nano-banana-2-1Nano Banana 2.1 is Google's high-efficiency image model for generation and editing. Google positions it as an upgrade in visual quality, prompt adherence, character consistency, text rendering and multi-reference support, with output up to 4K. On apimodels.app it is the model id nano-banana-2-1 on the unified image endpoint, callable with one API key. Text-to-image and editing share that one model: send only a prompt (up to 20,000 characters) to generate, or attach reference images — image for one, image_urls for up to 10 (URL or base64; JPEG, PNG or WebP) — and describe the change or the combination you want. Fifteen aspect ratios are accepted: auto (the default), 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus 1:4, 4:1, 1:8 and 8:1 for banners and tall strips. resolution picks the tier and the price: $0.024 at 1K (the default), $0.04 at 2K and $0.064 at 4K per image. Reference images cost nothing extra and failed calls are never charged. That is a lower per-image price than Nano Banana 2 at every tier here — gemini-3.1-flash-image is $0.06 at 1K/2K and $0.10 at 4K, nanobanana2 is $0.05 and $0.08. In our first test on 2026-10-07, a 16:9 request at 1K came back in about 20 seconds at 1376×768, with the sign text "NANO BANANA 2.1" spelled correctly. Calls are asynchronous: create a task, then poll it or pass a callback_url.
Generated image will appear here
Enter a prompt and click Generate
Priced per image by resolution, 1K by default; reference images cost nothing extra and failed calls are not charged
Send a prompt alone for text-to-image, or add image or image_urls (up to 10 references) to edit or combine
auto, 1:1 through 21:9, plus 1:4, 4:1, 1:8 and 8:1 for banners and tall strips
Google lists text rendering among the 2.1 upgrades; in our first test the sign "NANO BANANA 2.1" came out spelled correctly
Create a task, then poll it or receive a callback_url webhook; a 16:9 image at 1K took about 20 seconds in testing
Nano Banana 2.1 is a Image Generation API provided by Google. Nano Banana 2.1 is Google's high-efficiency image model for generation and editing. Google positions it as an upgrade in visual quality, prompt adherence, character consistency, text rendering and multi-reference support, with output up to 4K. On apimodels.app it is the model id nano-banana-2-1 on the unified image endpoint, callable with one API key. Text-to-image and editing share that one model: send only a prompt (up to 20,000 characters) to generate, or attach reference images — image for one, image_urls for up to 10 (URL or base64; JPEG, PNG or WebP) — and describe the change or the combination you want. Fifteen aspect ratios are accepted: auto (the default), 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus 1:4, 4:1, 1:8 and 8:1 for banners and tall strips. resolution picks the tier and the price: $0.024 at 1K (the default), $0.04 at 2K and $0.064 at 4K per image. Reference images cost nothing extra and failed calls are never charged. That is a lower per-image price than Nano Banana 2 at every tier here — gemini-3.1-flash-image is $0.06 at 1K/2K and $0.10 at 4K, nanobanana2 is $0.05 and $0.08. In our first test on 2026-10-07, a 16:9 request at 1K came back in about 20 seconds at 1376×768, with the sign text "NANO BANANA 2.1" spelled correctly. Calls are asynchronous: create a task, then poll it or pass a callback_url. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: 1K: $0.024, 2K: $0.04, 4K: $0.064.
Related model: gemini-3.1-flash-image — Nano Banana 2 (Gemini 3.1 Flash Image, GA) — adds a 512 tier at $0.04; $0.06 at 1K/2K, $0.10 at 4K
Related model: gpt-image-2 — OpenAI's image model — up to 16 reference images per edit, 1K $0.025, 2K $0.03, 4K $0.05
Related model: nanobananapro — Nano Banana Pro (Gemini 3 Pro Image) — the highest fidelity and text-rendering ceiling, $0.068 at 1K/2K, $0.13 at 4K
Generate high-quality product visuals for online stores, ads, and marketing materials.
Create eye-catching visual content for social platforms to boost engagement and brand visibility.
Produce concept art for characters, scenes, and props to accelerate game development.
Design posters, banners, and promotional graphics at a fraction of traditional design costs.
Nano Banana 2.1 is available through APIMODELS at: 1K: $0.024, 2K: $0.04, 4K: $0.064. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same Nano Banana 2.1 model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
Per image, set by the resolution field alone: $0.024 at 1K, $0.04 at 2K and $0.064 at 4K. Leave resolution out and you get 1K. Up to 10 reference images ride along at no extra charge, and neither the aspect ratio nor the prompt length moves the price. A failed request costs nothing, so 100 images at 1K come to $2.40 and the same 100 at 4K to $6.40.
Both go to POST /v1/images/generations with model set to nano-banana-2-1. A prompt on its own (up to 20,000 characters) generates from scratch. Add image for one reference or image_urls for an array — up to 10 in total, each a URL, data URI or base64 — and the same call becomes an edit or a multi-image composition. The call returns a taskId at once; poll GET /v1/images/generations?task_id=… until state is completed and read resultUrls, or pass a callback_url to be notified.
On price, Nano Banana 2.1 comes in lower at every tier here: $0.024 / $0.04 / $0.064, against $0.06 at 1K/2K and $0.10 at 4K for gemini-3.1-flash-image (Nano Banana 2, GA) and $0.05 and $0.08 for the nanobanana2 preview channel. Nano Banana Pro (nanobananapro, Gemini 3 Pro Image, $0.068 at 1K/2K and $0.13 at 4K) is the ceiling for fidelity and dense text — pick it when the finished image matters more than the unit price. All of them share the endpoint and the parameters, so comparing them on your own prompts is a one-string change to model.
Fifteen ratios: auto (the default), 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9, plus 1:4, 4:1, 1:8 and 8:1 for banners, skyscraper ads and tall strips. Anything else is rejected with a 400 rather than quietly replaced. Reference images go up to 10 per request (image and image_urls counted together), in JPEG, PNG or WebP; an eleventh returns a 400 instead of being dropped.
Yes — resolution accepts 4K as its top tier, billed at $0.064, alongside 1K and 2K; the exact pixel size follows the aspect ratio you pick. For a measured reference point: our first test on 2026-10-07, 16:9 at 1K, finished in about 20 seconds and came back at 1376×768 with the sign text "NANO BANANA 2.1" spelled correctly. Generation is asynchronous, so give your polling loop a few minutes of headroom rather than a short HTTP timeout, and copy results to your own storage — result files are deleted after 30 days.
On APIMODELS, Nano Banana 2.1 runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Text to Image, Image Editing, Up to 10 References, 15 Aspect Ratios, 1K/2K/4K, $0.024–$0.064/image, and you can weigh it on price and capability against other Image Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Image Generation option with live pricing at apimodels.app/models.
Nano Banana 2.1 supports: Text to Image, Image Editing, Up to 10 References, 15 Aspect Ratios, 1K/2K/4K, $0.024–$0.064/image. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes Nano Banana 2.1 through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.
Prompts shared by their authors — copy and adapt them. Each one credits its author and links back to the original post.
Weathered sailor on a fishing boat
Create a photorealistic candid photograph of an elderly sailor standing on a small fishing boat. He has weathered skin with visible wrinkles, pores, and sun texture, and a few faded traditional sailor tattoos on his arms. He is calmly adjusting a net while his dog sits nearby on the deck. Shot like a 35mm film photograph, medium close-up at eye level, using a 50mm lens. Soft coastal daylight, shallow depth of field, subtle film grain, natural color balance. The image should feel honest and unposed, with real skin texture, worn materials, and everyday detail. No glamorization, no heavy retouching.
by OpenAI
Automatic coffee machine workflow infographic
Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura. From bean basket, to grinding, to scale, water tank, boiler, etc. I'd like to understand technically and visually the flow.
by OpenAI
Thread streetwear ad with exact typography
Give me a cool in culture ad / fashion shot for a brand called Thread. It's a hip young street brand. The ad shows a group of friends hanging out together with the tagline "Yours to Create." Make it feel like a polished campaign image for a youth streetwear audience: stylish, contemporary, energetic, and tasteful. Use clean composition, strong color direction, natural poses, and premium fashion photography cues. Render the tagline exactly once, clearly and legibly, integrated into the ad layout. No extra text, no watermarks, no unrelated logos.
by OpenAI
We curate copy-ready prompt libraries — every entry shows its full text and a sample result, ready to adapt.