Nano Banana 2.1 API

Introduction

Nano Banana 2.1 Edit runs Google's newest Nano Banana model on images you already have. It accepts one to fourteen sources, keeps the source shape or reframes to one of fourteen shapes, and renders at 1k, 2k or 4k. Google built this update for conversational editing, with steadier characters across edits and more accurate text.

Choose a mode by starting material

Key features

Up to fourteen references

Combine people, garments, products and rooms from up to fourteen images. Google rates the model for up to four consistent characters and ten objects in one fusion. In our three-image edit, the man's face and the jacket's brass snaps and pockets carried over.

Faces kept through big changes

A daytime greenhouse photo became a night at the opera with a new gown, new hair styling and a new room, and the face stayed hers.

Text designed into the scene

A blank album sleeve held in a photo got a full cover design with the quoted title and band name, without disturbing the people holding it.

Reframe while editing

Aspect ratio auto keeps the source shape; any of fourteen shapes reframes the result. With several sources of different shapes, set the shape yourself.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 8 credits per image ($0.08).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Outfit and product try-ons

Put a garment, bag or product from a catalogue shot on a person from another photo, in the setting you choose.

Relocation and time-of-day changes

Move a person to a new place or turn day into night for a campaign, keeping the face.

Packaging and signage mock-ups

Design labels, sleeves, signs and posters directly into an existing photo, with the text in quotes.

Prompt guide & pro tips

Name each source by position

Say the first image, the second image, the third image, and what each one supplies: the person, the garment, the room.

List what must stay

After describing the change, name what stays: the face, the hair colour, the jacket's buttons. The model respects a written list.

Draft at 1k

Test the instruction at 1k first; if the change reads correctly, run the same request at 2k or 4k.

API quick start

Call the Nano Banana 2.1 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model google/nano-banana-2.1/edit and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "google/nano-banana-2.1/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "aspect_ratio": "auto",
    "resolution": "1k",
    "output_format": "png"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Nano Banana 2.1 API questions

All Nano Banana models

Nano Banana Pro plans the layout before it draws, so it handles dense text, diagrams and multi-part designs more carefully. Nano Banana 2.1 is newer, quicker and less than half the price per image, and adds 8:1 banners plus web and image search.

• Nano Banana 2.1 APIGoogle's newest Nano Banana, sharp text and 4K outputFrom 8 credits per image
• Nano Banana Pro APIPlans the layout first: dense text, diagrams and 4K editsFrom 17 credits per image
• Nano Banana 2 APIFast Gemini images up to 4K, with up to 14 referencesFrom 6 credits per image

Other image APIs

• GPT Image 2.5 Sunburst APIOpenAI's quality-first model, up to 4K with clean textFrom 1 credit per image
• Seedream 5.0 Pro APIHigh-detail images and edits from up to ten referencesFrom 6 credits per image
• FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
• Qwen Image 2.1 Pro APIUp to six detailed 2K images from one promptFrom 6 credits per image
• Qwen Image 2.1 Turbo APIFast 8-step renders, up to six per promptFrom 3 credits per image
• Qwen Image 2.1 APIOpen model with 2K output and transparent backgroundsFrom 4 credits per image

More about Nano Banana 2.1

Try it

Nano Banana 2.1 AI Image Generator onlineCreate images with Nano Banana 2.1 in PopNow

Compare

Nano Banana 2.1 vs GPT Image 2.5 SunburstNano Banana 2.1 vs Nano Banana ProSeedream 5.0 Pro vs Nano Banana 2.1

Docs

Nano Banana 2.1 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get Nano Banana 2.1 results without polling