Nano Banana 2.1 Edit API for Prompt-Based Image Editing

Pass 1 to 9 reference images in image_list plus an instruction to POST /api/v1/images/generations with model: nano-banana-2-1-edit. The model edits or combines them into one new image at 1k, 2k or 4k, priced the same no matter how many references you send.
Get API Key
Photographer's light table with several printed photos being arranged into one composition

Edit, Restyle and Combine with One Instruction

One photo, one targeted change

Send a single image with an instruction such as change the background to a beach. The prompt is 1 to 2000 characters and ratio defaults to auto, letting the model choose the framing.
Portrait photo on an easel with half the background repainted as a sunny beach

Up to nine references in one request

Put 1 to 9 objects of the form {"url": "https://…"} in image_list to combine a product, a model, a location and a style into one scene. Reference images are included in the price.
Moodboard wall with nine pinned photos connected to one finished composite print

Same knobs as text-to-image

image_size (1k, 2k, 4k), fifteen ratio values including 1:8 and 8:1, web_search grounding and thinking_level (High or Minimal) all work in edit requests.
Photo retouching station with a calibrated monitor hood and a color checker card
model, prompt and image_list are required; the rest are optional.

Nano Banana 2.1 Edit Request Fields and Limits

model

Always nano-banana-2-1-edit. For text-only generation use nano-banana-2-1.

prompt (required)

The edit or composition instruction, 1 to 2000 characters.

image_list (required)

1 to 9 reference images as [{"url": "https://…"}].

ratio

auto (default), 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2, 4:5, 5:4, 21:9, 1:4, 4:1, 1:8 or 8:1.

image_size

1k (default), 2k or 4k; 0.5k is not offered.

web_search, thinking_level, custom_callback_url

Optional web search grounding; reasoning depth High or Minimal (omit for medium, cannot be disabled); and an HTTPS URL that receives the job-detail body on every status change.
A flat price per output image. Reference images and thinking are included, whatever the number of references.

Nano Banana 2.1 Edit API Pricing

1k: 2.92 tokens ($0.0584) per image

Applies whether image_list holds 1 reference or 9.

2k: 4.02 tokens ($0.0804) per image

The mid tier for edits destined for larger screens.

4k: 8.08 tokens ($0.1616) per image

The highest resolution available for edits.

Same price as text-to-image

nano-banana-2-1 and nano-banana-2-1-edit share the same table. Failed jobs are refunded automatically, and cost shows what was actually charged.

Integrate the Nano Banana 2.1 Edit API

1

1. Create an API key

Generate a key at /keys and send it as Authorization: Bearer <key>.
2

2. Publish the references

Upload the images you want to edit to storage that serves them over public URLs.
3

3. Submit the edit

POST {"model": "nano-banana-2-1-edit", "prompt": "change the background to a beach", "image_list": [{"url": "https://…"}]} to /api/v1/images/generations and store the img_uuid.
4

4. Collect the result

Poll GET /api/v1/jobs/detail or handle the callback; on success, download the image from json before link_expired_at.
Create an API Key
Editing features that start from images your users already have.

What Developers Build with Nano Banana 2.1 Edit

Background and scene swaps

Place a product or person into a new setting with a one-line instruction instead of manual masking.

Multi-reference product scenes

Combine a product shot, a model photo and a location into one campaign image using several entries in image_list.

Text and label edits

Change wording on signs, packaging or posters in an existing image, taking advantage of the model's improved text rendering.

Consistent series

Reuse the same character or product references across many requests to keep a set of images visually consistent.
References, pricing and results.

Nano Banana 2.1 Edit API FAQ

What is the endpoint?

POST https://api.goenhance.ai/api/v1/images/generations with model: nano-banana-2-1-edit.

How many reference images can I send?

Between 1 and 9 in image_list. At least one is required.

Do more references cost more?

No. The price depends only on image_size: 2.92 tokens ($0.0584) at 1k, 4.02 tokens ($0.0804) at 2k, 8.08 tokens ($0.1616) at 4k.

Can I control the output shape?

Yes, with ratio. Leave it at auto to let the model choose framing from your prompt, or pick one of the 14 fixed ratios.

How many images does a request return?

One edited image per request, returned as a type: image entry in the job's json list.

What happens if the edit fails?

The job ends with status: failed and the tokens are refunded automatically.

Start Building with the Nano Banana 2.1 Edit API

Nano Banana 2.1 Edit API: Pricing & Integration | GoEnhance