Nano Banana 2.1 API
Google Nano Banana 2.1 — the latest Nano Banana image generation and editing model. Google reports gains over its previous models across the board, with notable improvements in visual design and subject consistency, plus tighter prompt adherence and cleaner text rendering.
Two endpoints: google/nano-banana-2.1/text-to-image and google/nano-banana-2.1/edit with up to 14 reference images. Fourteen aspect ratios including 1:4, 4:1, 1:8 and 8:1, 1K / 2K / 4K output, optional web and image search, and PNG or JPEG output — the same request shape as Nano Banana 2.
/filters:quality(82)/examples/48cc1e621e734eeba0ddda5004aa805d/b94abaf6-4369-4f65-bf93-e4da93382a36-96022c930e6b.webp)
Overview
About the Nano Banana 2.1 API
What Nano Banana 2.1 does, how it fits in the Google model lineup, and why teams reach for it.
Nano Banana 2.1 is a image generation and editing model from Google, available through the WaveSpeedAI REST API. Google Nano Banana 2.1 — the latest Nano Banana image generation and editing model. Google reports gains over its previous models across the board, with notable improvements in visual design and subject consistency, plus tighter prompt adherence and cleaner text rendering.
Two endpoints: google/nano-banana-2.1/text-to-image and google/nano-banana-2.1/edit with up to 14 reference images. Fourteen aspect ratios including 1:4, 4:1, 1:8 and 8:1, 1K / 2K / 4K output, optional web and image search, and PNG or JPEG output — the same request shape as Nano Banana 2.
The Nano Banana 2.1 family on WaveSpeedAI ships 2 REST endpoints covering Image-To-Image, Text-To-Image workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Nano Banana 2.1 through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
Specs
Nano Banana 2.1 API capabilities and release status
The model-specific details developers search for before choosing an API: availability, expected output length, reference support, and the current live fallback.
Endpoints
2 variants
Text-to-image and edit; edit takes up to 14 reference images.
Resolution
1K / 2K / 4K
Three output tiers; 1K is the default.
Aspect ratios
14
1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1.
Output
PNG / JPEG
Selectable per request; optional web and image search grounding.
Endpoints
All Nano Banana 2.1 API endpoints
2 Nano Banana 2.1 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.
/filters:quality(82)/media/images/1791312805430502065_dlG47iBV.webp)
Nano Banana 2.1 Edit
Google Nano Banana 2.1 Edit is the latest Nano Banana image editing model, with gains in visual design, subject consistency and prompt adherence, up to 14 reference images and 1K to 4K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1791312803887061677_SluDNW5I.webp)
Nano Banana 2.1 Text To Image
Google Nano Banana 2.1 is the latest Nano Banana image generation model, with gains in visual design, subject consistency and prompt adherence, cleaner text rendering, 1K to 4K output and optional web search. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Examples
See Nano Banana 2.1 in action
Real outputs generated by the Nano Banana 2.1 API. Hover any video to preview, click to open the full-size viewer.
How to
How to use the Nano Banana 2.1 API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 01
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.
- 02
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 03
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result. Return outputs on completed; stop with an error on failed, cancelled, timeout, or deleted; continue polling for every other status.
- 04
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 2.1 variant you called.
Use cases
What you can build with Nano Banana 2.1
Common workflows developers and creators use the Nano Banana 2.1 API for.
Design-heavy visuals
Google calls out visual design as one of the biggest gains in 2.1. Use it for posters, social graphics, packaging mockups, and layouts where composition and typography matter as much as the subject.
Consistent subjects across edits
Subject consistency is the other headline improvement. google/nano-banana-2.1/edit keeps people, products, and characters recognizable while you change the scene, outfit, or style — with up to 14 reference images per call.
Complex, multi-part prompts
Tighter prompt adherence means long instructions with several subjects, positions, and style constraints are followed more faithfully. Spell out every requirement instead of relying on follow-up edits.
Clean in-image text
Labels, signs, and headlines render sharper than before. Put the exact copy in quotes and say where it goes for menus, banners, and product labels.
Grounded in current information
Set enable_web_search to let the model look up current real-world information — recent products, places, or events — and enable_image_search to let it check what real things look like before generating.
Extreme aspect ratios up to 4K
Fourteen aspect ratios including 1:4, 4:1, 1:8 and 8:1 cover tall banners, wide headers, and skyscraper ads, at 1K, 2K, or 4K output.
Tips
Tips for prompting Nano Banana 2.1
Practical advice for getting better outputs from Nano Banana 2.1 — drawn from the patterns that work across image models in production pipelines.
- 01
Spell out the whole brief
2.1 follows long, multi-part prompts more closely. Describe subject, composition, lighting, style, and any text in one prompt rather than fixing details in later edits.
- 02
Quote the exact text
For signs, labels, and headlines, write the literal copy in quotes and say where it should appear ("title across the top", "price tag bottom right").
- 03
State what to keep when editing
With google/nano-banana-2.1/edit, describe the change and then what must stay the same — "swap the background for a beach at dusk, keep the person, pose, and lighting".
- 04
Refer to references by position
When sending several reference images, put the main subject first and refer to the others by order ("the jacket from image 2").
- 05
Draft at 1K, deliver at 2K or 4K
Iterate at 1K, then re-run the chosen prompt at the delivery resolution. Turn on web or image search only when the prompt depends on current real-world information or on how real things look.
Pricing
Nano Banana 2.1 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).
| Endpoint | Type | Starting price |
|---|---|---|
| google/ | image-to-image | $0.05 |
| google/ | text-to-image | $0.05 |
API
Call the Nano Banana 2.1 API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
POSThttps://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"enable_web_search": false,
"enable_image_search": false,
"output_format": "png"
}')
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"enable_web_search": false,
"enable_image_search": false,
"output_format": "png"
}),
});
const task = body.data ?? body;
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"enable_web_search": False,
"enable_image_search": False,
"output_format": "png"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image", json.dumps(payload).encode())
task = body.get("data", body)
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Compare
Nano Banana 2.1 vs alternatives
When to pick Nano Banana 2.1 over similar models on WaveSpeedAI.
Nano Banana 2.1 vs Nano Banana 2
Nearly the same parameters, so switching is a model-ID change. 2.1 is Google's newer model with better visual design, subject consistency, and prompt adherence; Nano Banana 2 additionally offers a 0.5K tier and the Fast variants.
Nano Banana 2.1 vs Nano Banana Pro
Nano Banana Pro remains the premium tier with Ultra and Multi variants. Nano Banana 2.1 brings Google's latest improvements to the faster, lower-cost Flash line.
Nano Banana 2.1 vs GPT Image 2.5
GPT Image 2.5 offers five quality levels and two tiers. Nano Banana 2.1 answers with web-search grounding, up to 14 reference images, and extreme aspect ratios down to 1:8.
FAQ
Nano Banana 2.1 API — Frequently asked questions
Pricing, license, integration — common questions about running Nano Banana 2.1 on WaveSpeedAI.
What is the Nano Banana 2.1 API?
Nano Banana 2.1 is a Google image generation model exposed as a REST API on WaveSpeedAI. Google Nano Banana 2.1 — the latest Nano Banana image generation and editing model. Google reports gains over its previous models across the board, with notable improvements in visual design and subject consistency, plus tighter prompt adherence and cleaner text rendering. You can call it programmatically or try it from the playground linked above.
How do I call the Nano Banana 2.1 API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image with your input as JSON. The endpoint returns a prediction id. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. Production-oriented Python / Node.js / cURL examples are above.
How much does the Nano Banana 2.1 API cost?
Nano Banana 2.1 starts at $0.05 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Nano Banana 2.1 variants are available?
WaveSpeedAI hosts 2 live Nano Banana 2.1 endpoints: google/nano-banana-2.1/edit, google/nano-banana-2.1/text-to-image. Each variant has its own playground page and pricing.
Can I use Nano Banana 2.1 outputs commercially?
Commercial usage rights follow the Google model license. Most Google models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Nano Banana 2.1 on WaveSpeedAI instead of going direct?
One API key + one billing account across Nano Banana 2.1 AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below Google's direct API.
Provider
About Google
The team behind Nano Banana 2.1 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.
Start building with Nano Banana 2.1 on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from Google and every other provider.
/filters:quality(82)/examples/c8d18eb9a94844e7ad929e6f2329e1c9/1aeb9d76-f6ad-467f-afa6-ad09693e5911-65bcec8e8edd.webp)
/filters:quality(82)/examples/2652743d9a2d40df8488300aa282872a/b3569273-299c-4046-b247-04f2735ee0b7-9f888ceafb9b.webp)
/filters:quality(82)/examples/28b41000bf134255a3840b68bac9d5e9/1a29ca9c-d88d-493f-a386-f0a0ba3fa37b-2a450c14afd4.webp)
/filters:quality(82)/examples/99da63b333b1471187f3edf2a74c16fe/5bc79c97-2253-49e3-a0c0-a49679986dcf-1ea4d9e65faf.webp)