Inference Logoinference shell
apps/google/gemini-nano-banana-2-1

Gemini Nano Banana 2.1

Gemini Nano Banana 2.1 via Vertex AI — Google's newest image model. Better design, mask editing and subject consistency than Nano Banana 2, and faster. Up to 4K, web search grounding.

run in browser →run via API
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# view schema & details
$belt app get google/gemini-nano-banana-2-1
# run
$belt app run google/gemini-nano-banana-2-1

api reference

about

gemini nano banana 2.1 via vertex ai — google's newest image model. better design, mask editing and subject consistency than nano banana 2, and faster. up to 4k, web search grounding.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash
1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash
1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python
1from inferencesh import inference23client = inference()456result = client.run({7        "app": "google/gemini-nano-banana-2-1",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python
1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "google/gemini-nano-banana-2-1",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python
1# local file paths are automatically uploaded2result = client.run({3    "app": "google/gemini-nano-banana-2-1",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python
1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python
1result = client.run({2    "app": "google/gemini-nano-banana-2-1",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}
idstring— task id
statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)
outputobject— task output (when completed)
errorstring— error message (when failed)
session_idstring— session id (if using sessions)
created_atstring— iso timestamp
updated_atstring— iso timestamp

5. schema

input

promptstring*

the prompt for image generation or editing. describe what you want to create or change.

imagesarray

optional input images for editing (up to 14). when provided, the model edits them based on the prompt. supported formats: jpeg, png, webp, heic, heif

context_filesarray

optional video or pdf files passed as extra context (up to 10 videos). supported formats: mp4, mov, webm, mpeg, pdf

num_imagesinteger

number of images to generate.

default: 1min:1max:4
aspect_ratiostring

aspect ratio. supports extreme ratios like 1:4, 4:1, 1:8, 8:1. use 'auto' to match the first input image.

default: "1:1"
options:"auto""21:9""16:9""8:1""4:1""3:2""4:3""5:4""1:1""4:5""3:4""2:3""1:4""1:8""9:16"
resolutionstring

output resolution: 1k, 2k, 4k.

default: "1K"
options:"1K""2K""4K"
output_formatstring

output format for the generated images.

default: "png"
options:"png""jpeg""webp"
enable_google_searchboolean

enable google search grounding (web and image search) for real-world subjects.

default: false
safety_tolerancestring

safety filter threshold.

default: "BLOCK_NONE"
options:"BLOCK_NONE""BLOCK_LOW_AND_ABOVE""BLOCK_MEDIUM_AND_ABOVE""BLOCK_ONLY_HIGH"
retry_countinteger

number of automatic retries on 429 rate limit errors.

default: 2min:0max:5

output

descriptionstring

text description from the model

imagesarray*

the generated or edited images

ready to run Gemini Nano Banana 2.1?

try in browserbrowse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.