Nano Banana Pro
⧉Nano Banana Pro (Gemini 3 Pro Image) is a flagship image model with stronger detail and composition. Supports text-to-image and image-to-image, excels at typography and complex scenes, and suits commercial covers and high-quality illustration, through the OpenAI-compatible images API.
What is the Nano Banana Pro API and what does it cost?
Nano Banana Pro is Google's Gemini 3 Pro Image model (gemini-3-pro-image in Google's API) for text-to-image and image editing, with output up to 4096x4096 px. On KovAPI it costs $0.02 per image at 1K ($0.03 at 2K, $0.05 at 4K) (Google list price: $0.134 per 1K or 2K image and $0.24 per 4K image). Base URL: https://kovapi.com/v1 (OpenAI-compatible).
Measured performance
Real image jobs sent through the public KovAPI API. Test window 2026-10-27 18:17 – 2026-10-27 18:20 UTC; sample size 8.
How this was measured
/v1/images/generations at 1K, at most four in flight at once. Time is measured from submitting the job to the moment polling first sees status: "succeeded", so it includes any queueing; it is only as precise as the polling interval (3 s). With a sample this small, read the numbers as indicative.
Measurements are repeated every week and this page updates itself; the date above is the latest run.
Cost example
KovAPI figures use the live price on this page; vendor figures use the vendor's published list price (sources below).
1,000 images at 1K
1,000 images at 1K resolution.
| Where | Cost | Difference |
|---|---|---|
| KovAPI | $20.00 | — |
| Google Gemini API (1K/2K image) | $134.00 | KovAPI 85% cheaper |
1,000 images at 4K
1,000 images at 4K resolution.
| Where | Cost | Difference |
|---|---|---|
| KovAPI | $50.00 | — |
| Google Gemini API (4K image) | $240.00 | KovAPI 79% cheaper |
Google also bills input at $2 per 1M tokens (about $0.0011 per input image); KovAPI has no separate input charge.
Vendor list prices checked 2026-09-25: Gemini API pricing.
Parameters & capabilities
"Vendor spec" is what the model's maker publishes. "Via KovAPI" is what our own requests through the gateway showed (last checked 2026-10-27).
| Item | Vendor spec | Via KovAPI |
|---|---|---|
| Model id | gemini-3-pro-image Google: Gemini 3 Pro Image model page |
nano-banana-pro |
| Endpoints | — | POST /v1/images/generations and POST /v1/images/edits (OpenAI Images format); both return a job you poll at GET /v1/images/jobs/{id} |
| Price | $0.134 per 1K/2K image · $0.24 per 4K image Gemini API pricing | $0.02 at 1K · $0.03 at 2K · $0.05 at 4K, flat per image |
| Max output size | 4096x4096 px (4K) Gemini API pricing | resolution: "4K" (long side 4096 px) |
| Sizes | — | An aspect ratio (1:1, 3:4, 2:3, 9:16, 4:3, 3:2, 16:9) or pixels (WxH); resolution 1K / 2K / 4K sets the long side |
| Reference images | — | Up to 8 per request, 16 MB each: public URL, data: URI or base64 |
| Output | — | PNG at a stable img.kovapi.com URL; add response_format: "b64_json" to also receive base64 |
| Response mode | — | Asynchronous: HTTP 202 with a job id, then poll |
| Failed jobs | — | Refunded in full |
Tool setup
Base URL https://kovapi.com/v1, your KovAPI API key, and the model id nano-banana-pro. Request and response samples (cURL, Python, Node.js) are in the Nano Banana Pro API docs.
- Add an HTTP Request node: method
POST, URLhttps://kovapi.com/v1/images/generations, headerAuthorization: Bearer <your key>, JSON body withmodel=nano-banana-proand yourprompt. - Add a Wait node (3 seconds), then a second HTTP Request node:
GET https://kovapi.com/v1/images/jobs/{{ $json.id }}with the same header. - Add an IF node on
{{ $json.status }}:succeededcontinues with{{ $json.data[0].url }}; anything else loops back to the Wait node (stop onfailed).
Differences from the official API & known limits
- OpenAI Images format instead of Google's
generateContent: you sendmodel,prompt,sizeandresolutionto/v1/images/generations, and no Google SDK, API key or Cloud project is involved. - Job-based: submitting returns HTTP 202 and a job id; poll
GET /v1/images/jobs/{id}untilstatusissucceeded, then readdata[0].url. - Flat price per image by resolution; no separate charge for input tokens or reference images.
- Any aspect ratio is accepted; the result is centre-cropped and resized to exactly the size you asked for and saved as PNG.
- An edit request takes at most 8 reference images; any beyond 8 are dropped without an error.
- Image URLs are hosted on
img.kovapi.com; the job record itself can be polled for 3 days after it finishes.
Nano Banana Pro API: frequently asked questions
Is Nano Banana Pro the same as Gemini 3 Pro Image?
gemini-3-pro-image in Google's API). On KovAPI you call it as nano-banana-pro through the OpenAI-style images API.How much does Nano Banana Pro cost on KovAPI?
How long does an image take?
Can I edit an existing image?
POST /v1/images/edits (or add image to a generations request) as public URLs, data: URIs or base64, together with a prompt describing the change.Are failed generations billed?
Real images from the test run
Generated through the API on 2026-10-27 with the prompts shown; not edited or cherry-picked beyond one result per prompt.
A minimalist poster for a jazz night called "BLUE HOUR", bold sans-serif title, deep navy and brass colours, one saxophone silhouette, lots of negative space
size 3:4 · 1K · 768×1024 px · ready in 23.2 s
Studio product photo of a matte ceramic coffee mug on a light oak table, soft window light from the left, shallow depth of field
size 1:1 · 1K · 1024×1024 px · ready in 26.7 s
Wide cinematic landscape of terraced rice fields at sunrise, low mist in the valleys, warm golden light, a small farmhouse in the middle distance
size 16:9 · 1K · 1024×576 px · ready in 19.5 s
Flat vector infographic titled "HOW A REQUEST TRAVELS" showing four labelled steps: Client, CDN, Gateway, Model, connected by arrows, clean pastel palette
size 4:3 · 1K · 1024×768 px · ready in 22.7 s
Live Test · Playground
Try out Nano Banana Pro right here (available after login).
Input
ImageOutput
imageAbout Nano Banana Pro
Nano Banana Pro is a flagship image model (Gemini 3 Pro Image) with stronger detail, composition and texture, and is especially good at in-image text layout and complex scenes — ideal for commercial covers, refined posters and high-quality illustration. On KovAPI it is served through the OpenAI images API: set model to nano-banana-pro to generate with your existing SDK. It supports 1K / 2K / 4K resolutions, billed per use, and failed requests are not charged.
Use cases
Generate high-quality commercial covers, campaign key visuals and brand posters with finer detail and composition for premium output.
Strong at in-image typography, it produces infographics, explainer graphics and text cards with clear titles and captions.
Handles multi-element, multi-subject compositions with more consistent characters and faithful scene reconstruction.
How to choose
Choose Nano Banana Pro for top output quality, fine detail and in-image text; choose Nano Banana 2 when speed and cost matter more.
Related Models
Explore other models you can integrate.
Nano Banana 2.1
The upgraded Nano Banana 2, with better images and text
Nano Banana 2
High-quality text-to-image / image-to-image model
GPT Image 2.5 Flare
Next-gen image model - clean and smooth
GPT Image 2
High-quality text-to-image / image-to-image model
