Nano Banana 2 API

About the Nano Banana 2 API

What Nano Banana 2 does, how it fits in the Google model lineup, and why teams reach for it.

All Nano Banana 2 API endpoints

4 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.

Text To Image Fast (Fast)

Google Nano Banana 2 Fast (Gemini 3.1 Flash Image) is the cheapest Nano Banana 2 option, starting at just $0.045 per image. Delivers fast text-to-image generation with 2K default output and 4K support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-imagefrom $0.045

Text To Image

Google Nano Banana 2 (Gemini 3.1 Flash Image) delivers Pro-quality image generation at Flash speed with 512px to 4K resolution support. Features include improved text rendering, character consistency for up to 5 characters, and real-world knowledge integration. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-imagefrom $0.070

Edit Fast (Fast)

Google Nano Banana 2 Edit Fast (Gemini 3.1 Flash Image) is the cheapest Nano Banana 2 editing option, starting at just $0.045 per image. Enables fast image editing with 2K default output and 4K support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-imagefrom $0.045

Edit

Google Nano Banana 2 Edit (Gemini 3.1 Flash Image) enables advanced image editing with 4K-capable output, fast iteration, and precise instruction following. Supports text translation, localization within images, and maintains subject consistency during edits. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-imagefrom $0.070

See Nano Banana 2 in action

Real outputs generated by the Nano Banana 2 API. Hover any video to preview, click to open the full-size viewer.

A young woman with short red hair and round glasses wearing a dark green trench coat, standing in a rainy Tokyo street at night. Neon signs reflected in puddles. Cinematic still, anamorphic lens look.

an epic sci-fi movie poster, a lone astronaut standing on a vast desert planet, a gigantic ringed planet rising in the sky, dramatic sunset lighting, blowing sand, cinematic composition, IMAX scale, photorealistic, space for title at the top, film poster design, ultra detailed

"resolution": "8K ultra high definition", "style": "hyper - realistic food illustration with editorial infographic overlays", "lighting": "soft directional key light, subtle rimlight' "scene_description": "A vertical stack of cake slices floating above a plate against soft pink gradient background", "motion_elements": ["floating fruits", "floating macarons", "crumbs suspended in air"], "text_design": { "ingredient_name_color": "metallic gold", "indicator_lines": "long, thin, smooth golden lines with rounded corners"

a man standing in the middle of a busy city street while everything around him is frozen in time, suspended rain drops and floating papers, dramatic cinematic lighting, epic composition, hyper realistic, movie still, 8k

a quiet train platform at sunset, golden sunlight streaming through the station roof, a traveler holding a suitcase waiting alone, cinematic composition, film still, warm color grading, 35mm lens

Change to animation style.

Remove people

Replace the man with a handsome blonde man.

How to use the Nano Banana 2 API

Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.

1. 1

   Get an API key

   Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.

2. 2

   Submit a prediction

   POST your input as JSON to https://api.wavespeed.ai/api/v3/google/nano-banana-2/text-to-image. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.

3. 3

   Poll for completion

   GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from "queued" or "processing" to "completed".

4. 4

   Read the output URL

   Once status is "completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Nano Banana 2 variant you called.

What you can build with Nano Banana 2

Common workflows developers and creators use the Nano Banana 2 API for.

Tips for prompting Nano Banana 2

Practical advice for getting better outputs from Nano Banana 2 — drawn from the patterns that work across image models in production pipelines.

Nano Banana 2 API pricing

Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).

Call the Nano Banana 2 API

Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.

# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/google/nano-banana-2/text-to-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{}'

# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# Read the output URL from data.outputs[0].

// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY

const result = await client.run("google/nano-banana-2/text-to-image", {});
console.log(result.outputs[0]); // → URL of the generated output

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "google/nano-banana-2/text-to-image",
    {}
)
print(output["outputs"][0])  # → URL of the generated output

Nano Banana 2 vs alternatives

When to pick Nano Banana 2 over similar models on WaveSpeedAI.

Nano Banana 2 API — Frequently asked questions

Pricing, license, integration — common questions about running Nano Banana 2 on WaveSpeedAI.

About Google

The team behind Nano Banana 2 and the broader Google model lineup on WaveSpeedAI.

Google's AI work happens primarily at Google DeepMind and Google Research. Its image and video models — Imagen, Veo, and Gemini-family multimodal models like Nano Banana (Gemini 3 Image) — share architecture and training infrastructure with the broader Gemini lineup. Outputs are noted for accurate text rendering, broad style coverage, and commercial-grade licensing.

Related model APIs on WaveSpeedAI

Other AI APIs from Google and the rest of the image model lineup — one API key, one billing account.