本文へスキップ

OpenAIImage model確認中

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

プレイグラウンドで GPT Image 2.6 を実行

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

パラメーター

モデル
model

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

必須
input.prompt

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

一般的なオプション
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.

詳細設定 (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
料金を読み込み中…

タスクが受け付けられるとクレジットが確保され、成功した場合のみ課金されます。失敗したタスクは確保を解除し、結果未確定のものは確認まで確保されたままです。

リクエストのプレビュー

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

Web Playground はサインイン中のセッションでこのボディを送信します。コードからは同じボディを API キーとともに送信してください。

結果

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

GPT Image 2.6 の料金

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.

料金を読み込み中…
  • 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 retries同じキーによる冪等な再試行で二重に課金されることはありません。
  • Price changesexpectedPriceMicros を送ると、表示後に料金が変わった場合に PRICE_CHANGED でタスクを拒否できます。

GPT Image 2.6 のバリアントを比較

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 2.6 でできること

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.

できること

  • 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

    バリアント: 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

    バリアント: 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

    バリアント: Sunburst image to image token, Flare image to image token

ユースケース

  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.

コードから GPT Image 2.6 を呼び出す

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

  1. 1

    API キーを作成

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

    タスクを送信

    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.

最小リクエスト

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
エンドポイント
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"

入力パラメーター

Fields of Flare text to image token (gpt-image-2-6-flare-text-to-image-stable-token). 不明なフィールドは INVALID_MODEL_INPUT で拒否されます。

フィールド型必須デフォルト許可される値と制約
prompt
string必須—

Image generation prompt (2-32000 characters).

2–32000 chars

size
string任意"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
string任意"auto"

Output background mode.

選択肢: "auto", "transparent", "opaque"

quality
string任意"auto"

Generation quality; higher levels increase latency and token usage.

選択肢: "auto", "low", "medium", "high", "xhigh", "max"

complexity
string任意—

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

選択肢: "low", "medium", "high"

moderation
string任意—

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

選択肢: "auto", "low"

svgModel
string任意—

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

選択肢: "gpt-4.1-mini", "gpt-5.4-mini", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-6-astra", "gpt-6-luna"

svgReasoningEffort
string任意—

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

選択肢: "none", "minimal", "low", "medium", "high", "xhigh", "max"

frameCount
integer任意—

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

2–16

frameDurationMs
integer任意—

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

20–2000

outputCompression
integer任意—

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

0–100

outputFormat
string任意"png"

Output image format.

選択肢: "jpeg", "png", "webp", "gif", "svg"

Headers, response, task statuses and errors
ヘッダー値備考
AuthorizationBearer <API key>または x-api-key でキーを送信します。
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>必須。まったく同じリクエストを再試行する場合のみ再利用してください。
フィールド型備考
idstringHermes AI のタスク ID。ポーリングに使用します。
modelstringモデル slug。
statusstringタスクのステータスを参照。
errorCodestring | nullタスクが失敗した場合や確認が必要な場合に設定されます。
priceMicrosinteger受付時に確定した見積もり(USD マイクロ単位)。
currency"USD"
createdAt / updatedAtstringISO 8601 形式のタイムスタンプ。
assets[]array{ id, type, url?, text? }。url は同一オリジンの /api/v1/results/<uuid> リンクです。
replayedboolean送信時のみ。冪等な再試行が一致した場合は true。
ステータス終了状態意味
queuedいいえ受け付け済みで、ワーカーを待っています。
submittingいいえモデルプロバイダーに送信中です。
runningいいえモデルが生成中です。
succeededはい完了しました。結果は assets にあります。
failedはい結果なしで終了しました。予約は解放されます。
reconciliation_requiredはいThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPコード意味と対応
401AUTH_REQUIREDAPI キーまたはセッションがない、または無効です。
403INSUFFICIENT_SCOPEAPI キーにこのエンドポイントで必要な権限がありません。
403PERMISSION_DENIEDこの認証情報ではこの操作を実行できません。
429API_KEY_RATE_LIMITEDAPI キーのレート制限に達しました。Retry-After に従ってください。
429API_KEY_USAGE_EXCEEDEDAPI キーが使用上限に達しました。新しいキーを作成してください。
400INVALID_REQUESTボディが JSON オブジェクトではないか、必須の値がありません。
400INVALID_IDEMPOTENCY_KEYIdempotency-Key は 1〜128 文字の印字可能な ASCII 文字である必要があります。
400INVALID_MODEL_INPUTinput がモデルのスキーマと一致しません(不明なフィールド、必須フィールドの欠落、または無効な値)。
400 / 413INPUT_TOO_LARGEリクエストボディが 256 KB を超えています。先にメディアをアップロードし、メディア参照を送信してください。
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDこの slug のモデルはありません。
404JOB_NOT_FOUNDこの ID のタスクはお客様のアカウントに存在しません。
409IDEMPOTENCY_CONFLICTこの Idempotency-Key は別の入力で使用されています。新しいリクエストには新しいキーを使ってください。
409PRICE_CHANGED料金が expectedPriceMicros と異なります。料金を取得して再度確認してください。
409MODEL_PRICE_UNAVAILABLEこのモデルにはまだ料金が設定されていないため、実行できません。
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITS利用可能なクレジットがタスクの料金に足りません。
429RATE_LIMITED1 分あたりのタスク送信数が多すぎます。後で再試行してください。
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITED未完了のタスクが多すぎます。いずれかが完了するまでお待ちください。
503EXECUTION_UNAVAILABLE現在、このモデルの実行は設定されていません。
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_UNAVAILABLE一時的に実行できません。同じ Idempotency-Key で再試行してください。
503AUTH_UNAVAILABLE一時的に認証を利用できません。後で再試行してください。
503API_UNAVAILABLE一時的に API を利用できません。後で再試行してください。

GPT Image 2.6 API のよくある質問

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 テキストから画像 および 画像から画像. 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 画像 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. 不明なフィールドは INVALID_MODEL_INPUT で拒否されます。

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 および 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 および 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.