Google

Nano Banana 2 Lite

Nano-Banana-2-Lite

A lightweight, efficiency-focused model in the Google image family, built for low latency and low cost, suited to rapid ideation and high-throughput image generation, and a seamless replacement for the first-generation Nano Banana

Nano-Banana-2-Lite

Try Nano-Banana-2-Lite

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

Nano-Banana-2-Lite per image

Unit Price	$0.033

Positioning Overview

Nano-Banana-2-Lite is an efficiency-oriented lightweight model in Google's image generation series, supporting both text-to-image generation and image editing based on reference images. It prioritizes response speed and invocation cost, making it suitable for developers who need batch image generation and rapid iteration of first drafts; it maintains usable performance in instruction following and character consistency, and can handle multi-size output from concept sketches to marketing images, with fine-tuning as needed.

Key Highlights

Unified interface for text-to-image and image editing — The same pipeline can both generate images directly from prompts and accept up to 10 reference images for editing and remixing, reducing workflow switching.
Efficiency positioning for high-frequency invocation — Within the series, it prioritizes speed and cost, making it suitable for throughput-sensitive tasks such as batch assets and template-based image generation.
Output coverage across 14 aspect ratios — From 1:1, 16:9 to extreme ratios such as 1:8 and 8:1, all can be specified directly, generating in one pass for multiple platform placements.
Support for multi-round local iteration — Existing results can be repeatedly modified in local areas, rapidly advancing first drafts to a usable state.

Capability Description

Text-to-image and reference image editing: Passing only a prompt performs text-to-image generation; attaching 1 to 10 reference image URLs switches to editing or remixing. The same interface covers both types of needs, facilitating unified encapsulation in a single pipeline.

Aspect ratio controllable output: aspect_ratio provides 14 values and supports auto automatic selection. Developers can directly lock the ratio according to placement positions, eliminating subsequent cropping and secondary adaptation.

Long prompt input: prompts can be up to 20,000 characters, accommodating fairly complete descriptions of subject, composition, and style, suitable for batch construction of generation requests through template concatenation.

Multi-reference image input: Up to 10 JPEG, PNG, WebP reference images (each no larger than 30MB), usable for editing tasks requiring multi-image context such as style transfer and asset mixing.

Applicable Scenarios

Creative teams generating batch concept sketches — Batch generate proposal sketches with short prompts as materials for internal review and direction screening, deciding on refinement investment after seeing the direction.
Developers building high-throughput image generation pipelines — Batch generate product or content images using templated prompts, directly stored for on-demand invocation by business systems.
Marketing and social media multi-placement images — Specify ratios such as 1:1, 9:16, 16:9 for placement positions, generating finished images in multiple sizes at once, reducing post-processing cropping rework.
Multi-round local modification of existing images — Upload reference images and describe changes with prompts, adjusting local details round by round to produce deliverable iterative versions.
Cross-image character-consistent series content — Use the same reference image to maintain character and visual identity, batch producing complete sets of illustrations or storyboards with a consistent series look.

Limitations and Selection Advice

As an efficiency-first lightweight model, first drafts of long sentences or complex layout text rendering may require manual adjustment, with simple and clear text instructions being more reliable; for complex layouts and high-precision details, reserve a rework phase. Currently, specific specifications such as resolution limits, concurrency, and quotas are not available and need to be verified independently before integration. If the task requires higher image quality and complex instruction understanding than throughput, choose a higher-tier model in the same series; if it is only batch sketches and rapid iteration, this model is more suitable.

Frequently asked questions

View all FAQs →

What is Nano Banana 2 Lite best for?

A fixed-1K entry route for high-volume drafts, fast iteration, and optional multi-reference remixing.
Does Nano Banana 2 Lite accept reference images?

Yes, up to 10 optional references. Omit them for text-only generation.
Which output settings are supported?

The page exposes 1K and auto, 1:1, 16:9, 9:16, 4:3, 3:4, 8:1, 1:8; use the Playground contract for the final available set.
How is Nano Banana 2 Lite billed?

Billing is per successful generated image. Resolution or quality differences, when present, are reflected by the live page price.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: Nano-Banana-2-Lite

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for Nano-Banana-2-Lite and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 20000

Text prompt for image generation, in string form, maximum 20000 characters, used to describe the image content to be generated or edited.

image_urlsarrayOptionalminItems 1maxItems 10

Optional array of reference image URLs, with elements being image address strings, used for image editing or mixed image generation; up to 10 images, each supporting JPEG/PNG/WebP and no larger than 30MB; if not provided, it falls back to pure text-to-image generation.

Array [ string ]

aspect_ratiostringRequiredDefault: "auto"

The aspect ratio of the output image, in string form; the default auto lets the model choose on its own.

Options:auto1:12:33:23:44:34:55:4

Show all (7)

9:1616:921:91:44:11:88:1

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "Nano-Banana-2-Lite",
  "input": {
    "prompt": "…",
    "aspect_ratio": "auto"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "Nano-Banana-2-Lite",
    input: {
      "prompt": "…",
      "aspect_ratio": "auto"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "Nano-Banana-2-Lite",
        "input": {
          "prompt": "…",
          "aspect_ratio": "auto"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}