MCP tool, which runs the generation as an async task and polls the status for you. When the status changes to completed, the agent reports the generated image URL back in the workbench. `task_id: tsk_abc123` ## Imagen 4 API parameters | Parameter | Type | Description | | --- | --- | --- | | `model` | `string` | Required. imagen-4, imagen-4-fast, or imagen-4-ultra. | | `prompt` | `string` | Text description of the desired image. | | `aspect_ratio` | `string` | Optional. E.g. 1:1, 16:9, 9:16. | | `negative_prompt` | `string` | Optional. What to avoid in the generated image. | ## What is Imagen 4 on WorkBuddy? Imagen 4 is Google DeepMind's image model that users call "stunning in seconds" with what reviewers describe as the "best value per pixel" in the API market. It ships in three tiers — Fast for rapid prototyping, Standard for production work, and Ultra for maximum detail — with the cheapest tier running around $0.02 per image. WorkBuddy reaches all three tiers through the runapi MCP server with a single RUNAPI_API_KEY. ## Imagen 4 use cases - **Rapid prototyping at scale** - Use the Fast tier for quick concept exploration at $0.02 per image, generating dozens of variations before committing to a direction with the Standard or Ultra tier. - **UI and label design with readable text** - Generate interface mockups, product labels, and signage designs where the embedded text renders cleanly and follows the prompt precisely. - **Photorealistic textures and materials** - Create photorealistic material textures, vintage travel postcards, and editorial photography scenes with accurate lighting and surface detail, straight from a WorkBuddy task. ## Imagen 4 + WorkBuddy questions ### How do I use Imagen 4 in WorkBuddy? Add RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, then prompt the workbench agent to generate an image with model imagen-4. The agent calls the RunAPI MCP tool and returns the finished image URL — no plugins or GCP account required. ### Do I need a separate API key for Imagen 4? No. The same RUNAPI_API_KEY behind the runapi MCP server works for all 250+ models across chat, image, video, and music. One key, one billing account. ### Is Imagen 4 async, and does WorkBuddy handle the waiting? Generation runs as an async task that returns a task_id with status pending. The RunAPI MCP server handles status polling, so the WorkBuddy agent simply reports the image URL when the task completes. ### When should I use Imagen 4 Fast vs Standard vs Ultra? Fast is for draft iterations and concept exploration where speed and cost matter more than detail — it runs at around $0.02 per image. Standard is the default for production work. Ultra produces the highest-detail output for hero images or print-quality assets. All three use the same prompt format — just change the model slug. ### How strict are Imagen 4's content filters? Imagen 4 has relatively strict content filters that can sometimes flag innocuous prompts. If a generation is rejected, rephrase to be more explicit about the intended context. The filters are most sensitive around people and brand imagery. All outputs include an invisible SynthID watermark. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not configured yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [Imagen 4 models →](https://runapi.ai/models/imagen-4.md) - See all Imagen 4 variants, pricing, and API docs. ## Try Imagen 4 in WorkBuddy today. Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating images with Google Imagen 4. [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 Imagen 4 for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Generate images with Google Imagen 4 inside WorkBuddy through RunAPI. One MCP server exposes Fast, Standard, and Ultra tiers with async polling handled.", "url": "https://runapi.ai/workbuddy-imagen-4" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "How do I use Imagen 4 in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "Add RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp with your RUNAPI_API_KEY, then prompt the workbench agent to generate an image with model imagen-4. The agent calls the RunAPI MCP tool and returns the finished image URL — no plugins or GCP account required." } }, { "@type": "Question", "name": "Do I need a separate API key for Imagen 4?", "acceptedAnswer": { "@type": "Answer", "text": "No. The same RUNAPI_API_KEY behind the runapi MCP server works for all 250+ models across chat, image, video, and music. One key, one billing account." } }, { "@type": "Question", "name": "Is Imagen 4 async, and does WorkBuddy handle the waiting?", "acceptedAnswer": { "@type": "Answer", "text": "Generation runs as an async task that returns a task_id with status pending. The RunAPI MCP server handles status polling, so the WorkBuddy agent simply reports the image URL when the task completes." } }, { "@type": "Question", "name": "When should I use Imagen 4 Fast vs Standard vs Ultra?", "acceptedAnswer": { "@type": "Answer", "text": "Fast is for draft iterations and concept exploration where speed and cost matter more than detail — it runs at around $0.02 per image. Standard is the default for production work. Ultra produces the highest-detail output for hero images or print-quality assets. All three use the same prompt format — just change the model slug." } }, { "@type": "Question", "name": "How strict are Imagen 4's content filters?", "acceptedAnswer": { "@type": "Answer", "text": "Imagen 4 has relatively strict content filters that can sometimes flag innocuous prompts. If a generation is rejected, rephrase to be more explicit about the intended context. The filters are most sensitive around people and brand imagery. All outputs include an invisible SynthID watermark." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use Imagen 4 in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy and prompt the workbench agent to generate images with Google Imagen 4.", "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 in WorkBuddy for chat, the same server exposes Imagen 4.", "url": "https://runapi.ai/workbuddy-imagen-4#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Prompt the workbench agent", "text": "Ask WorkBuddy to generate an image with model imagen-4 and a descriptive prompt. Add aspect_ratio or negative_prompt as needed. Switch the slug to imagen-4-fast for cheap draft rounds or imagen-4-ultra for maximum detail.", "url": "https://runapi.ai/workbuddy-imagen-4#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Get the result", "text": "WorkBuddy calls the RunAPI MCP tool, which runs the generation as an async task and polls the status for you. When the status changes to completed, the agent reports the generated image URL back in the workbench.", "url": "https://runapi.ai/workbuddy-imagen-4#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 Imagen 4 for WorkBuddy", "item": "https://runapi.ai/workbuddy-imagen-4" } ] } ] ```