Google · Image

Hermes Agent 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.

Public versions and endpoints

Model IDVersionEndpointsStarting priceCatalog
nano-banana1K resolution; fast and cheap baseline (Aug 2025)
/api/v1/nano_banana/text_to_image
$0.040Model detail
nano-banana-2Built on Gemini 3.1 Flash; best multi-character consistency, 4–8s
/api/v1/nano_banana/text_to_image
$0.080Model detail
nano-banana-2-liteFastest, lowest-cost Nano Banana image model for rapid creation and iteration
/api/v1/nano_banana/edit_image
/api/v1/nano_banana/text_to_image
$0.040Model detail
nano-banana-editPrompt-driven image editing from an existing image
/api/v1/nano_banana/edit_image
$0.040Model detail
nano-banana-proBuilt on Gemini 3 Pro; 4K resolution, best text rendering, 10–20s
/api/v1/nano_banana/text_to_image
$0.180Model detail

Configuration

Guide endpoint: <endpoint>

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

Verify

Select <model-id> to generate verification commands.

How it works

  1. 1. Choose a model ID

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

  2. 2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. 3. Verify the result

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

FAQ

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.