Google

Nano Banana Pro

nano-banana-pro

A quality-first image generation and editing model built on the Gemini 3 Pro reasoning backbone, stronger at multi-image character consistency and text rendering, supporting native 2K output with intelligent upscaling to 4K

nano-banana-pro

Try nano-banana-pro

Input

Showcases

View all showcases

Output

image

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

Pricing

nano-banana-pro per image

Specifications	Unit Price
1K	$0.057
2K	$0.057
4K	$0.100

Overview

nano-banana-pro is an image generation and editing model from Google that supports both text-to-image and image-to-image workflows. It targets quality-first creative tasks, performing more reliably on composition, multi-image character consistency, and text rendering, and supports 1K to 4K output with a range of aspect ratios. It suits designers, e-commerce and brand content teams that need series-based visual output, and developers integrating image generation into product workflows.

Key Highlights

Up to 4K resolution output — output resolution can be selected among 1K, 2K, and 4K, covering the full workflow from quick previews to high-definition final images.
Up to 8 reference images — in image-to-image mode, multiple reference images can be supplied to maintain character and style consistency across images, suitable for series production.
More controllable composition and text rendering — reasoning-based parsing of prompt semantics and spatial relationships makes the model more usable for layout-heavy tasks such as posters and covers containing text.
Adjustable aspect ratio and format parameters — supports 11 aspect ratios and two output formats, png and jpg, making it easy to match the asset specs of different channels directly.

Capabilities

Text-to-image and image-to-image in one: The same model can generate new images from text prompts and edit or transform input images per prompt, reducing the cost of switching between multiple models.

Multi-reference consistency: Up to 8 reference images can be supplied, letting the model maintain characters and visual style across a series of images, suitable for content projects requiring a complete set of outputs.

Resolution and aspect ratio control: Output can be 1K, 2K, or 4K, with 11 ratios from 1:1 to 21:9 plus auto selection, producing assets that directly match placement specs.

Semantic and compositional reasoning: Object relationships and spatial layout in the prompt are parsed before generation, giving more stable composition under complex descriptions and reducing repeated retries.

Use Cases

Brand and social media content teams: campaign copy — produce batches of series posters and social media images in a consistent style, using multi-reference consistency to keep characters and visual language from drifting.
E-commerce and advertising design: product images and creative briefs — use image-to-image to replace scenes and styles while preserving the product subject, producing images ready for detail pages and ad placements.
Game and film pre-production: character design and storyboards — lock character traits with multiple reference images and generate concept art and storyboards that stay consistent across shots for internal review and iteration.
Publishing and graphic design: cover and poster typography — rely on text rendering and composition control to generate draft covers and posters with title text, reducing later rework.

Limitations and Selection Advice

This model is positioned as quality-first, and its generation process involves heavy reasoning, so it is slower than lightweight models focused on throughput and is not suited to scenarios requiring millisecond-level response or large-volume rapid trial and error. Character consistency and text rendering depend on prompts and the specific image, and are not absolutely guaranteed; for complex layouts, validate with a small batch first. It handles only image generation and editing, not general conversation or text tasks. If the primary goal is low-cost, high-frequency iteration, consider a lighter model in the same family.

Frequently asked questions

View all FAQs →

What is Nano Banana Pro best for?

Generate high-detail commercial images or remix optional references with broad ratios and up to 4K output.
Does Nano Banana Pro accept reference images?

Yes, up to 8 optional references. Omit them for text-only generation.
Which output settings are supported?

The page exposes 1K, 2K, 4K and auto, 1:1, 16:9, 9:16, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9; use the Playground contract for the final available set.
How is Nano Banana Pro 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-pro

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for nano-banana-pro and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 20000

A text prompt describing the image content to generate or edit, as a string, with a maximum length of 20,000 characters.

resolutionstringOptionalDefault: "1K"

Controls the resolution of the output image, as a string, defaulting to 1K.

Options:1K2K4K

image_inputarrayOptionalmaxItems 8

An optional array of reference image URLs, each element being an image link, up to 8 images, supporting image/jpeg, image/png, and image/webp formats, with a maximum file size of 30MB per image.

Array [ string ]

aspect_ratiostringOptionalDefault: "auto"

Controls the aspect ratio of the output image, as a string, defaulting to auto.

Options:auto1:116:99:163:44:33:22:3

Show all (3)

5:44:521:9

output_formatstringOptionalDefault: "png"

Controls the format of the output image, as a string, defaulting to png.

Options:pngjpg

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-pro",
  "input": {
    "prompt": "…",
    "resolution": "1K",
    "aspect_ratio": "auto",
    "output_format": "png"
  }
}'

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-pro",
    input: {
      "prompt": "…",
      "resolution": "1K",
      "aspect_ratio": "auto",
      "output_format": "png"
    }
  }),
});
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-pro",
        "input": {
          "prompt": "…",
          "resolution": "1K",
          "aspect_ratio": "auto",
          "output_format": "png"
        }
    },
)
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"
    }
  }
}