Ideogram AI Ideogram V4.5 API Documentation

Ideogram AI Ideogram V4.5 API Documentation

Playground

Ideogram V4.5 Text-to-Image generates high-quality images from text prompts with flexible quality, strong typography, and composition controls for posters, logos, marketing visuals, brand assets, and creative production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Ideogram V4.5 generates high-quality images from text descriptions with strong typography, composition, and prompt adherence. It is especially useful for posters, packaging concepts, advertising creatives, branded graphics, editorial artwork, and other designs where layout and readable text matter.

Choose between 1K and 2K output, multiple aspect ratios, and three quality tiers depending on your workflow and budget.

Why Choose This?

• Typography-focused generation
  Create images containing signs, headlines, labels, packaging text, and other designed typography.

• Strong prompt adherence
  Guide subjects, layout, lighting, visual style, and text placement directly through natural-language prompts.

• Flexible framing
  Choose from square, landscape, portrait, and widescreen aspect ratios.

• 1K and 2K output
  Select the resolution that fits rapid iteration or higher-resolution production.

• Three quality tiers
  Choose low, medium, or high depending on the desired balance of cost and output quality.

• Prompt expansion
  Enable automatic prompt expansion to give the model additional interpretation of the original prompt.

Parameters

How to Use

1. Write a prompt — Describe the subject, composition, lighting, visual style, and any text that should appear in the image.
2. Choose resolution — Select 1k or 2k.
3. Choose aspect ratio — Pick the layout that fits your target composition.
4. Choose quality — Use low, medium, or high depending on your quality and cost requirements.
5. Configure prompt expansion optional — Keep it enabled for automatic prompt enhancement or disable it when you want to preserve the original prompt more directly.
6. Submit — Generate and retrieve the final image.

Pricing

Pricing is based only on the selected quality tier.

The default medium quality request costs $0.06 per image.

resolution, aspect_ratio, and enable_prompt_expansion do not add separate charges.

Best Use Cases

• Advertising creatives — Generate campaign concepts, promotional artwork, and branded visual assets.
• Packaging concepts — Create product packaging designs with integrated typography.
• Poster design — Generate compositions where headlines and visual hierarchy are important.
• Editorial illustrations — Produce magazine-style artwork, covers, and supporting visuals.
• Social media graphics — Create campaign and promotional content for different layouts.
• Typography-heavy concepts — Generate visuals containing signs, labels, titles, and other readable text.

Pro Tips

• Put exact text that should appear in the image inside quotation marks.
• Describe where text should appear relative to the subject and other design elements.
• Specify composition, lighting, color palette, and visual hierarchy when layout matters.
• Use low quality for rapid concept exploration before moving to higher-quality output.
• Use 2k when additional output detail or larger final dimensions are needed.
• Disable prompt expansion when you want the model to follow the original wording more directly.
• Check spelling and small text details before publishing generated artwork.

Notes

• prompt is required.
• resolution defaults to 1k.
• aspect_ratio defaults to 1:1.
• quality defaults to medium.
• enable_prompt_expansion defaults to true.
• This endpoint generates images from text; use the edit model when modifying an existing image.

Related Models

• Ideogram V4.5 — Generate images from text with typography, composition, and prompt control.
• Ideogram V4.5 Edit — Edit existing images with natural-language instructions.

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",
  "resolution": "1k",
  "aspect_ratio": "1:1",
  "quality": "medium",
  "enable_prompt_expansion": true
}
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-v4.5" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters