Google · Image

OpenClaw x Nano Banana

Nano Banana is Google's image model embedded in Gemini, purpose-built for fast generation with in-image text accuracy. Through RunAPI, all Nano Banana variants share a single key.

5 variants from $0.04 / call Commercial OK
Get API Key View OpenClaw Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use nano-banana when it matches the task: 1K resolution; fast baseline (Aug 2025).

You have access to RunAPI task tools for Nano Banana.

Available Nano Banana models:
- nano-banana: 1K resolution; fast baseline (Aug 2025)
  endpoints: /api/v1/nano_banana/text_to_image
  request fields: model, prompt, aspect_ratio
- nano-banana-2: Built on Gemini 3.1 Flash; best multi-character consistency, 4–8s
  endpoints: /api/v1/nano_banana/text_to_image
  request fields: model, prompt, aspect_ratio
- nano-banana-2-lite: Fastest, lowest-cost Nano Banana image model for rapid creation and iteration
  endpoints: /api/v1/nano_banana/edit_image, /api/v1/nano_banana/text_to_image
  request fields: model, prompt, aspect_ratio
- nano-banana-edit: Prompt-driven image editing from an existing image
  endpoints: /api/v1/nano_banana/edit_image
  request fields: model, prompt, source_image_urls
- nano-banana-pro: Built on Gemini 3 Pro; up to 4K resolution, best text rendering, 10–20s
  endpoints: /api/v1/nano_banana/text_to_image
  request fields: model, prompt, aspect_ratio

Use the model ID and endpoint that match the user's request.
Example prompt: Create a motivational poster with the text 'Never Give Up' in bold serif, sunset mountains in the background.
/api/v1/nano_banana/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/nano_banana/text_to_image and save the returned Task id.
GET /api/v1/nano_banana/text_to_image/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/nano_banana/edit_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/nano_banana/edit_image and save the returned Task id.
GET /api/v1/nano_banana/edit_image/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
nano-banana
/api/v1/nano_banana/text_to_image
$0.04 / call Model detail
nano-banana-2
/api/v1/nano_banana/text_to_image
$0.08 / call Model detail
nano-banana-2-lite
/api/v1/nano_banana/edit_image /api/v1/nano_banana/text_to_image
$0.04 / call Model detail
nano-banana-edit
/api/v1/nano_banana/edit_image
$0.04 / call Model detail
nano-banana-pro
/api/v1/nano_banana/text_to_image
$0.18 / call Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with OpenClaw + Nano Banana

  • Interior design renders

    Generate many room layout variations with believable furniture placement and lighting, replacing manual 3D rendering during design iteration.

  • Hero images for landing pages

    Create hero images and social ad visuals that reflect current styles and real-world context.

  • Book covers with accurate typography

    Generate book cover designs with titles and author names rendered as part of the image.

Why Use Nano Banana Through RunAPI + OpenClaw

  • 5 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

OpenClaw + Nano Banana Questions

Can Nano Banana render readable text in images?

Yes. Include the exact words in the prompt and the model handles placement and legibility, which many diffusion models struggle with.

Can I edit existing images with Nano Banana in OpenClaw?

Yes. Use the edit endpoint shown on this page, pass the source image, and describe the change in the prompt. Edits can add or change text in the image.

Is Nano Banana asynchronous?

Yes. The create endpoint returns a task ID immediately. Poll the task status or provide a callback URL to receive a webhook when the image is ready.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Nano Banana with OpenClaw

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us