GPT Image 2.5 Flare API

Introduction

GPT Image 2.5 Flare Text to image is OpenAI's gpt-image-2.5-flare, released on 8 September 2026, generating images from a written prompt. OpenAI calls it its fastest model for high-quality, everyday image generation.

Choose a mode by starting material

Key features

Speed without a smaller option list

Flare accepts the same quality tiers, sizes and shapes as Sunburst. In our high-tier tests at 1k it usually finished in 25 to 45 seconds, which makes batches of ten and tools where someone is waiting on the result practical.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 1 credit per image ($0.01).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Daily social content

Posts, story frames and ad variations where a steady flow of finished images matters more than the last bit of detail.

Previews inside products

Apps and design tools that show a generated image while the user waits, where 30 seconds is acceptable and two minutes is not.

Thumbnails and covers in batches

Video thumbnails, playlist covers and blog headers, up to ten per request from one brief.

Prompt guide & pro tips

Stay at high for finished images

High is the default and gives finished-looking results; low and medium are for rough layout checks only.

Quote any sign or caption

Put the words in double quotes and say where they sit. The OPEN LATE sign in our example came back spelled as written.

Describe motion and weather

Wind in the hair, steam, rain on asphalt: short physical details make fast renders feel photographed rather than composed.

API quick start

Call the GPT Image 2.5 Flare API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model openai/gpt-image-2.5-flare/text-to-image and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "openai/gpt-image-2.5-flare/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "quality": "high",
    "num_outputs": 1,
    "output_format": "png"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

GPT Image 2.5 Flare API questions

All GPT Image models

GPT Image 2.5 Sunburst costs the same and takes longer, and it's the one to choose for final images and precise retouching. Flare is the choice when turnaround matters.

• GPT Image 2.5 Sunburst APIOpenAI's quality-first model, up to 4K with clean textFrom 1 credit per image
• GPT Image 2.5 Flare APIOpenAI's speed-first model with masked edits and cut-outsFrom 1 credit per image
• GPT Image 2 APILegible in-image text and precise masked editsFrom 1 credit per image

Other image APIs

• Nano Banana 2.1 APIGoogle's newest Nano Banana, sharp text and 4K outputFrom 8 credits per image
• Nano Banana Pro APIPlans the layout first: dense text, diagrams and 4K editsFrom 17 credits per image
• Seedream 5.0 Pro APIHigh-detail images and edits from up to ten referencesFrom 6 credits per image
• FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
• Qwen Image 2.1 Pro APIUp to six detailed 2K images from one promptFrom 6 credits per image
• Qwen Image 2.1 Turbo APIFast 8-step renders, up to six per promptFrom 3 credits per image

More about GPT Image 2.5 Flare

Try it

GPT Image 2.5 Flare AI Image Generator onlineCreate images with GPT Image 2.5 Flare in PopNow

Docs

GPT Image 2.5 Flare model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get GPT Image 2.5 Flare results without polling