Ideogram AI Ideogram V3 Balanced API Documentation

Ideogram AI Ideogram V3 Balanced API Documentation

Playground

Ideogram V3 Balanced delivers the highest-quality image generation with stunning realism, creative design, and consistent styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Generate high-quality images with exceptional typography using Ideogram V3 Balanced. This versatile model offers the optimal balance between speed, quality, and cost — perfect for everyday design work, marketing materials, and professional content creation.

Why It Looks Great

• Balanced performance: Optimal trade-off between speed, quality, and price.
• Superior typography: Industry-leading text rendering for posters, logos, and designs.
• Multiple modes: Text-to-image generation, image editing, and masked inpainting.
• Style presets: Choose from Auto, General, Realistic, or Design styles.
• Reference images: Use up to 3 reference images to guide generation.
• Mask support: Precise regional editing with custom masks.
• Flexible aspect ratios: Five format options for any use case.
• Safety Checker: Optional content filtering for appropriate output.

Parameters

How to Use

Text-to-Image Generation

1. Write your prompt — describe the image including any text you want rendered.
2. Choose style — select Auto, General, Realistic, or Design.
3. Set aspect ratio — pick the format that fits your use case.
4. Add reference images (optional) — click ”+ Add Item” to include style references.
5. Run — click the button to generate.
6. Download — preview and save your image.

Image Editing

1. Upload source image — the image you want to edit.
2. Upload mask (optional) — white areas indicate regions to regenerate.
3. Write your prompt — describe the desired changes or new elements.
4. Run — click the button to apply edits.

Pricing

Flat rate per image generation.

Style Guide

Best Use Cases

• Everyday Design Work — Create quality designs without premium pricing.
• Marketing Content — Produce professional graphics for campaigns and social media.
• Logo & Branding — Generate polished brand concepts and materials.
• Typography & Posters — Create designs with clean, readable text.
• Production Workflows — Balance quality and volume for regular content needs.

Example Prompts

• “modern minimalist poster saying ‘DESIGN WEEK 2025’, clean sans-serif typography, gradient background”
• “coffee shop menu board with text ‘Today’s Special: Caramel Latte’, chalkboard style, warm tones”
• “YouTube thumbnail with bold text ‘TOP 10 TIPS’, energetic colors, eye-catching design”
• “event invitation for ‘Summer Garden Party’, floral illustrations, elegant script font”
• “app splash screen with logo ‘FOCUS’, minimal design, calming blue gradient”

Model Comparison

Pro Tips for Best Results

• Balanced is ideal for most production work — great quality at reasonable cost.
• For typography, put the exact text in quotes within your prompt.
• Use the Design style for graphic design work with text elements.
• Use Turbo for testing concepts, Balanced for production, Quality for finals.
• Reference images help maintain consistency across multiple generations.
• Describe typography style: “modern”, “clean”, “bold”, “elegant”.

Notes

• Ideogram is renowned for best-in-class text rendering in AI-generated images.
• Balanced mode is the recommended choice for most everyday use cases.
• If using URLs for images, ensure they are publicly accessible.
• The enable_base64_output option is only available through the API.
• Reference images (up to 3) help guide style without directly copying content.

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",
  "style": "Auto",
  "aspect_ratio": "1:1"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/ideogram-ai/ideogram-v3-balanced" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters