Skip to content
Pricing
Get started ↗
Google

Nano Banana 2 API

Playground
LLMs
llms.txt ↗
Try online

Create images with Nano Banana 2 using text, images. Available resolutions: 512 / 1k / 2k / 4k. Try the current API settings, preview results and reuse your inputs.

Modalities
TextImageImage
Published
1kAbout 55% less than official
$0.03/ request
$0.067 · official reference
2kAbout 60% less than official
$0.04/ request
$0.101 · official reference
4kAbout 60% less than official
$0.06/ request
$0.151 · official reference
Input
Sign in to choose a key from your account.
Generation mode
Guide generation with the supported reference inputs below.
images0
JPEG / PNG / WEBP · ≤ 10 MB
Add a reference before running in reference mode.
Request preview
{
  "model": "nano-banana2",
  "input": {
    "images": [],
    "resolution": "1k",
    "aspect_ratio": "auto",
    "output_format": "jpeg",
    "prompt": "Premium product editorial for an imaginary ceramic fragrance bottle named AER, warm limestone pedestal, precise soft shadow, quiet-luxury art direction, restrained cream and cobalt palette, clean studio photography, no existing brands or logos."
  }
}
Checking current pricing…
Output
Example output
Quiet-luxury product editorial
Open original ↗
Next

Nano Banana 2 pricing

Estimate one request, then choose a budget for your workflow.

UsageQuantityRateCost
1k1 request$0.03/ request$0.03
Cost per request$0.03

Public USD estimate. Your account rate and final recorded usage determine the actual charge.

View all specifications and prices
SpecificationOur priceOfficial reference
1k$0.03 / request$0.067 About 55% less than official
2k$0.04 / request$0.101 About 60% less than official
4k$0.06 / request$0.151 About 60% less than official

See what it can create.

Capability-based prompts and platform-generated examples are labeled separately, with their sources.

Official capability source ↗ · 2026-10-14

Visual iteration

Create a cafe opening graphic with warm light, a paper menu and wooden surfaces. Make the headline “OPEN TODAY” clearly readable.

Use an explicit scene and headline when iterating visual concepts.

Consistent character editing

Place the original reference character in a full-body rainy street scene. Preserve facial traits, costume design and main colors; change only pose and setting.

Provide a character reference before changing pose and setting.

Platform-generated examples

nano-banana2 · Quiet-luxury product editorial

Quiet-luxury product editorial

View prompt

Premium product editorial for an imaginary ceramic fragrance bottle named AER, warm limestone pedestal, precise soft shadow, quiet-luxury art direction, restrained cream and cobalt palette, clean studio photography, no existing brands or logos.

nano-banana2 · Typographic culture poster

Typographic culture poster

View prompt

Contemporary cultural poster for a fictional exhibition titled TIDELINE, bold readable Latin typography, modular grid, deep ultramarine and warm coral, subtle paper grain, generous negative space, no real logos.

nano-banana2 · Cinematic architectural scene

Cinematic architectural scene

View prompt

Cinematic coastal library at first light, weathered pale stone, shallow reflecting pool, a single person for scale, atmospheric haze, realistic architecture and believable materials.

nano-banana2 · Structured visual explainer

Structured visual explainer

View prompt

Clear four-step visual explainer for a fictional circular packaging workflow: collect, clean, remake, return; accurate simple icons, readable short English labels, off-white background, forest green and amber accents.

What is Nano Banana 2?

Create images with Nano Banana 2 using text, images. Available resolutions: 512 / 1k / 2k / 4k. Try the current API settings, preview results and reuse your inputs.

Nano Banana 2 maps to Gemini 3.1 Flash Image for efficient image generation and editing at production scale.

Official model information ↗ · 2026-10-14

Nano Banana 2 specifications

Model IDnano-banana2
ProviderGoogle
API/v1/tasks
Resolution512 / 1k / 2k / 4k
Aspect ratioauto / 1:1 / 3:2 / 2:3 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9 / 1:4 / 1:8 / 4:1 / 8:1
Output formatpng / jpeg / webp
Reference imagesSupported; see input validation

Before you generate

  • Use the current model ID and the API request shape shown on this page.
  • Generation is asynchronous. Keep the returned task ID to retrieve the result and billing status.
  • Only options supported by the current platform contract are exposed in Playground.

Task fit and practical limits

For product visuals or social content, define the delivery aspect ratio, resolution and format before adding reference images. Keep the prompt and inputs, then review text, details and consistency with references.

These are acceptance checks, not guarantees of output quality or speed. A resolution label is not a fixed-pixel promise. Use the current contract and account pricing for supported inputs, combinations and cost; validate an approved small sample before batching.

Image specifications and reference tutorial · Batch budgeting and cost reconciliation

Compare Nano Banana 2 with related models

SpecificationNano Banana 2GPT Image 2GPT Image 2.5 Flare
ProviderGoogleOpenAIOpenAI
Input → outputTextImageImageTextImageImageTextImageImage
Selection basisCurrent modelBoth declare text, image input · Same billing unitsBoth declare text, image input · Same billing units
Resolution512 / 1k / 2k / 4k1k / 2k / 4k1k / 2k / 4k
Reference imagesSupported2020
Starting price$0.03 / request$0.02 / request$0.02 / request

Choose by the input types, output settings and billing unit your workflow needs. Try the same prompt across models to compare results for your own use case.

BUILD WITH NEWROUTERS

Build with Nano Banana 2 in your app

Submit parameters through the Media Tasks API, then retrieve the result with the task ID. Image and video models keep their own input requirements.

  1. 01
    Get your API key

    Sign in and prepare a key with access to this model.

  2. 02
    Configure your request

    Choose parameters in Playground and copy the API example.

  3. 03
    Run and inspect the result

    Review status, outputs and charges in History.

Read the model API guide ↗

API integration

POST /v1/tasks · Authorization: Bearer

cURL
curl 'https://newrouters.com/v1/tasks' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "nano-banana2",
  "input": {
    "images": [],
    "resolution": "1k",
    "aspect_ratio": "auto",
    "output_format": "jpeg",
    "prompt": "A quiet mountain lake at sunrise, soft morning light."
  }
}'
JavaScript
const response = await fetch("https://newrouters.com/v1/tasks", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer $MODEL_API_KEY"
  },
  body: JSON.stringify({
    "model": "nano-banana2",
    "input": {
      "images": [],
      "resolution": "1k",
      "aspect_ratio": "auto",
      "output_format": "jpeg",
      "prompt": "A quiet mountain lake at sunrise, soft morning light."
    }
  })
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.text());
Python
import json
import requests

response = requests.post(
    "https://newrouters.com/v1/tasks",
    headers=json.loads("{\"Content-Type\":\"application/json\",\"Authorization\":\"Bearer $MODEL_API_KEY\"}"),
    json=json.loads("{\"model\":\"nano-banana2\",\"input\":{\"images\":[],\"resolution\":\"1k\",\"aspect_ratio\":\"auto\",\"output_format\":\"jpeg\",\"prompt\":\"A quiet mountain lake at sunrise, soft morning light.\"}}"),
    timeout=300,
)
response.raise_for_status()
print(response.text)

Poll the returned task ID for processing status and output assets.

curl -H "Authorization: Bearer $MODEL_API_KEY" "https://newrouters.com/v1/tasks/$TASK_ID"

Documentation: Authentication · Task status and results · Error handling

Full API parameters and combination constraints

Request parameters

ParameterTypeValues & constraints
countinteger1
imagesarrayDefault: []
prompt *string
resolutionJSON"512" · "1k" · "2k" · "4k"Default: "1k"
aspect_ratioJSON"auto" · "1:1" · "3:2" · "2:3" · "3:4" · "4:3" · "4:5" · "5:4" · "9:16" · "16:9" · "21:9" · "1:4" · "1:8" · "4:1" · "8:1"Default: "auto"
ground_searchboolean
output_formatJSON"png" · "jpeg" · "webp"Default: "jpeg"
Full JSON Schema and combination constraints
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "count": {
      "enum": [
        1
      ],
      "type": "integer"
    },
    "images": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "default": []
    },
    "prompt": {
      "type": "string",
      "maxLength": 100000,
      "minLength": 1
    },
    "resolution": {
      "enum": [
        "512",
        "1k",
        "2k",
        "4k"
      ],
      "default": "1k"
    },
    "aspect_ratio": {
      "enum": [
        "auto",
        "1:1",
        "3:2",
        "2:3",
        "3:4",
        "4:3",
        "4:5",
        "5:4",
        "9:16",
        "16:9",
        "21:9",
        "1:4",
        "1:8",
        "4:1",
        "8:1"
      ],
      "default": "auto"
    },
    "ground_search": {
      "type": "boolean"
    },
    "output_format": {
      "enum": [
        "png",
        "jpeg",
        "webp"
      ],
      "default": "jpeg"
    }
  },
  "additionalProperties": false
}

Nano Banana 2 API · Common questions

Answers about pricing, inputs, integration and results.

How much does Nano Banana 2 cost?

The current public price starts at $0.03 / request. The pricing section lists each specification. Playground checks your account price before submitting; the completed request records the final charge.

How do I get a NewRouters API key?

Sign in and open Quick Start above the workspace. Select or create a key with access to this model, then copy the request example.

Which inputs and output settings are supported?

Supported input fields: count, images, prompt, resolution, aspect_ratio, ground_search, output_format. The parameter table includes allowed values and defaults.

Can I use reference images?

Yes. Use the reference mode to upload images or supply their URLs. Reference images guide a new generation; they do not imply mask editing support.

How do I retrieve results and past requests?

Save the returned task ID and query the task until it succeeds or fails. The History tab lets you reopen your tasks and reuse their parameters.

What happens if the model is closed?

The model keeps its page and identity, but new generation requests are blocked. Existing task records remain accessible. An upstream outage is reported separately from an administrator closing the model.

Read the API documentation ↗

Discover more AI tools

Browse all models ↗

AI image generator

Create from a prompt and reference images.

Choose a model ↗

AI video generator

Explore text, references and frame inputs.

Choose a model ↗

AI chat API

Integrate conversations, instructions and streaming.

Choose a model ↗

API documentation

Browse endpoints, request examples and integration steps.

Read documentation ↗

Integration topics / Documentation

All documentation ↗
IMAGEHello, API.

Docs: Choose image specifications and references

Check resolution, aspect ratio, format and reference constraints.

View docs section ↗
BUDGET/v1/tasks

Docs: Batch tasks and budgets

Estimate using the actual specification and billing unit; reconcile task charges.

View docs section ↗
WORKFLOW{ your next idea }

Docs: Image and video task learning path

Understand asynchronous states, result URLs and safe recovery.

View docs section ↗