Aller au contenu

MiniMaxVideo modelVérification

MiniMax H3 API

Model IDminimax-h3-regeneration-image-to-video

MiniMax H3 video generation with text, image, multimodal reference and regeneration variants.

  • Image to video
  • Text to video
  • Video to video
  • Reference to video
  • Up to 9 input images
  • Up to 15 seconds
  • 480p or 768p output

Lancez MiniMax H3 dans le playground

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

Paramètres

Modèle
model

MiniMax H3Regeneration image to videominimax-h3-regeneration-image-to-video

Obligatoire
input.prompt

The final prompt actually sent to the model when generating the 768P source video. 1–40000 chars

input.firstFrameUrl

first frame image (same as generation) HTTPS image URL or media:<uuid>

input.baseVideoUrl

MiniMax-H3 768P source video (with audio track, 24fps, dims divisible by 32, area <=768x1344, 107-362 frames). ≤ 1 items · HTTPS video URL or media:<uuid>

input.resolution

Target resolution (2K only).

Options courantes
input.lastFrameUrl

last frame image (same as generation) HTTPS image URL or media:<uuid>

Estimated cost
Chargement du prix…

Les crédits sont réservés à l’acceptation d’une tâche et débités seulement en cas de succès. Une tâche échouée libère la réservation ; un résultat non confirmé reste réservé jusqu’à vérification.

Aperçu de la requête

{"model": "minimax-h3-regeneration-image-to-video","input": {"resolution": "2K"}}

Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.

Résultat

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

Tarifs de MiniMax H3

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.

Chargement du prix…
  • 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 retriesLes nouvelles tentatives idempotentes avec la même clé ne créent pas de second débit.
  • Price changesEnvoyez expectedPriceMicros pour rejeter la tâche avec PRICE_CHANGED si le prix a changé après son affichage.

Comparez les variantes de MiniMax H3

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

  • Max turbo image to video

    minimax-h3-max-turbo-image-to-video

    Image to video; Texte, image; 5–15 s; 480p, 768p

  • Max turbo text to videoPar défaut

    minimax-h3-max-turbo-text-to-video

    Text to video; Texte; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    aspectRatio
  • Max image to video

    minimax-h3-max-image-to-video

    Image to video; Texte, image; 5–15 s; 480p, 768p

  • Max text to video

    minimax-h3-max-text-to-video

    Text to video; Texte; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    ratio
  • Image to video

    minimax-h3-image-to-video

    Image to video; Texte, image; 5–15 s; 2K, 768p

    aigc_watermark
  • Text to video

    minimax-h3-text-to-video

    Text to video; Texte; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    ratioaigc_watermark
  • Regeneration text to video

    minimax-h3-regeneration-text-to-video

    Video to video; Texte, vidéo; 2K

  • Regeneration image to video

    minimax-h3-regeneration-image-to-video

    Video to video; Texte, image, vidéo; 2K

    firstFrameUrllastFrameUrl
  • Multimodal reference to video

    minimax-h3-multimodal-reference-to-video

    Reference to video; Texte, image, vidéo, audio; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Ce que MiniMax H3 sait faire

MiniMax describes H3 as a multimodal video model that can use text, images, video and audio and generate video with native stereo sound. MiniMax's model documentation describes up to 2K and 15 seconds; actual options depend on the Hermes variant.

The Hermes catalog separates H3, Max and Max Turbo text-to-video and image-to-video, multimodal reference-to-video, and regeneration tasks. The multimodal reference schema lists up to nine images, three videos and three audio inputs. Regeneration variants take a base video; the other variants use different fields. Check the selected variant's status, valid options and price before running.

Capacités

  • Up to 15 seconds

    Choose a length from 5 to 15 seconds.

    duration

    Every variant except Regeneration text to video, Regeneration image to video

  • Start and end frames

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

    firstFrameUrllastFrameUrl

    Variantes: Max turbo image to video, Max image to video, Image to video, Regeneration image to video

  • 480p or 768p output

    Pick the output resolution: 480p or 768p.

    resolution

    Every variant except Regeneration text to video, Regeneration image to video

  • 6 aspect ratios

    21:9, 16:9, 4:3, 1:1, 3:4 or 9:16.

    aspectRatioratio

    Variantes: Max turbo text to video, Max text to video, Text to video, Multimodal reference to video

  • Up to 9 input images

    Send up to 9 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    Variantes: Multimodal reference to video

  • Video input

    Accepts a source video as input.

    baseVideoUrlvideoUrls

    Variantes: Regeneration text to video, Regeneration image to video, Multimodal reference to video

  • Audio input

    Accepts reference audio as input.

    audioUrls

    Variantes: Multimodal reference to video

Cas d’usage

  1. Generate a scene

    Describe the visual action and sound for a text-to-video task.

  2. Create from references

    Use the multimodal variant to supply supported reference media.

  3. Regenerate a clip

    Select a regeneration variant when you have a base video and follow its input requirements.

Appelez MiniMax H3 depuis votre code

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

  1. 1

    Créez une clé d’API

    In the dashboard, with the jobs:create and jobs:read scopes. Clés d’API
  2. 2

    Soumettre une tâche

    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.

Requête minimale

Required fields only, generated from the schema of Regeneration image to video. Set HERMES_API_KEY in your environment.

Model ID
minimax-h3-regeneration-image-to-video
Point de terminaison
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": "minimax-h3-regeneration-image-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "firstFrameUrl": "https://example.com/input.png",
    "baseVideoUrl": "https://example.com/input.mp4",
    "resolution": "2K"
  }
}'

# 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"

Paramètres d’entrée

Fields of Regeneration image to video (minimax-h3-regeneration-image-to-video). Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.

ChampTypeObligatoirePar défautValeurs autorisées et contraintes
prompt
stringobligatoire—

The final prompt actually sent to the model when generating the 768P source video.

1–40000 chars

firstFrameUrl
stringobligatoire—

first frame image (same as generation)

HTTPS image URL or media:<uuid>

lastFrameUrl
stringfacultatif—

last frame image (same as generation)

HTTPS image URL or media:<uuid>

baseVideoUrl
stringobligatoire—

MiniMax-H3 768P source video (with audio track, 24fps, dims divisible by 32, area <=768x1344, 107-362 frames).

≤ 1 items, HTTPS video URL or media:<uuid>

resolution
stringobligatoire"2K"

Target resolution (2K only).

Parmi: "2K"

Importez d’abord un fichier local

Remplacez l’URL d’exemple par la référence média renvoyée.

POST /api/v1/media
curl -X POST https://api.hermes-ai.net/api/v1/media \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: image/png" \
  --data-binary @input.png
# → { "reference": "media:<uuid>", ... }  Use the reference in an image, video or audio field.
Headers, response, task statuses and errors
En-têteValeurRemarques
AuthorizationBearer <API key>Ou envoyez la clé dans x-api-key.
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>Obligatoire. Ne le réutilisez que pour retenter la même requête.
ChampTypeRemarques
idstringID de tâche Hermes AI. Utilisez-le pour interroger.
modelstringSlug du modèle.
statusstringVoir les statuts de tâche.
errorCodestring | nullDéfini lorsqu’une tâche échoue ou doit être examinée.
priceMicrosintegerDevis fixé à l’admission, en micro-unités USD.
currency"USD"
createdAt / updatedAtstringHorodatages ISO 8601.
assets[]array{ id, type, url?, text? }. url est un lien /api/v1/results/<uuid> de même origine.
replayedbooleanSoumission uniquement. true lorsqu’une nouvelle tentative idempotente correspond.
StatutFinalSignification
queuednonAcceptée, en attente d’un worker.
submittingnonEn cours d’envoi au fournisseur du modèle.
runningnonLe modèle est en cours de génération.
succeededouiTerminée. Les résultats sont dans assets.
failedouiTerminée sans résultat. La réservation est libérée.
reconciliation_requiredouiThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPCodeSignification et action
401AUTH_REQUIREDClé d’API ou session manquante ou invalide.
403INSUFFICIENT_SCOPELa clé d’API n’a pas la portée requise par ce point de terminaison.
403PERMISSION_DENIEDCet identifiant ne peut pas effectuer cette opération.
429API_KEY_RATE_LIMITEDLa limite de débit de la clé d’API est atteinte. Respectez Retry-After.
429API_KEY_USAGE_EXCEEDEDLa clé d’API a atteint sa limite d’utilisation. Créez une nouvelle clé.
400INVALID_REQUESTLe corps n’est pas un objet JSON ou une valeur obligatoire manque.
400INVALID_IDEMPOTENCY_KEYIdempotency-Key doit comporter de 1 à 128 caractères ASCII imprimables.
400INVALID_MODEL_INPUTinput ne correspond pas au schéma du modèle (champ inconnu, champ obligatoire manquant ou valeur invalide).
400 / 413INPUT_TOO_LARGELe corps de la requête dépasse 256 Ko. Importez d’abord les médias et envoyez une référence média.
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDAucun modèle n’a ce slug.
404JOB_NOT_FOUNDAucune tâche avec cet ID n’appartient à votre compte.
409IDEMPOTENCY_CONFLICTCette Idempotency-Key a été utilisée avec une autre entrée. Utilisez une nouvelle clé pour une nouvelle requête.
409PRICE_CHANGEDLe prix diffère de expectedPriceMicros. Récupérez le prix et confirmez à nouveau.
409MODEL_PRICE_UNAVAILABLEAucun prix n’est encore configuré pour ce modèle ; il ne peut donc pas s’exécuter.
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITSLes crédits disponibles ne couvrent pas le prix de la tâche.
429RATE_LIMITEDTrop de soumissions de tâches par minute. Réessayez plus tard.
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITEDTrop de tâches inachevées. Attendez qu’une tâche se termine.
503EXECUTION_UNAVAILABLEL’exécution n’est pas configurée pour ce modèle actuellement.
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_UNAVAILABLEL’exécution est temporairement indisponible. Réessayez avec la même Idempotency-Key.
503AUTH_UNAVAILABLEL’authentification est temporairement indisponible. Réessayez plus tard.
503API_UNAVAILABLEL’API est temporairement indisponible. Réessayez plus tard.

FAQ de l’API MiniMax H3

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

Can all H3 variants accept audio references?

No. Audio reference fields are listed for the multimodal reference-to-video variant; the other tasks have different input schemas.

What can the MiniMax H3 API do?

MiniMax H3 by MiniMax handles image vers vidéo, texte vers vidéo, vidéo vers vidéo et la référence vers vidéo. The catalog lists 9 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 MiniMax H3 support?

Across its variants, MiniMax H3 supports durations from 5 to 15 seconds, 480p, 768p et la 2K resolution et la aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4 et la 9:16. Each variant accepts its own subset; the variants table on this page lists them.

What input does MiniMax H3 accept?

A text prompt of up to 40,000 characters, plus image, vidéo ou audio input (up to 9 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. Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.

How is MiniMax H3 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 MiniMax H3 variant should I choose?

For image to video, Max turbo image to video, Max image to video et la Image to video differ in fields: Image to video adds aigc_watermark; for text to video, Max turbo text to video, Max text to video et la Text to video differ in fields: Max turbo text to video adds aspectRatio; Max text to video adds ratio; Text to video adds ratio, aigc_watermark; for video to video, Regeneration text to video et la Regeneration image to video differ in fields: Regeneration image to video adds firstFrameUrl, lastFrameUrl; for reference to video, use Multimodal reference to video. Pick the task first, then compare the tiers in the variants table.

How do I call the MiniMax H3 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 MiniMax H3 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.