Build with an AI image generation API.

01 / WORKFLOW

Match the model to the visual task

Decide whether you need a new image from text, a variation using a reference, or an edit to an existing asset. Inspect the model detail page for supported inputs, sizes, formats and generation settings. A model in the image category does not automatically accept every edit field. Studio offers examples and prompts to explore before you wire the same capability into an application.

02 / WORKFLOW

Write a brief and submit supported parameters

Describe the subject, composition, lighting and intended use in the prompt. Add size, quality, reference inputs or other options only when the selected model publishes support. The example on this page uses those published generation defaults. If no configured live model is available, it keeps an explicit placeholder so a request cannot silently target a guessed model.

03 / WORKFLOW

Handle the returned asset and review the output

Follow the response contract for the chosen endpoint: inspect returned image URLs or encoded data rather than assuming a single response format. Download or store assets according to your application requirements and the provider conditions. Review output for visual accuracy and suitability before publishing it. If a paid submission loses its response, investigate the request instead of immediately repeating the POST.

Request example

This example does not execute automatically. Verify the current model and parameters, then set these environment variables on your server. Replace any YOUR_* placeholders with confirmed supported values.

export ALLGATE_BASE_URL='https://api.allgate.ai/v1'
export ALLGATE_API_KEY='YOUR_API_KEY'

# Submit once; a lost response is not permission to repeat a paid POST.
curl --fail-with-body --silent --show-error "$ALLGATE_BASE_URL/images/generations" \
  -H "Authorization: Bearer $ALLGATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image-2.5-flare",
  "prompt": "A sculptural glass sphere above a calm silver sea",
  "n": 1,
  "size": "1024x1024",
  "quality": "auto",
  "output_format": "png"
}'

Check models and current availability

These entries come from the public catalogue build snapshot. A listing does not guarantee endpoint capability or continuing supply. For audio, verify synthesis or transcription support separately. Open a model to check its exact ID, settings and billing unit.

Catalogue snapshot: 2026-10-30

• GPT Image 2.5 FlareOpenAI · Available route in snapshot
• Gemini 3.1 Flash ImageGoogle · Available route in snapshot

Costs and workflow limits

Read the unit next to the selected model rate. Image workflows may be priced per image, per request or by another published unit. Output count and supported generation options can affect the cost. Compare the public rate and your account quote before estimating a batch; do not treat a token calculator as an image price estimator.