Resolution
1K · 2K · 4K
Three output tiers, billed per image.
Nano Banana 2.1 is Google''s latest high-efficiency image generation and conversational editing model, built on Gemini 3.6 Flash as an update to Nano Banana 2. It keeps Flash-level speed while improving visual quality, prompt adherence, text rendering, mask-based editing and multi-turn character consistency at 1K, 2K and 4K, blending up to 14 reference images.
New · Nano Banana 2.1
The next generation of Nano Banana 2 — sharper, more faithful, still Flash-fast.
Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest image model, built on Gemini 3.6 Flash. It brings better visual design, mask-based editing, stronger subject consistency and more natural-looking images — and plugs into the exact same APIPod image API you already use for Nano Banana 2. Just change the model ID.
Resolution
1K · 2K · 4K
Three output tiers, billed per image.
Reference Images
Up to 14
Blend products, styles and characters in one request.
Consistency
4 chars · 10 objects
Up to 4 consistent characters and 10 high-fidelity objects.
Starting Price
$0.02
Per 1K image on APIPod — half the price of Nano Banana 2.
Official Nano Banana 2.1 sample image from Google DeepMind.
2.1 is the new default for everyday production. Keep the rest of the family for the jobs it is built for.
Same API contract on APIPod — what changes is the model behind it.
| Spec | Nano Banana 2.1 | Nano Banana 2 |
|---|---|---|
| Upstream Model | gemini-nano-banana-2.1 | Gemini 3.1 Flash Image |
| Resolution | 1K · 2K · 4K | 512px · 1K · 2K · 4K |
| Aspect Ratios | 10 standard (banner ratios coming) | 10 standard + 4 banner |
| Reference Images | Up to 14 | Up to 14 |
| Subject Consistency | 4 characters · 10 objects, across edit turns | 5 characters · 14 objects |
| Visual Design & Text | Improved layout and text rendering | Legible text + localization |
| Speed | Flash tier | Flash tier |
| Price / Image | $0.02 (1K) · $0.04 (2K) · $0.05 (4K) | $0.04 (512px/1K) · $0.06 (2K) · $0.08 (4K) |
Capability notes follow Google's Nano Banana 2.1 model card and API docs; results vary by prompt. Google notes small text at 1K and long paragraphs can still be imperfect — use 2K or 4K for text-heavy layouts. Google lists 1:4–8:1 panorama ratios for 2.1; they will open on APIPod once our upstream supports them.
APIPod Pricing
Pay per generated image by resolution tier. No subscription, no minimum spend.
| Resolution | Price / Image |
|---|---|
| 1K | $0.02 |
| 2K | $0.04 |
| 4K | $0.05 |
Prices are in USD and may change; the console shows the live price before you submit. Generation and editing are billed the same.
One model ID covers text-to-image and image editing.
Photorealistic scenes, portraits and products at up to 4K, with improved lighting and detail.
Sketch a mask over a source image and describe the change — the object keeps its size and position while the scene around it changes.
Blend up to 14 reference images while keeping up to 4 characters and 10 objects consistent.
Cleaner typography and layouts for posters, infographics, packaging and website mockups.
Official Samples
Sample images and their original prompts from Google DeepMind's Nano Banana 2.1 launch. Copy a prompt and send it to the same image endpoint.
Natural light, lens character and fine textures in a misty Highland scene.
Prompt
A cinematic landscape portrait still, captured with a 50mm f/1.8 prime lens, depicting an adult Scottish crofter in a tweed cap and waxed jacket scratching the woolly forelock of a majestic red-haired Highland cow in a misty mountain pasture in the Isle of Skye. Deep green peat bogs and craggy basalt pinnacles of the Storr rise dramatically in the soft overcast morning daylight.
A bold yellow, pink and green palette with precise composition.
Prompt
A 16:9 horizontal cinematic still, shot from street level looking up at the sharp diagonal steel exterior staircase of a two-story retro motel painted vibrant mustard-yellow against a flamingo-pink stucco facade. An adult woman in an emerald-green mini dress descends the staircase, her hand trailing along the yellow railing. The bright yellow, pink, and green color clash creates a delightful, sun-drenched cinematic mood.
The masked object keeps its size and position while the environment is replaced.
Prompt
mask the object inside the sketch and place in a completely different environment but don't change the size and position of the object itself, create 5 of these each 16:9, each it's own server call, one at a time
Several reference portraits fused into one consistent editorial composition.
Prompt
i want a high-end editorial fashion shot with all these models posing together in abstract colorful set, dramatic composition, some models are far and some are close. choose a theme
Images and prompts: Google DeepMind, "Introducing Nano Banana 2.1". Reference-image inputs for the editing samples are not included.
Quickstart
Submit a task, poll the status, pick up the image URL. Already on Nano Banana 2? Only the model ID changes.
Full parameter reference (quality / aspect_ratio / image_urls) lives in the Nano Banana 2.1 docs.
import os, time, requests
headers = {"Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}"}
payload = {
"model": "nano-banana-2.1",
"prompt": "A minimalist product shot of a ceramic coffee cup on travertine, soft morning light",
"quality": "2K", # 1K / 2K / 4K
"aspect_ratio": "4:5", # 10 standard ratios
# "image_urls": ["https://..."] # up to 14 references for editing
}
resp = requests.post("https://api.apipod.ai/v1/images/generations", json=payload, headers=headers)
task_id = resp.json()["data"]["task_id"]
while True:
data = requests.get(f"https://api.apipod.ai/v1/images/status/{task_id}", headers=headers).json()["data"]
if data["status"] in ("completed", "failed"):
print(data.get("result"))
break
time.sleep(2)Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest high-efficiency image generation and editing model, released on October 6, 2026 as an update to Nano Banana 2 and built on Gemini 3.6 Flash. It improves visual quality, prompt adherence, text rendering and character consistency across editing turns. On APIPod its model ID is nano-banana-2.1.
2.1 is built on Gemini 3.6 Flash and produces more natural images, better visual design and text layout, mask-based editing and stronger multi-reference consistency. On APIPod, Nano Banana 2 still offers the 512px tier and banner aspect ratios (1:4, 4:1, 1:8, 8:1), which are not yet available for 2.1. Both use the same request format, and 2.1 is cheaper at every resolution.
Nano Banana 2.1 outputs 1K (default), 2K or 4K images — the 512px tier of Nano Banana 2 is not available. On APIPod it currently supports 10 standard aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9.
Up to 14 reference images per request via image_urls. Google reports consistent depiction of up to four characters and up to ten objects.
$0.02 per 1K image, $0.04 per 2K image and $0.05 per 4K image, billed per generated image. Text-to-image and editing cost the same.
Send a POST request to /v1/images/generations with model set to nano-banana-2.1, then poll /v1/images/status/{task_id} until the task completes. You can also configure a webhook to receive the result.
Create an API key and switch your model ID — your existing Nano Banana 2 integration works as-is, at a lower price per image.