본문으로 건너뛰기

OpenAIImage model확인 중

GPT Image 2.6 API

Model IDgpt-image-2-6-flare-text-to-image-stable-token

Generate or edit images with GPT Image 2.6: choose Flare for fast iteration or Sunburst for detailed visual work.

  • Text to image
  • Image to image
  • Animated GIF
  • SVG output option
  • Up to 16 input images
  • Markup-guided edits
  • Quality options

플레이그라운드에서 GPT Image 2.6 실행

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

매개변수

모델
model

GPT Image 2.6Flare text to image tokengpt-image-2-6-flare-text-to-image-stable-token

필수
input.prompt

Image generation prompt (2-32000 characters). 2–32000 chars

일반 옵션
input.background

Output background mode.

input.quality

Generation quality; higher levels increase latency and token usage.

input.complexity

Planning effort before generation. low, medium, high. Omitted when not sent.

input.moderation

Moderation level. auto or low. Omitted when not sent; upstream defaults to auto.

input.svgModel

Text model that writes the SVG. Set only when outputFormat is svg. Omitted otherwise.

input.svgReasoningEffort

Reasoning effort for the SVG author. Applied only when outputFormat is svg and svgModel is set. Omitted when not sent.

input.outputFormat

Output image format.

고급 (4)
input.size

Output size. Use auto, or a supported size such as 1024x1024, 1536x1024, or 1024x1536. A custom size is WIDTHxHEIGHT: both edges must be multiples of 16 and the aspect ratio must be between 1:3 and 3:1. Neither edge may exceed 3840, and total pixels must be between 655360 and 8294400. Sizes above 2560x1440 are experimental. Omit to use auto. ≤ 32 chars · 4/32

input.frameCount

GIF frame count, 2 to 16. Set only when outputFormat is gif. Upstream defaults to 9 when omitted. 2–16

input.frameDurationMs

GIF frame duration in milliseconds, 20 to 2000, rounded to 10ms. Set only for gif. Upstream defaults to 200. 20–2000

input.outputCompression

Output compression, 0 to 100. Applies to jpeg and webp only. Omitted when not sent. 0–100

Estimated cost
가격 불러오는 중…

작업이 접수되면 크레딧이 예약되고 성공한 경우에만 차감됩니다. 실패한 작업은 예약이 해제되고, 결과가 확인되지 않은 작업은 확인될 때까지 예약이 유지됩니다.

요청 미리보기

{"model": "gpt-image-2-6-flare-text-to-image-stable-token","input": {"size": "auto","background": "auto","quality": "auto","outputFormat": "png"}}

웹 Playground는 로그인된 세션으로 이 본문을 보냅니다. 코드에서는 같은 본문을 API 키와 함께 보내세요.

결과

Run the request and the result appears here, with its status and cost.

GPT Image 2.6 가격

Prices are shown in USD for each available variant and specification. The billing unit is shown with its rate; an official reference appears only when a matching list price is published.

가격 불러오는 중…
  • Charged only on successOnly successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
  • Safe retries같은 키로 멱등 재시도해도 중복 청구되지 않습니다.
  • Price changesexpectedPriceMicros를 보내면 표시 후 가격이 바뀐 경우 PRICE_CHANGED로 작업을 거부합니다.

GPT Image 2.6 변형 비교

Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.

GPT Image 2.6로 할 수 있는 일

OpenAI positions Flare for fast, interactive image generation and editing, while Sunburst is intended for detailed compositions and image editing. Both accept text and image inputs. Select the variant and task based on your own quality and latency needs; results and timing vary by request.

The OpenAI image guide describes adjustable generation complexity, markup-guided edits, animated GIF generation and SVG output. Complexity and rendering quality are separate settings. OpenAI documents SVG for image generation, but not image editing.

Animated GIF is a distinct output option: use it to explore short motion concepts from a text prompt or an edit reference. OpenAI documents GIF generation and frame controls in its image guide; the Hermes schemas list frameCount and frameDurationMs. The manufacturer documents 2–16 frames and 20–2,000 ms per frame, subject to a total pixel budget; its GIF output does not support streaming or custom compression. Its API reference also describes preview access and mask restrictions. Check availability before running and validate the delivered result for your workflow.

The Hermes request schema has four variants: Flare and Sunburst, each with text-to-image and image-to-image modes. Edit requests list one to 16 reference images in imageUrls, plus optional maskUrl and markupUrl. Text-to-image requests list PNG, JPEG, WebP, GIF and SVG; edit requests list PNG, JPEG, WebP and GIF. These are request options, not a guarantee that every format is currently available for delivery.

Check the live availability and pricing on this page before sending a task. Input text, reference images, output format and quality can affect upstream usage; the price and billing rules for a variant are shown when configured.

기능

  • Animated GIF

    The request schema includes animated GIF output and controls for frame count and frame duration. Check current availability before running.

    outputFormatframeCountframeDurationMs

    Every variant

  • SVG output option

    The request schema includes SVG output for this variant. Check current availability and result delivery before running.

    outputFormat

    변형: Sunburst text to image token, Flare text to image token

  • Markup-guided edits

    The edit schema accepts a markup image to indicate where to change the source image.

    markupUrlmaskUrl

    변형: Sunburst image to image token, Flare image to image token

  • Quality options

    Choose a quality setting for the generated result. Options depend on the variant.

    auto · low · medium · high · xhigh · max

    quality

    Every variant

  • Format options

    The request schema lists these formats. Availability and delivery depend on the variant.

    JPEG · PNG · WEBP · GIF

    outputFormat

    Every variant

  • Up to 16 input images

    Send up to 16 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    변형: Sunburst image to image token, Flare image to image token

활용 사례

  1. Explore ideas quickly

    Try Flare for interactive iteration on a written brief, then compare settings against the result you need.

  2. Refine detailed compositions

    Try Sunburst for work where the composition and editing details matter.

  3. Edit from references

    Supply up to 16 images and describe what to keep or change. The edit schema includes optional masks and markup.

  4. Prepare motion or vector concepts

    The manufacturer documents GIF generation and SVG output for supported requests. Check the selected Hermes variant's current availability before using these formats.

코드에서 GPT Image 2.6 호출

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    API 키 생성

    In the dashboard, with the jobs:create and jobs:read scopes. API 키
  2. 2

    작업 제출

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

최소 요청

Required fields only, generated from the schema of Flare text to image token. Set HERMES_API_KEY in your environment.

Model ID
gpt-image-2-6-flare-text-to-image-stable-token
엔드포인트
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "gpt-image-2-6-flare-text-to-image-stable-token",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light"
  }
}'

# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
  -H "Authorization: Bearer $HERMES_API_KEY"

입력 매개변수

Fields of Flare text to image token (gpt-image-2-6-flare-text-to-image-stable-token). 알 수 없는 필드는 INVALID_MODEL_INPUT으로 거부됩니다.

필드유형필수기본값허용 값 및 제약 조건
prompt
string필수—

Image generation prompt (2-32000 characters).

2–32000 chars

size
string선택"auto"

Output size. Use auto, or a supported size such as 1024x1024, 1536x1024, or 1024x1536. A custom size is WIDTHxHEIGHT: both edges must be multiples of 16 and the aspect ratio must be between 1:3 and 3:1. Neither edge may exceed 3840, and total pixels must be between 655360 and 8294400. Sizes above 2560x1440 are experimental. Omit to use auto.

≤ 32 chars

background
string선택"auto"

Output background mode.

허용 값: "auto", "transparent", "opaque"

quality
string선택"auto"

Generation quality; higher levels increase latency and token usage.

허용 값: "auto", "low", "medium", "high", "xhigh", "max"

complexity
string선택—

Planning effort before generation. low, medium, high. Omitted when not sent.

허용 값: "low", "medium", "high"

moderation
string선택—

Moderation level. auto or low. Omitted when not sent; upstream defaults to auto.

허용 값: "auto", "low"

svgModel
string선택—

Text model that writes the SVG. Set only when outputFormat is svg. Omitted otherwise.

허용 값: "gpt-4.1-mini", "gpt-5.4-mini", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-6-astra", "gpt-6-luna"

svgReasoningEffort
string선택—

Reasoning effort for the SVG author. Applied only when outputFormat is svg and svgModel is set. Omitted when not sent.

허용 값: "none", "minimal", "low", "medium", "high", "xhigh", "max"

frameCount
integer선택—

GIF frame count, 2 to 16. Set only when outputFormat is gif. Upstream defaults to 9 when omitted.

2–16

frameDurationMs
integer선택—

GIF frame duration in milliseconds, 20 to 2000, rounded to 10ms. Set only for gif. Upstream defaults to 200.

20–2000

outputCompression
integer선택—

Output compression, 0 to 100. Applies to jpeg and webp only. Omitted when not sent.

0–100

outputFormat
string선택"png"

Output image format.

허용 값: "jpeg", "png", "webp", "gif", "svg"

Headers, response, task statuses and errors
헤더값참고
AuthorizationBearer <API key>또는 x-api-key로 키를 보냅니다.
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>필수입니다. 동일한 요청을 재시도할 때만 재사용하세요.
필드유형참고
idstringHermes AI 작업 ID입니다. 폴링에 사용하세요.
modelstring모델 slug입니다.
statusstring작업 상태를 참조하세요.
errorCodestring | null작업이 실패하거나 검토가 필요할 때 설정됩니다.
priceMicrosinteger접수 시 확정된 견적(USD 마이크로 단위)입니다.
currency"USD"
createdAt / updatedAtstringISO 8601 타임스탬프입니다.
assets[]array{ id, type, url?, text? }. url은 동일 출처의 /api/v1/results/<uuid> 링크입니다.
replayedboolean제출 시에만 해당합니다. 멱등 재시도가 일치하면 true입니다.
상태최종 상태의미
queued아니요접수되어 워커를 기다리는 중입니다.
submitting아니요모델 제공업체로 전송 중입니다.
running아니요모델이 생성 중입니다.
succeeded예완료되었습니다. 결과는 assets에 있습니다.
failed예결과 없이 종료되었습니다. 예약이 해제됩니다.
reconciliation_required예The result is being verified. Keep the task ID and do not resubmit automatically.
HTTP코드의미 및 조치
401AUTH_REQUIREDAPI 키 또는 세션이 없거나 유효하지 않습니다.
403INSUFFICIENT_SCOPEAPI 키에 이 엔드포인트에 필요한 권한이 없습니다.
403PERMISSION_DENIED이 자격 증명으로는 이 작업을 수행할 수 없습니다.
429API_KEY_RATE_LIMITEDAPI 키의 요청 한도에 도달했습니다. Retry-After를 따르세요.
429API_KEY_USAGE_EXCEEDEDAPI 키가 사용 한도에 도달했습니다. 새 키를 생성하세요.
400INVALID_REQUEST본문이 JSON 객체가 아니거나 필수 값이 없습니다.
400INVALID_IDEMPOTENCY_KEYIdempotency-Key는 1~128자의 출력 가능한 ASCII 문자여야 합니다.
400INVALID_MODEL_INPUTinput이 모델 스키마와 일치하지 않습니다(알 수 없는 필드, 누락된 필수 필드 또는 잘못된 값).
400 / 413INPUT_TOO_LARGE요청 본문이 256KB를 초과합니다. 미디어를 먼저 업로드하고 미디어 참조를 보내세요.
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUND이 slug를 가진 모델이 없습니다.
404JOB_NOT_FOUND이 ID의 작업은 계정에 속하지 않습니다.
409IDEMPOTENCY_CONFLICT이 Idempotency-Key는 다른 입력으로 사용되었습니다. 새 요청에는 새 키를 사용하세요.
409PRICE_CHANGED가격이 expectedPriceMicros와 다릅니다. 가격을 다시 가져와 확인하세요.
409MODEL_PRICE_UNAVAILABLE이 모델에는 아직 가격이 설정되지 않아 실행할 수 없습니다.
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITS사용 가능한 크레딧이 작업 가격보다 부족합니다.
429RATE_LIMITED분당 작업 제출이 너무 많습니다. 나중에 다시 시도하세요.
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITED완료되지 않은 작업이 너무 많습니다. 하나가 끝날 때까지 기다리세요.
503EXECUTION_UNAVAILABLE현재 이 모델의 실행이 구성되어 있지 않습니다.
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDEDThis model is temporarily unavailable. Try again later.
503EXECUTION_TEMPORARILY_UNAVAILABLE실행을 일시적으로 사용할 수 없습니다. 같은 Idempotency-Key로 다시 시도하세요.
503AUTH_UNAVAILABLE인증을 일시적으로 사용할 수 없습니다. 나중에 다시 시도하세요.
503API_UNAVAILABLEAPI를 일시적으로 사용할 수 없습니다. 나중에 다시 시도하세요.

GPT Image 2.6 API 자주 묻는 질문

Answers built from the model's schema and the Hermes AI API contract.

Which variant should I choose?

Pick text to image for a written prompt, or image to image to supply references. OpenAI positions Flare for fast iteration and Sunburst for detailed visual work. Check the current status and price of the exact Hermes variant before running it.

Why can't I run a variant?

A listed variant may be unavailable while its pricing or execution is being configured. Its current status and the playground's run control show whether it can accept requests.

Can I provide a mask?

The image-to-image variants list optional maskUrl and markupUrl fields. The source describes a mask as a PNG with an alpha channel and the same dimensions as the source image.

What can the GPT Image 2.6 API do?

GPT Image 2.6 by OpenAI handles 텍스트→이미지 및 이미지→이미지. The catalog lists 4 variants, each with its own model ID and input schema. Check the current availability before sending a request.

What input does GPT Image 2.6 accept?

A text prompt of up to 32,000 characters, plus 이미지 input (up to 16 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 알 수 없는 필드는 INVALID_MODEL_INPUT으로 거부됩니다.

How is GPT Image 2.6 priced and billed?

You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.

Which GPT Image 2.6 variant should I choose?

For text to image, Sunburst text to image token 및 Flare text to image token take the same input fields and differ in tier and price; for image to image, Sunburst image to image token 및 Flare image to image token take the same input fields and differ in tier and price. Pick the task first, then compare the tiers in the variants table.

How do I call the GPT Image 2.6 API from code?

Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.

Can I try GPT Image 2.6 without writing code?

Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.

What happens when a task fails or I hit a rate limit?

A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.