Google Nano Banana 2.1 Text To Image API Documentation

Google Nano Banana 2.1 Text To Image API Documentation

Playground

Google Nano Banana 2.1 is the latest Nano Banana image generation model, with gains in visual design, subject consistency and prompt adherence, cleaner text rendering, 1K to 4K output and optional web search. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Nano Banana 2.1 Text-to-Image is Google’s latest Nano Banana AI image generation model. Google reports that it outperforms its previous image models across the board, with notable leaps in visual design and subject consistency, tighter prompt adherence and cleaner text rendering.

Why Choose This?

• Google’s newest Nano Banana Upgraded over Nano Banana 2 in visual design, subject consistency and prompt adherence.

• Cleaner text rendering Sharper labels, signs and typography inside the image.

• Multi-resolution support Output in 1K, 2K, or 4K resolution based on your needs.

• Flexible aspect ratios Fourteen options: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1.

• Web & image search grounding Optionally let the model use current information and real reference images from the web.

• Format choice Export in PNG or JPEG format.

Parameters

How to Use

1. Write your prompt — describe the image in detail, including subject, composition, lighting, style and any text in quotes.
2. Choose aspect ratio (optional) — select a preset or leave empty for the default 1:1.
3. Select resolution — choose 1K, 2K, or 4K based on your needs.
4. Enable web or image search (optional) — for prompts that depend on current real-world information or how real things look.
5. Choose output format — PNG or JPEG.
6. Run — submit and download your generated image.

Pricing

Best Use Cases

• Design-heavy visuals — Posters, social graphics and packaging mockups where layout and typography matter.
• Character & product consistency — Keep the same subject recognizable across a series.
• Marketing & Ads — Campaign images with clean in-image copy.
• Infographics & signage — Clear labels and text elements.
• Concept Art — Visualize complex, multi-part ideas faithfully.

Pro Tips

• Spell out the whole brief in one prompt — 2.1 follows long, multi-part instructions closely.
• Put exact on-image text in quotes and say where it goes.
• Match aspect ratio to your target platform: 9:16 for Stories/Reels, 16:9 for banners, 1:8 / 8:1 for skyscraper ads.
• Draft at 1K, then re-run the final prompt at 2K or 4K.

Notes

• Prompt is the only required field.
• If aspect_ratio is not selected, the output is 1:1.
• Ensure your prompts comply with Google’s Safety Guidelines.

Related Models

• Nano Banana 2.1 Edit — Edit images with text instructions and up to 14 references.
• Nano Banana 2 Text-to-Image — Previous generation with a 0.5K option and Fast variants.
• Nano Banana Pro Text-to-Image — Pro tier image generation.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "enable_web_search": false,
  "enable_image_search": false,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/google/nano-banana-2.1/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters