Nano Banana 2
Gemini Flash Image v2 · text-to-image & edit. Sharper photoreal than nano-banana.
Google$0.039 / imagetext-to-imagegoogle
Capability
Est. cost$0.04For $1 you can run this model 25 times.
Example output
$0.039/ image
$0.039 per image. For $1 you can run this model 25 times.
Pay only for successful generations. No idle, no minimums, no per-seat.
API
Wire it up.
Endpoint
POST https://api.tryinfer.com/v1/inference/nano-banana-2/text-to-imagerequest
curl https://api.tryinfer.com/v1/inference/nano-banana-2/text-to-image \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "a tropical beach at sunset with palm silhouettes, cinematic lighting"
}
}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| seed | integer | — | — | — |
| prompt | string | Yes | — | — |
| num_images | integer | — | 1 | — |
| aspect_ratio | string | — | 1:1 | 21:916:93:24:31:13:42:39:16 |
| output_format | string | — | png | jpegpngwebp |
Authenticate with a bearer token. Get an API key →
Further reading
From the Infer content directory.
Best ofBest AI models for product photography in 2026Imagen 4 wins clean catalog shots, GPT Image 1.5 handles lifestyle staging, FLUX Kontext swaps backgrounds, and SAM 3.1 cuts out products at scale in 2026.CompareNano Banana 2 vs GPT Image 1.5: OpenAI vs Google imagesNano Banana 2 beats GPT Image 1.5 on speed, price, and multilingual text. GPT Image 1.5 wins complex multi-subject photorealism. Full comparison and verdict.GuidesMidjourney API alternatives: there's still no official oneMidjourney has no official API in 2026. Here's how V8.1's painterly, typography, and photoreal strengths map onto FLUX, Seedream, Nano Banana, and GPT Image.