ListenHubDocs
API ReferenceImage Generation

Nano Banana

Nano Banana Pro, Flash, and 2.1: model IDs, limits, pricing, and examples.

Nano Banana is Google's image family on ListenHub: Pro (gemini-3-pro-image), Flash (gemini-3.1-flash-image), and 2.1 (gemini-nano-banana-2.1). All three use the shared image endpoints. For the endpoints, request schema, async flow, and error codes, see the Image Generation overview. This page covers only what is specific to Nano Banana.

Models

ModelDisplay nameBest for
gemini-3-pro-imageNano Banana ProThe most detailed output in the catalogue
gemini-3.1-flash-imageNano Banana FlashFaster, cheaper generation, and the only Nano Banana tier that takes the extreme ratios
gemini-nano-banana-2.1Nano Banana 2.1Nano Banana 2.1; 15 credits at 1K/2K, 30 at 4K

All three take provider: "google". The preview IDs gemini-3-pro-image-preview and gemini-3.1-flash-image-preview are still accepted and normalized to the GA IDs above.

Limits

Limitgemini-3-pro-imagegemini-3.1-flash-imagegemini-nano-banana-2.1
Image sizes1K, 2K, 4K1K, 2K, 4K1K, 2K, 4K
Aspect ratiosThe 10 standard ratiosAll 14, including the extreme fourThe 10 standard ratios
Default aspect ratio1:1 (schema default)1:1 (schema default)1:1 (schema default)
Reference imagesUp to 14Up to 14Up to 14
qualityIgnoredIgnoredIgnored

1:4, 4:1, 1:8, and 8:1 are Flash-only within this family — sending one to gemini-3-pro-image or gemini-nano-banana-2.1 returns 400 with code: 29003. Every ratio rejection on Nano Banana carries 29003, not the 26019 that GPT-Image and Wan 2.7 use.

All three models accept up to 14 reference images in total, including URL and base64 inputs.

The extreme ratios

Four ratios cover shapes the standard set cannot express — banners, vertical strips, and panoramas:

RatioShapeTypical use
1:4Narrow portraitSidebar art, vertical strips
4:1Wide landscapePage banners, headers
1:8Extreme portraitTall scrolling panels
8:1PanoramicWide panoramas, footer strips

Within Nano Banana they are Flash-only. Outside it, seedream-5-0-pro and seedream-5-5 accept them too — they are validated on size rather than on ratio.

Free quota

Pro and Flash have their own free-quota resource, spendable at 1K and 2K only — a 4K request is always billed in credits. How the quota is earned and read back is on the overview.

ModelFree-quota resource
gemini-3-pro-imagegemini-3-pro-image-relax-1k-2k
gemini-3.1-flash-imagegemini-3.1-flash-image

Nano Banana 2.1 has no free quota or relax lane; every size is billed in credits.

The relax lane

gemini-3-pro-image is the only model in the catalogue whose free quota runs on a separate execution lane. How it runs depends on your account type:

  • Accounts that have ever paid (active subscription, recharge, or credit-pack purchase) keep full priority, normal capacity, and normal fallback while spending free quota — the quota changes billing, not the lane you run on.
  • Pure-free accounts (never paid anything) run on a lowest-priority free lane with a fixed throughput cap. At peak times a request may be queued or rejected with a retryable busy/timeout response. When that happens, no credits are spent and the free quota is not consumed — retry later.

A pure-free relax failure returns machine-readable metadata so you can detect it without parsing localized text:

  • failReason is free_relax_busy or free_relax_timeout.
  • retryable is true.
  • freeUsageRolledBack is true once the free quota has been refunded.
  • userMessage carries friendly, localizable copy on the synchronous error body; the async task object exposes the same copy as failUserMessage. The two surfaces use different field names — read both if you handle both paths.

For synchronous requests this appears in the error body; for async requests it appears on the failed task detail (and in the task list). Treat both reasons as "retry later, nothing was charged".

Pricing

All three models use fixed per-size credit pricing (pricing.mode: "fixed") and do not require a subscription. Nano Banana 2.1 costs 15 credits at 1K, 15 at 2K, and 30 at 4K per image. Call POST /v1/images/generation/estimate-credits with the model and size to check the current price.

Example

curl -X POST "https://api.marswave.ai/openapi/v1/images/generation/async" \
  -H "Authorization: Bearer $LISTENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "google",
    "model": "gemini-3.1-flash-image",
    "prompt": "A panoramic mountain range at dawn, layered mist, muted palette",
    "imageConfig": { "imageSize": "2K", "aspectRatio": "8:1" }
  }'

See the Image Generation overview for the full parameter list and the reference-image request shapes.

Nano Banana 2.1 example

curl -X POST "https://api.marswave.ai/openapi/v1/images/generation/async" \
  -H "Authorization: Bearer $LISTENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "google",
    "model": "gemini-nano-banana-2.1",
    "prompt": "A mountain range at dawn, layered mist, muted palette",
    "imageConfig": { "imageSize": "2K", "aspectRatio": "16:9" }
  }'

This body works with the synchronous endpoint /v1/images/generation and the estimate endpoint /v1/images/generation/estimate-credits too. Add referenceImages in the format shown in the overview for image editing (up to 14 images).

On this page