by OpenAI

OpenAI's fast tier for quick drafts, edits and short GIF loops

openai/gpt-image-2.6-flare/text-to-image
  • Up to 4K
  • Up to 16 reference images
  • 15 aspect ratios
  • Up to 10 per run
  • Create Image
  • Edit Image

About GPT Image 2.6 Flare

GPT Image 2.6 Flare is the fast tier of OpenAI's GPT Image 2.6. A medium 1K image took about 12 to 16 seconds in testing. It has the same five quality levels, sizes up to 4K, edits with up to 16 pictures, masks and marked-up copies, and looping GIFs as Sunburst. Compared with GPT Image 2.5 it adds GIF output, marked-up copies, transparent backgrounds in text to image, and an optional reasoning effort setting.

Call it with the model name openai/gpt-image-2.6-flare/text-to-image on POST /jobs/createTask, from $0.02232.

Introduction

GPT Image 2.6 Flare Text to Image produces pictures from written briefs for everyday generation and quick iteration. Flare is the faster of the two 2.6 tiers, making it useful when reviewing several visual directions.

No source picture is needed for this task: write the scene and choose the delivery settings. In our tests, Flare returned medium 1k images in about 12–16 seconds each; max quality and 4k need more time.

Key features

  • Animation drafts: request output_format gif, set aspect_ratio and describe how the action repeats.
  • Quick exploration: medium is the starting quality, with four other levels available when a draft needs different detail.
  • Composition options: 15 ratios cover square artwork and tall or wide placements without a ratio fee.
  • Size selection: choose roughly 1 MP at 1k, 3.7 MP at 2k or 8.3 MP at 4k.
  • Short text in scenes: our tests produced accurate poster headlines and cafe menu lettering.

Request parameters

ParameterRequiredDescription
promptYesDescribe what you want to make.
qualityNoChoose one of this model’s quality settings. low · medium · high · xhigh · max · Default: medium
backgroundNoKeep, remove or replace the background. auto · transparent · opaque · Default: auto
resolutionNoChoose an available output size. 1k · 2k · 4k · 512 · 768 · Default: 1k
frame_countNoHow many frames the GIF loops through. Up to 8 frames count as one image; 9 to 16 count as two. ≥ 2 · ≤ 16
num_outputsNoHow many results to make in one go. ≥ 1 · ≤ 10 · Default: 1
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 2:1 · 1:2 · 3:1 · 1:3 · 5:4 · 4:5 · Default: 1:1
output_formatNoFile type of the result. png · jpeg · webp · gif · Default: png
output_qualityNoCompression for JPEG and WebP. Higher keeps more detail and makes bigger files. ≥ 0 · ≤ 100
reasoning_effortNoReasoning effort for the spoken response; reasoning consumes output tokens. low · medium · high
frame_duration_msNoHow long each GIF frame stays on screen, in milliseconds. ≥ 20 · ≤ 2000

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per image
quality low · resolution 1K$0.02232
quality low · resolution 512$0.027
quality medium · resolution 1K$0.03915
quality low · resolution 2K$0.04131
quality low · resolution 768$0.04392
quality high · resolution 1K$0.04743
quality medium · resolution 512$0.04752
quality high · resolution 512$0.05742
quality medium · resolution 2K$0.07299
quality low · resolution 4K$0.07479
quality medium · resolution 768$0.07776
quality xhigh · resolution 1K$0.08433

Billed on the tokens each request uses: $4.50 per 1M text input tokens, $7.20 per 1M image input tokens and $27.00 per 1M image output tokens. The table lists the square-image price for each tier, so other ratios usually cost less. With several output images, input tokens count once per image.

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

  • Social campaign drafts: explore a seaside poster direction before choosing the image to develop.
  • Cafe content planning: generate a morning chalkboard scene with a small set of quoted menu labels.
  • Editorial concepts: preview a workshop portrait with natural light and a film treatment.

Prompt guide & pro tips

  • Begin with a specific scene: try “lighthouse on a cliff at sunset” to establish the setting.
  • Quote short labels: include “SUMMER 1958 at the bottom” when a draft needs a date line.
  • Give the light a source: use “sunlight through workshop windows” to define illumination.
  • Revise one idea at a time: change “bold flat colors” to a new palette while reviewing the composition.

API quick start

Call the GPT Image 2.6 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-. API calls use your separate USD balance.
  2. Send the request. POST /jobs/createTask with model openai/gpt-image-2.6-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-2.6-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": "medium",
    "num_outputs": 1,
    "background": "auto"
  }
}'

# 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 2.6 Flare price on other platforms

OptionsPopNowReplicate
1K · low · square · ≤100 prompt tokens−55% vs Replicate$0.0223/ image$0.0500/ image
1K · medium · square · ≤100 prompt tokens−56% vs Replicate$0.0392/ image$0.0900/ image
1K · high · square · ≤100 prompt tokens−62% vs Replicate$0.0474/ image$0.1280/ image
1K · xhigh · square · ≤100 prompt tokens−66% vs Replicate$0.0843/ image$0.2500/ image
1K · max · square · ≤100 prompt tokens−62% vs Replicate$0.1897/ image$0.5000/ image

Each platform's public API list price for the same model and settings, checked Nov 6, 2026.

GPT Image 2.6 Flare API questions

How much does the GPT Image 2.6 Flare API cost?

GPT Image 2.6 Flare starts at $0.02232 per image with Create Image, its cheapest task. Prices by option: low · 1K $0.02232 per image, low · 512 $0.027 per image, medium · 1K $0.03915 per image, low · 2K $0.04131 per image. The API uses a separate USD balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for GPT Image 2.6 Flare in the API?

Put openai/gpt-image-2.6-flare/text-to-image for Create Image; openai/gpt-image-2.6-flare/edit for Edit Image in the model field of POST /jobs/createTask.

Is Flare the right 2.6 tier for my task?

Use Flare for quick iteration, or see [GPT Image 2.6 Sunburst](/models/gpt-image-2-6-sunburst) for the precision tier built around fidelity and repeated revisions.

Can Flare return an asset with transparency?

Yes; request a transparent background with PNG or WebP output, a combination that worked with PNG at low 1k in our tests.

Can I mark a region for a Flare edit?

Attach a PNG mask sized to match Image 1; make the region to repaint transparent in that mask.

Where does Flare 2.5 fit?

Flare 2.6 is the speed tier of this generation; consult [GPT Image 2.5 Flare](/models/gpt-image-2-5-flare) for the prior release.

How long did Flare take in testing?

In our tests on November 5, 2026, medium 1k took about 12–16 seconds per image, compared with about 30 seconds for Sunburst at those settings.

What are the limits of the GPT Image 2.6 Flare API?

Resolutions: 1K · 2K · 4K · 512 · 768; Aspect ratios: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +9; Outputs per call: 1–10; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try GPT Image 2.6 Flare without writing code?

Run GPT Image 2.6 Flare in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All GPT Image models

GPT Image 2.6 Sunburst has the same options and price and takes longer. Choose it for final images and careful revisions.

More about GPT Image 2.6 Flare