Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
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.
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_servers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"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
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
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
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
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.
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.
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.
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.
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 general setup
Not configured yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →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.