GPT Image 2.6 Flare Text to Image API

openai/gpt-image-2.6-flare/text-to-image

1K · 2K · 4K

GPT Image 2.6 Flare Text to Image turns text prompts into 1K–4K images with fast low-quality drafts, legible poster typography and transparent backgrounds. It places headlines, subjects and props where the prompt puts them, so one prompt carries a concept from quick draft to final quality.

Get API Key

Input

PromptRequired832/32000

SizeOptional

ResolutionOptional

Output FormatOptional

QualityOptional

BackgroundOptional

ModerationOptional

ComplexityOptional

OutputReady

Maximum upfront charge: 5.50 credits · $0.02750

Billed by actual tokens. Any difference is refunded after completion.

Continue using

GPT Image 2.6 Flare Image Edit GPT Image 2.6 Sunburst Text to Image GPT Image 2.5 Flare Text to Image

Examples

Premium commercial product photograph of an unbranded handmade stoneware pour-over coffee dripper in speckled oatmeal glaze, seated on a clear borosilicate glass carafe half filled with dark coffee. A thin wisp of steam rises from the dripper. Beside it on the right: a small matching speckled cup on a saucer and a few whole coffee beans scattered naturally. Everything rests on a honed cream travertine slab with visible pores. Soft early-morning window light from the left casts long gentle shadows and a warm rim highlight on the glaze; background is a softly blurred warm plaster wall. Eye-level 50mm lens, shallow depth of field, crisp focus on the dripper rim, realistic glass refraction and liquid. Calm minimal styling, no text, no logos, no brand marks, no watermark.

A wide gouache-and-ink landscape illustration of a small red mountain train crossing a curved stone viaduct high above a green alpine valley. Snow-dusted granite peaks rise behind under a pale overcast sky that fills the top third of the frame. A turquoise glacial river winds along the valley floor between larch forests turning gold, with a tiny wooden chapel and three chalets on the left slope. Visible brush texture, crisp ink linework, gentle atmospheric perspective, calm late-afternoon light. Wide cinematic composition with the viaduct across the middle third. No people in close-up, no text, no logos, no watermark.

REST API

Quick Start

This flow submits one valid GPT Image 2.6 Flare Text to Image request, captures its task_id, and reads image URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one image task

Send the current model ID, prompt to the unified submit endpoint. The example keeps only first-call fields.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-image-2.6-flare/text-to-image",
  "input": {
    "prompt": "A serene mountain landscape at sunset.",
    "size": "16:9",
    "resolution": "1K",
    "output_format": "webp",
    "output_compression": 80,
    "quality": "medium"
  }
}'

Wait for the image result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "not_started",
    "created_time": "2026-09-25T08:00:00"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "finished",
    "created_time": "2026-09-25T08:00:00",
    "files": [
      {
        "file_url": "https://example.com/result.png",
        "file_type": "image"
      }
    ]
  }
}

Complete runnable polling example

Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "openai/gpt-image-2.6-flare/text-to-image",
  "input": {
    "prompt": "A serene mountain landscape at sunset.",
    "size": "16:9",
    "resolution": "1K",
    "output_format": "webp",
    "output_compression": 80,
    "quality": "medium"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	Non-blank text, up to 32,000 characters.
input.size	string	No	1:1	Default 1:1. Ratios: auto, 1:1, 2:3, 3:2, 4:3, 3:4, 4:5, 5:4, 16:9, 9:16, 21:9, or custom WIDTHxHEIGHT. auto works at any resolution and is billed at 1K. Custom WIDTHxHEIGHT works at any resolution: positive multiples of 16, maximum edge 3840, ratio at most 3:1 and 655360–8294400 pixels, billed at the higher of the selected resolution and its pixel tier (up to 1,572,864 px 1K, up to 4,194,304 px 2K, above that 4K).
input.resolution	string	No	1K	1K, 2K or 4K. Default 1K. 1K, 2K, 4K.
input.output_format	string	No	png	png, jpeg or webp. Default png. png, jpeg, webp.
input.quality	string	No	high	low, medium, high, xhigh or max. Default high. Quality and the billing tier set the upfront cap; final billing uses actual tokens. low, medium, high, xhigh, max.
input.background	string	No	auto	auto, transparent or opaque. Default auto. transparent requires png or webp. auto, transparent, opaque.
input.output_compression	integer	No	–	Integer from 0 to 100 for jpeg or webp output. Leave empty for the default compression.
input.moderation	string	No	auto	auto or low. Default auto; low applies less restrictive filtering. Does not change the price. auto, low.
input.complexity	string	No	high	low, medium or high. Default high. Sets how much the model plans before rendering and does not change the price. low, medium, high.

Response Fields

The submit response identifies the task. The status response supplies image files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct generated-image URL.
data.files[].file_type	string	Image results are identified as image.
data.files[].watermark_url	string \| null	Optional watermarked-file URL when present.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Image generation is in progress; continue polling.
finished
Successful terminal state; validate files and read image URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

AuthenticationKeep a valid VIDGO_API_KEY on the server and send requests with Bearer authentication.
Validation400 indicates an invalid model ID, field, enum, length, or image count.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesRead image URLs from files after finished, or error_message after failed. Both states end polling.
Callback optionProvide a public top-level callback_url to receive a flat task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Model	openai/gpt-image-2.6-flare/text-to-image	Text-to-image generation.
size	auto / 1:1 / 2:3 / 3:2 / 4:3 / 3:4 / 4:5 / 5:4 / 16:9 / 9:16 / 21:9 / WIDTHxHEIGHT	Default: 1:1
Output	1 image per request · png / jpeg / webp	jpeg and webp accept output_compression from 0 to 100.
complexity	low / medium / high	Planning effort before rendering. Default high; does not change the price.

GPT Image 2.6 Flare Text to Image API documentation

GPT Image 2.6 Flare Text to Image

GPT Image 2.6 Flare Text to Image uses the faster of the two models in OpenAI’s Images 2.6 release, launched on November 4, 2026. OpenAI reports about 50% faster generation on average than earlier models, roughly six-second results at low quality, and better layout for posters and product shots. Render at 1K, 2K or 4K with presets or custom sizes, and use the new compression, moderation and planning controls.

Why Choose GPT Image 2.6 Flare Text to Image?

Fast drafts at low qualityOpenAI positions Flare for quick iteration and cites about six seconds per image at low quality, so you can test compositions and copy before moving to higher tiers.
Layout and lettering for postersImproved layout for posters and product visuals keeps headlines, captions and subjects where the prompt places them. Quote the exact words you want rendered.
Planning control with complexityChoose low, medium or high complexity to set how much the model plans before rendering. It works independently of quality and costs the same at every level.
Lighter files with output_compressionExport jpeg or webp with output_compression from 0 to 100 and deliver web-ready assets straight from the API.
Any size at any resolutionUse 10 presets, auto or a custom WIDTHxHEIGHT at 1K, 2K or 4K. auto is billed at 1K, and custom sizes follow their pixel tier.
Token billing with a known ceilingYou pay for actual text and image tokens. The upfront hold is the most a task can cost, and the unused part returns to your balance when it finishes.

Parameters

Parameter	Requirement	Description
prompt	Required	Non-blank text, up to 32,000 characters.
size	Optional	Default 1:1. Ratios: auto, 1:1, 2:3, 3:2, 4:3, 3:4, 4:5, 5:4, 16:9, 9:16, 21:9, or custom WIDTHxHEIGHT. auto works at any resolution and is billed at 1K. Custom WIDTHxHEIGHT works at any resolution: positive multiples of 16, maximum edge 3840, ratio at most 3:1 and 655360–8294400 pixels, billed at the higher of the selected resolution and its pixel tier (up to 1,572,864 px 1K, up to 4,194,304 px 2K, above that 4K). Default`1:1`
resolution	Optional	1K, 2K or 4K. Default 1K. Default`1K2K4K`
output_format	Optional	png, jpeg or webp. Default png. Default`pngjpegwebp`
quality	Optional	low, medium, high, xhigh or max. Default high. Quality and the billing tier set the upfront cap; final billing uses actual tokens. Default`highlowmediumxhighmax`
background	Optional	auto, transparent or opaque. Default auto. transparent requires png or webp. Default`autotransparentopaque`
output_compression	Optional	Integer from 0 to 100 for jpeg or webp output. Leave empty for the default compression.
moderation	Optional	auto or low. Default auto; low applies less restrictive filtering. Does not change the price. Default`autolow`
complexity	Optional	low, medium or high. Default high. Sets how much the model plans before rendering and does not change the price. Default`highlowmedium`

How to Use

Write the promptDescribe the subject, layout, lighting and style. Put any words that should appear in the image inside straight double quotes.
Pick size and resolutionChoose a preset such as 2:3 for posters or 16:9 for banners, auto, or a custom WIDTHxHEIGHT, then 1K, 2K or 4K.
Set quality and planningStart with low or medium quality for drafts. Keep complexity at high for scenes with many constrained elements.
Choose the file formatUse png for transparency or lossless files, or jpeg and webp with output_compression for lighter files.
Run and collect the imageSubmit the task and read the image URL from the result once its status is finished.

Usage and Pricing

Billed by actual text input, image input and image output tokens. 1 credit = $0.005.

An upfront cap is held at submission from quality and billing tier, from 5.50 credits at low 1K to 142.34 credits at max 4K. The cap is the most a task can cost: after completion, actual tokens are settled and the difference is refunded, and failed tasks are refunded in full.

Usage and Pricing
Usage	Credits / 1M tokens	USD / 1M tokens
Text input	800	$4.00
Image input	1,280	$6.40
Image output	4,800	$24.00

Best Use Cases

Posters, banners and social graphicsDraft layouts with headlines and captions at low quality, then re-run the chosen prompt at high quality for delivery.
Product shots and ad conceptsExplore surfaces, lighting and props around a product in 4:5, 1:1 or 16:9 before committing to a final render.
Web-ready illustrationsGenerate webp or jpeg with output_compression for blog headers and landing pages without a separate compression step.
Transparent design assetsCreate stickers, icons and spot illustrations as transparent PNG or WebP for direct use in layouts.

Pro Tips

Quote exact text: wrap headlines and labels in straight double quotes and state that they are the only words, as in the Port Alder poster example.
Draft cheap, finish sharp: keep the prompt fixed and move from low to high quality once the composition works.
Use complexity deliberately: keep the high default for crowded scenes and try low for simple single-subject images.
Match formats to features: transparency needs png or webp, and output_compression applies to jpeg and webp.

Notes

Each request returns one image. prompt accepts up to 32,000 characters.
The upfront cap depends on quality and billing tier; complexity and moderation leave the price unchanged.
To edit existing images or combine up to 16 references, use GPT Image 2.6 Flare Image Edit.
Tasks run asynchronously: submission returns a task_id, and the finished status carries the image URL.

Related Models

GPT Image 2.6 Flare Image EditGPT Image 2.6 Flare Image Edit turns 1–16 reference images and text instructions into a new 1K–4K image, with optional masks, transparent cutouts and adjustable planning effort. It keeps the first image’s aspect ratio by default, and keep-and-change instructions let it recolor or relight a subject while the rest holds.

GPT Image 2.6 Sunburst Text to Image preview

GPT Image 2.6 Sunburst Text to ImageGPT Image 2.6 Sunburst Text to Image turns detailed text prompts into 1K–4K images with fine material texture, crowded multi-element layouts and quality up to max. It keeps long scene descriptions in order, placing subjects, props and light where the prompt puts them.

GPT Image 2.6 Sunburst Image Edit preview

GPT Image 2.6 Sunburst Image EditGPT Image 2.6 Sunburst Image Edit turns 1–16 reference images and text instructions into a refined 1K–4K image, with masks, multi-image composites and quality up to max. Built for stronger consistency across edits, it keeps identity, materials and lighting steady while applying the requested change.

Ideogram Vector 1.0 Text to Vector preview

Ideogram Vector 1.0 Text to VectorIdeogram Vector 1.0 Text to Vector turns a written prompt into SVG artwork for logos, icons and illustrations, with up to five reference images and 17 aspect ratios plus auto. Results are true vector files that scale cleanly from favicon to billboard.

Ideogram Vector 1.0 Image to Vector preview

Ideogram Vector 1.0 Image to VectorIdeogram Vector 1.0 Image to Vector turns one raster image into an SVG file, with a detailed default mode and a simple mode that uses fewer shapes. It follows the shapes and colours of the source so logos, sketches and illustrations become scalable artwork.

FLUX 3 Klein Text to ImageFLUX 3 Klein Text to Image turns prompts into product shots, scenes and illustrations at 1K, 2K or 4K, with seven presets, exact custom sizes and up to four images per call. It keeps per-image cost low so you can iterate widely before rendering finals.

FLUX 3 Klein EditFLUX 3 Klein Edit turns one to ten input images and a written instruction into edited or combined results at 1K, 2K or 4K, priced the same as generation. It keeps the subjects you name from each image while changing backgrounds, outfits, materials or style.

Nano Banana 2.1 Text to ImageNano Banana 2.1 Text to Image turns text prompts into 1K–4K images with text layout rendering and panoramic compositions. It preserves perspective and lighting while eliminating tiling artifacts in panoramic aspect ratios.

Nano Banana 2.1 EditNano Banana 2.1 Edit uses 1–10 reference images for image blending and local edits, with consistent characters and sharp redraws. It preserves character appearance and lighting as elements change, delivering crisp results at up to 4K resolution.

Ideogram 4.5 Text to ImageIdeogram 4.5 Text to Image turns written prompts into posters, wordmarks and text-rich images, with three quality tiers and 1–8 images per request. It keeps headlines and short copy legible while you pick the aspect ratio or one of 36 exact pixel sizes.

Ideogram 4.5 EditIdeogram 4.5 Edit turns one source image and a written instruction into a revised image, with optional masks, up to four reference images and high edit precision. It keeps the areas you did not ask to change, so repeated edits stay close to the original.

Qwen Image 2.1 Text to ImageQwen Image 2.1 Text to Image turns text into native 1K and 2K images with RGBA transparency and Chinese-English typography. It preserves lighting, composition, and aspect ratios while delivering clean transparent layers that need no background removal.

Qwen Image 2.1 EditQwen Image 2.1 Edit turns 1-10 reference images and instructions into precise edits, with multi-image feature fusion and masked inpainting. It preserves facial features and product materials while replacing backgrounds naturally and retaining every pixel outside the mask.

Seedream 5.0 Flash Text to Image preview

Seedream 5.0 Flash Text to ImageSeedream 5.0 Flash Text to Image turns text prompts into high-definition 1K to 2K images, with Chinese and English text layout and 8 aspect ratios. It closely follows complex prompts while providing fine control over lighting and composition.

Seedream 5.0 Flash Image EditSeedream 5.0 Flash Image Edit combines 1 to 10 reference images with a prompt to create new work at up to 2K resolution. It closely preserves faces, clothing and composition from the source images while naturally transforming their style.

GPT Image 2.5 Flare Text to Image preview

GPT Image 2.5 Flare Text to ImageGPT Image 2.5 Flare Text to Image turns text prompts into detailed 1K–4K images, with transparent backgrounds and low latency. It combines fast responses with natural lighting while avoiding structural distortion in large images.

GPT Image 2.6 Flare Text to Image API FAQ

What is the GPT Image 2.6 Flare Text to Image API?

GPT Image 2.6 Flare Text to Image is an OpenAI model for generating images from text prompts. It produces one 1K, 2K or 4K image per request with fast low-quality drafts, poster-ready typography, transparent backgrounds and five quality tiers from low to max. Built on OpenAI’s Images 2.6 release, it keeps the GPT Image 2.5 request fields and adds complexity, moderation and output_compression for planning, filtering and file-size control. You can call it programmatically or try it from the playground above.

How fast is GPT Image 2.6 Flare at low quality?

According to OpenAI, Flare can finish a low-quality image in about six seconds, and Images 2.6 generates about 50% faster on average than earlier models. Higher quality tiers, larger resolutions and higher complexity take longer, so draft at low quality and raise the tier once the composition is settled.

What changed from GPT Image 2.5 Flare to GPT Image 2.6 Flare?

GPT Image 2.6 Flare accepts every 2.5 Flare field and adds output_compression, moderation and complexity. Token rates stay the same, while the upfront cap at low and medium quality is higher on 2.6: 5.50 and 9.50 credits at 1K, compared with 1.31 and 2.95 on 2.5. Choose 2.5 Flare for the lowest caps, or 2.6 for the new controls and faster generation.

How does complexity affect GPT Image 2.6 Flare Text to Image?

complexity sets how much the model plans before rendering: low, medium or high, with high as the default. It is separate from quality, which controls visual fidelity, and it leaves the price unchanged. Lower values suit simple single-subject images; keep high for scenes with many elements or layout constraints.

Can GPT Image 2.6 Flare Text to Image render poster text?

Yes. Put the exact words in straight double quotes and say they are the only text. The Port Alder example on this page renders a headline, a subtitle and a date line from a single low-quality request, and OpenAI cites improved layout for posters and product visuals in Flare.

Does GPT Image 2.6 Flare Text to Image support output_compression?

Yes, for jpeg and webp output. Send an integer from 0 to 100, or leave it out for the default compression. The alpine railway example uses webp with output_compression 80. For lossless files or transparency, choose png.

Which sizes does GPT Image 2.6 Flare Text to Image support?

Ten presets from 1:1 to 21:9, auto, and custom WIDTHxHEIGHT, all at 1K, 2K or 4K. auto is billed at 1K. Custom sizes use multiples of 16, an edge of at most 3840 and a ratio up to 3:1, and are billed at the higher of the chosen resolution and their pixel tier.

How is GPT Image 2.6 Flare Text to Image billed?

By actual tokens: 800 credits ($4) per 1M text input tokens and 4,800 credits ($24) per 1M image output tokens, with 1 credit = $0.005. A cap from 5.50 credits (low, 1K) to 142.34 credits (max, 4K) is held at submission, and the unused amount is refunded when the task finishes.