本文へスキップ

KlingVideo model確認中

Kling 3.0 API

Model IDkling-v3-turbo-pro-text-to-video

Kling's video model in eleven variants on one page, for text to video, image to video, a 4K image to video tier and motion control, with clips from 3 to 15 seconds.

  • Image to video
  • Text to video
  • Video motion control
  • Up to 15 seconds
  • Sound
  • Multi-shot scenes
  • Start and end frames

プレイグラウンドで Kling 3.0 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

Kling 3.0Turbo pro text to videokling-v3-turbo-pro-text-to-video

必須
input.prompt

prompt. Mutually exclusive with multi-prompt. 1–2500 chars

input.duration

Billing duration: single-shot = this duration; multi-shot = sum of all segment durations, capped at 15s.

一般的なオプション
input.aspectRatio
詳細設定 (1)
input.multiPrompt

Optional shot prompts; when supplied, the main prompt is ignored. ≤ 6 items

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": "kling-v3-turbo-pro-text-to-video","input": {"duration": "5","aspectRatio": "16:9"}}

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.

Kling 3.0 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。

Kling 3.0 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.

  • Pro image to video

    kling-v3-0-pro-image-to-video

    Image to video; テキスト, 画像; 3–15 s

    negativePromptfirstImageUrllastImageUrlcfgScalesoundelementListmultiShotshotType
  • Pro text to videoデフォルト

    kling-v3-0-pro-text-to-video

    Text to video; テキスト; 3–15 s; 1:1, 16:9, 9:16

    negativePromptcfgScalesoundmultiShotshotType
  • Standard image to video

    kling-v3-0-std-image-to-video

    Image to video; テキスト, 画像; 3–15 s

    negativePromptfirstImageUrllastImageUrlcfgScalesoundelementListmultiShotshotType
  • Standard text to video

    kling-v3-0-std-text-to-video

    Text to video; テキスト; 3–15 s; 1:1, 16:9, 9:16

    negativePromptcfgScalesoundmultiShotshotType
  • Turbo pro image to video

    kling-v3-turbo-pro-image-to-video

    Image to video; テキスト, 画像; 3–15 s

    firstImageUrl
  • Turbo standard image to video

    kling-v3-turbo-std-image-to-video

    Image to video; テキスト, 画像; 3–15 s

    firstImageUrl
  • Turbo pro text to video

    kling-v3-turbo-pro-text-to-video

    Text to video; テキスト; 3–15 s; 1:1, 16:9, 9:16

  • Turbo standard text to video

    kling-v3-turbo-std-text-to-video

    Text to video; テキスト; 3–15 s; 1:1, 16:9, 9:16

  • Pro motion control

    kling-v3-0-pro-motion-control

    Video motion control; テキスト, 画像, 動画

  • Standard motion control

    kling-v3-0-std-motion-control

    Video motion control; テキスト, 画像, 動画

  • 4K image to video

    kling-v3-0-4k-image-to-video

    Image to video; テキスト, 画像; 3–15 s

    imageUrlnegativePromptendImageUrlcfgScalesoundshotTypeelementListmultiShot

Kling 3.0 でできること

Kling describes VIDEO 3.0 as a video model family with native audio, improved element consistency and multi-shot storytelling. Its guide describes optional sound and storyboard controls, but the available controls depend on the particular Hermes variant below. The separate Omni family and manufacturer product features should not be assumed to be part of every endpoint.

Kling 3.0 groups eleven model IDs that differ in two ways: the task (text to video, image to video or motion control) and the tier (Standard, Pro, Turbo Standard, Turbo Pro and one 4K variant). Each one has its own input schema, so a request that works for one variant can be rejected by another.

Pro and Standard accept the most controls: negativePrompt, cfgScale, sound, and multi-shot scenes with multiShot, shotType and up to six shots in multiPrompt. The Turbo variants take a prompt, a duration and multiPrompt only. The variant guide compares every field.

Check the selected variant’s status and price before sending a task.

できること

  • Up to 15 seconds

    Choose a length from 3 to 15 seconds.

    duration

    Every variant except Pro motion control, Standard motion control

  • Multi-shot scenes

    Describe up to 6 shots in one request, each with its own prompt and duration.

    multiShotmultiPrompt

    Every variant except Pro motion control, Standard motion control

  • Start and end frames

    Set the first frame and, optionally, the last frame the clip moves to.

    firstImageUrllastImageUrlimageUrlendImageUrl

    バリアント: Pro image to video, Standard image to video, 4K image to video

  • Sound

    Generate audio together with the video.

    sound

    バリアント: Pro image to video, Pro text to video, Standard image to video, Standard text to video, 4K image to video

  • 3 aspect ratios

    1:1, 16:9 or 9:16.

    aspectRatio

    バリアント: Pro text to video, Standard text to video, Turbo pro text to video, Turbo standard text to video

  • Motion transfer

    Animate a character image with the movement of a reference video.

    imageUrlvideoUrl

    バリアント: Pro motion control, Standard motion control

  • Element references

    Add up to 3 element references to the request.

    elementList

    バリアント: Pro image to video, Standard image to video, Pro motion control, Standard motion control, 4K image to video

  • Negative prompt

    Describe what to keep out of the result.

    negativePrompt

    Every variant except Turbo pro image to video, Turbo standard image to video, Turbo pro text to video, Turbo standard text to video

ユースケース

  1. Short clips from a script

    Text to video with a duration from 3 to 15 seconds and an aspectRatio of 1:1, 16:9 or 9:16.

  2. Animate a frame you already have

    Image to video with firstImageUrl and, on Pro and Standard, an optional lastImageUrl the clip moves toward.

  3. Several shots in one request

    Describe up to six shots in multiPrompt, each with its own prompt and duration.

  4. Character motion

    The motion control variants transfer the movement of a driving video onto a character image.

コードから Kling 3.0 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 Turbo pro text to video. Set HERMES_API_KEY in your environment.

Model ID
kling-v3-turbo-pro-text-to-video
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": "kling-v3-turbo-pro-text-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "duration": "5"
  }
}'

# 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 Turbo pro text to video (kling-v3-turbo-pro-text-to-video). 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—

prompt. Mutually exclusive with multi-prompt.

1–2500 chars

duration
string必須"5"

Billing duration: single-shot = this duration; multi-shot = sum of all segment durations, capped at 15s.

選択肢: "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"

aspectRatio
string任意"16:9"

選択肢: "1:1", "16:9", "9:16"

multiPrompt
object[]任意—

Optional shot prompts; when supplied, the main prompt is ignored.

≤ 6 items

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。

Kling 3.0 API のよくある質問

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

Is duration a string or a number?

On the Pro, Standard and Turbo variants it is a string such as "5"; sending the number 5 is rejected. The 4K image to video variant is the exception: its duration is an integer from 3 to 15.

Can I copy a Pro request to the 4K variant?

Not unchanged. The 4K variant names the first frame imageUrl and the optional last frame endImageUrl, defaults sound to false, and takes either prompt or multiPrompt, never both.

What can the Kling 3.0 API do?

Kling 3.0 by Kling handles 画像から動画, テキストから動画 および 動画モーション制御. The catalog lists 11 variants, each with its own model ID and input schema. Check the current availability before sending a request.

Which durations, resolutions and aspect ratios does Kling 3.0 support?

Across its variants, Kling 3.0 supports durations from 3 to 15 seconds および aspect ratios 1:1, 16:9 および 9:16. Each variant accepts its own subset; the variants table on this page lists them.

What input does Kling 3.0 accept?

A text prompt of up to 2,500 characters, plus 画像 または 動画 input. 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 Kling 3.0 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 Kling 3.0 variant should I choose?

For image to video, Pro image to video, Standard image to video, Turbo pro image to video, Turbo standard image to video および 4K image to video differ in fields: Pro image to video adds negativePrompt, firstImageUrl, lastImageUrl, cfgScale, sound, elementList, multiShot, shotType; Standard image to video adds negativePrompt, firstImageUrl, lastImageUrl, cfgScale, sound, elementList, multiShot, shotType; Turbo pro image to video adds firstImageUrl; Turbo standard image to video adds firstImageUrl; 4K image to video adds imageUrl, negativePrompt, endImageUrl, cfgScale, sound, shotType, elementList, multiShot; for text to video, Pro text to video, Standard text to video, Turbo pro text to video および Turbo standard text to video differ in fields: Pro text to video adds negativePrompt, cfgScale, sound, multiShot, shotType; Standard text to video adds negativePrompt, cfgScale, sound, multiShot, shotType; for video motion control, Pro motion control および Standard motion control 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 Kling 3.0 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 Kling 3.0 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.