Start building

Nano Banana 2 Lite

google/nano-banana-2-lite

Nano 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.

Use in agentGet API key
Base price
$0.05USD / run
Execution
async
Model type
image
Input fields
6

Try the model

Playground

Open playground
Input
The text prompt to generate an image from.
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).
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.05 / run

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Google
Model ID
google/nano-banana-2-lite
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Nano Banana 2 Lite

Nano Banana 2 Lite is a speed-first image generator for rapid ideation, interactive products, and high-volume visual pipelines. It retains reliable prompt adherence, character consistency, and legible in-image text while prioritizing low latency and cost efficiency.

This endpoint accepts a text prompt and produces one image. It is the Lite text-to-image route: it does not accept reference images, while optional thinking and system instructions can help shape more demanding generations.

Highlights

  • Built for fast iteration. Designed for high-throughput, near-real-time workflows where teams need to draft, compare, and refine many visual directions quickly.
  • Reliable instruction following. Preserves the requested subjects, scene details, and relationships across practical text-to-image prompts.
  • Character consistency. Maintains recognizable character traits, making it useful for repeated concepts and coherent creative exploration.
  • Legible visual text. Handles readable wording inside posters, labels, signs, and other designed imagery without turning the request into a separate editing workflow.

Pricing

UnitPrice
Per request$0.048375

When to Use

Good fitConsider alternatives
Rapid concept thumbnails and visual draftsEditing an existing image, which needs an edit endpoint
High-volume campaign or catalog ideationMaximum-detail professional artwork where speed is secondary
Interactive image experiencesMulti-image reference composition
Character-led concept explorationOutputs above the endpoint's documented resolution controls
Posters, labels, and social graphics with textVideo, animation, or audio generation

Prompt Guide

Describe the subject first, then lock composition, visible text, lighting, and style. Put any wording that must appear in quotation marks, and use concrete spatial directions instead of vague requests. Use thinking_level only when a more involved composition benefits from extra planning.

{
  "prompt": "A friendly yellow robot barista behind a compact walnut coffee counter, three-quarter view, morning window light, teal ceramic cups arranged on the right. A clean menu board above the robot reads \"ROBOT ROAST\" in bold white sans-serif letters. Polished editorial illustration with consistent character details.",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "thinking_level": "minimal",
  "system_prompt": "Keep the composition clean and preserve all quoted text exactly."
}

Technical Specs

SpecValue
Model IDgoogle/nano-banana-2-lite
InputRequired text prompt (3–50,000 characters)
Aspect ratios21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Output formatPNG (default) or JPEG
Optional controlsInteger seed, system prompt, thinking level (minimal or high; omit to disable)
OutputOne downloadable image URL
ExecutionAsync

Related

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
google/nano-banana-2-lite
# 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"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Nano Banana 2 LiteThis model
Google		———Jun 30, 2026
Nano Banana Lite
Google		———Jun 30, 2026
Nano Banana Lite Edit
Google		———Jun 30, 2026
Nano Banana 2 Image Editing
Google		———Feb 26, 2026
Nano Banana 2
Google		———Feb 26, 2026
Nano Banana Pro Image Editing
Google		———Nov 20, 2025