Openai Gpt Image 1.5 Edit API Documentation

Openai Gpt Image 1.5 Edit API Documentation

Playground

GPT Image 1.5 Edit is OpenAI’s image model for precise, natural-language edits. Add/remove objects, swap backgrounds, retouch faces, adjust colors/lighting, edit text/graphics, crop/resize, and apply hex color control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

GPT Image 1.5 Edit is a cost-efficient image editing model powered by OpenAI’s GPT image technology. It enables users to refine, modify, or transform existing images using natural language instructions, while maintaining the original style, composition, and visual integrity.

🌟 Key Features

• 🧠 Strong Visual Understanding Understands complex textual instructions and applies targeted edits that match intent and context.

• 🎨 Intelligent Image Editing Add, remove, or modify elements in an image with precision — from subtle adjustments to full stylistic transformations.

• 🖼 Multi-Image Support Accepts one or more image inputs to guide the edit or style reference process.

• 💡 Context-Aware Refinement Preserves the key artistic or photographic features (lighting, tone, pose) while applying changes only where needed.

• 💰 Efficient and Accessible Professional-quality visual editing at low cost, ideal for rapid prototyping, design iteration, or creative workflows.

⚙️ Parameters

💡 Example Prompt

Three fashionable young women in a nighttime urban scene, showcasing Y2K and streetwear aesthetics. Each has distinct styling: plaid shirt with ripped jeans, off-shoulder top with retro socks and chunky sneakers, crop top with cowboy boots and accessories. Enhance lighting and color balance for a cinematic look.

💰 Pricing

Reference table (total_price per image edit):

• Prices include one input image processed at low input fidelity.
• Each additional input image adds $0.01.
• input_fidelity: high (the default) adds $0.05 per input image on top.

Use Cases

• Product & Fashion Editing — Adjust outfits, lighting, or background for catalog or campaign visuals.
• UI/UX & Brand Design — Apply aesthetic refinements to mockups or visual assets.
• Creative Direction — Evolve photo concepts while preserving original mood and framing.
• Photography & Illustration — Fix, enhance, or restyle images using natural text prompts.

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",
  "size": "auto",
  "background": "opaque",
  "quality": "medium",
  "input_fidelity": "high",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-1.5/edit" \
  -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