seedinteger
The seed for the random number generator.
Nano Banana 2 Lite Text to Image
google/nano-banana-2-liteNano Banana 2 Lite by Google - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.
Try the model
Playground
Input
The text prompt to generate an image from.
Additional Settings More
Customize your input with more control.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The format of the generated image. Allowed values: jpeg, png.
The seed for the random number generator.
When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable. Allowed values: minimal, high.
Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "aspect_ratio": "1:1", "prompt": "A chalkboard menu outside a small coffee shop, photographed straight on. The board reads exactly, one item per line: 'BELUGA BLEND $4.10', 'OAT FLAT WHITE $5.25', 'MATCHA TONIC $6.00', 'BANANA BREAD $3.75'. Hand-lettered white chalk, no other text." } - Open result ↗
Input
{ "prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater." }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Text to Image
- Rank
- #15 of 106
- Elo
- 1107 ±10
- Gap to #1
- −115
Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.
- #10MAI-Image-2.6-Flash1119±12
- #11Nano Banana Pro (Gemini 3 Pro Image)1118±10
- #12MAI-Image-2.51118±11
- #13FLUX 3 Image1117±12
- #14MAI-Image-2.5-Pro1114±10
- #15Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)1107±10
- #16Seedream 5.0 Pro1100±11
- #17Qwen-Image-3.0-Pro1095±12
- #18Qwen-Image-3.01070±12
- #19Qwen-Image-2.1-Pro1056±12
Nano Banana 2 Lite Text to Image
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is the low-latency, lowest-cost Nano Banana tier for high-volume generation at 1K.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 | — | Output frame shape. |
output_format | jpeg / png | png | Output file format. |
seed | integer | random | Fix it to compare prompt changes. |
thinking_level | minimal / high | — | high reasons more about the prompt before drawing; minimal is faster. |
system_prompt | string | — | Optional standing instructions applied to every request. |
Billing
$0.0336 per 1K image, Google's list price.
| Request | Price |
|---|---|
| One image | $0.0336 |
Failed runs are not charged.
Prompting
- Keep prompts direct; use
thinking_level: highfor complex layouts.
Limits
- Output is 1K only.
Also on SandBase
Other Nano Banana endpoints: google/nano-banana-pro, google/nano-banana-pro/edit, google/nano-banana-2, google/nano-banana-2/edit, google/nano-banana-2-lite/edit.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "google/nano-banana-2-lite",
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"output_format": "png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
promptstringrequired
The text prompt to generate an image from.
aspect_ratiostring
The aspect ratio of the generated image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
output_formatstring
The format of the generated image.
Default: "png"
Possible values: "jpeg", "png"
system_promptstring
Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).
Default: ""
thinking_levelstring
When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.
Possible values: "minimal", "high"
{
"model": "google/nano-banana-2-lite",
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"output_format": "png"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/88898443-5e18-47c9-91e3-0b450057e25f/output/cb84e116-65eb-4eb4-8eb6-4b7cfefa2f13.jpg"
}
]